Hugging Face's logo

ibm-granite
/
granitelib-rag-r1.0

Granite Library
Safetensors
GGUF
English
Model card Files
xet
 Community
61
frreiss commited on
Commit
43c92f1
·
1 Parent(s): a7ded25

remove answer relevance (#19)

Browse files

- Remove answer relevance for now (f06aba57223772103a129049abd881f450c36e40)

This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. answer_relevance_classifier/README.md +0 -156
  2. answer_relevance_classifier/granite-3.3-8b-instruct/alora/adapter_config.json +0 -33
  3. answer_relevance_classifier/granite-3.3-8b-instruct/alora/adapter_model.safetensors +0 -3
  4. answer_relevance_classifier/granite-3.3-8b-instruct/alora/added_tokens.json +0 -9
  5. answer_relevance_classifier/granite-3.3-8b-instruct/alora/io.yaml +0 -58
  6. answer_relevance_classifier/granite-3.3-8b-instruct/alora/merges.txt +0 -0
  7. answer_relevance_classifier/granite-3.3-8b-instruct/alora/special_tokens_map.json +0 -39
  8. answer_relevance_classifier/granite-3.3-8b-instruct/alora/tokenizer.json +0 -0
  9. answer_relevance_classifier/granite-3.3-8b-instruct/alora/tokenizer_config.json +0 -235
  10. answer_relevance_classifier/granite-3.3-8b-instruct/alora/vocab.json +0 -0
  11. answer_relevance_classifier/granite-3.3-8b-instruct/lora/adapter_config.json +0 -33
  12. answer_relevance_classifier/granite-3.3-8b-instruct/lora/adapter_model.safetensors +0 -3
  13. answer_relevance_classifier/granite-3.3-8b-instruct/lora/added_tokens.json +0 -9
  14. answer_relevance_classifier/granite-3.3-8b-instruct/lora/io.yaml +0 -58
  15. answer_relevance_classifier/granite-3.3-8b-instruct/lora/merges.txt +0 -0
  16. answer_relevance_classifier/granite-3.3-8b-instruct/lora/special_tokens_map.json +0 -39
  17. answer_relevance_classifier/granite-3.3-8b-instruct/lora/tokenizer.json +0 -0
  18. answer_relevance_classifier/granite-3.3-8b-instruct/lora/tokenizer_config.json +0 -235
  19. answer_relevance_classifier/granite-3.3-8b-instruct/lora/vocab.json +0 -0
  20. answer_relevance_classifier/granite-4.0-micro/lora/adapter_config.json +0 -42
  21. answer_relevance_classifier/granite-4.0-micro/lora/adapter_model.safetensors +0 -3
  22. answer_relevance_classifier/granite-4.0-micro/lora/chat_template.jinja +0 -118
  23. answer_relevance_classifier/granite-4.0-micro/lora/io.yaml +0 -58
  24. answer_relevance_classifier/granite-4.0-micro/lora/merges.txt +0 -0
  25. answer_relevance_classifier/granite-4.0-micro/lora/special_tokens_map.json +0 -30
  26. answer_relevance_classifier/granite-4.0-micro/lora/tokenizer.json +0 -0
  27. answer_relevance_classifier/granite-4.0-micro/lora/tokenizer_config.json +0 -783
  28. answer_relevance_classifier/granite-4.0-micro/lora/training_args.bin +0 -3
  29. answer_relevance_classifier/granite-4.0-micro/lora/vocab.json +0 -0
  30. answer_relevance_classifier/granite4_micro/lora/Lora-q8_0.gguf +0 -3
  31. answer_relevance_classifier/granite4_micro/lora/Modelfile +0 -2
  32. answer_relevance_classifier/granite4_micro/lora/io.yaml +0 -50
  33. answer_relevance_rewriter/README.md +0 -157
  34. answer_relevance_rewriter/granite-3.3-8b-instruct/alora/adapter_config.json +0 -33
  35. answer_relevance_rewriter/granite-3.3-8b-instruct/alora/adapter_model.safetensors +0 -3
  36. answer_relevance_rewriter/granite-3.3-8b-instruct/alora/added_tokens.json +0 -9
  37. answer_relevance_rewriter/granite-3.3-8b-instruct/alora/io.yaml +0 -29
  38. answer_relevance_rewriter/granite-3.3-8b-instruct/alora/merges.txt +0 -0
  39. answer_relevance_rewriter/granite-3.3-8b-instruct/alora/special_tokens_map.json +0 -39
  40. answer_relevance_rewriter/granite-3.3-8b-instruct/alora/tokenizer.json +0 -0
  41. answer_relevance_rewriter/granite-3.3-8b-instruct/alora/tokenizer_config.json +0 -235
  42. answer_relevance_rewriter/granite-3.3-8b-instruct/alora/vocab.json +0 -0
  43. answer_relevance_rewriter/granite-3.3-8b-instruct/lora/adapter_config.json +0 -33
  44. answer_relevance_rewriter/granite-3.3-8b-instruct/lora/adapter_model.safetensors +0 -3
  45. answer_relevance_rewriter/granite-3.3-8b-instruct/lora/added_tokens.json +0 -9
  46. answer_relevance_rewriter/granite-3.3-8b-instruct/lora/io.yaml +0 -29
  47. answer_relevance_rewriter/granite-3.3-8b-instruct/lora/merges.txt +0 -0
  48. answer_relevance_rewriter/granite-3.3-8b-instruct/lora/special_tokens_map.json +0 -39
  49. answer_relevance_rewriter/granite-3.3-8b-instruct/lora/tokenizer.json +0 -0
  50. answer_relevance_rewriter/granite-3.3-8b-instruct/lora/tokenizer_config.json +0 -235
answer_relevance_classifier/README.md DELETED
@@ -1,156 +0,0 @@
1
- ---
2
- license: apache-2.0
3
- language:
4
- - en
5
- pipeline_tag: text-generation
6
- library_name: peft
7
- library_name: transformers
8
- ---
9
-
10
- # Intrinsics for Answer Relevance Classifier
11
-
12
- ## Model Summary
13
- This is a RAG-specific intrinsic for answer relevance classification task.
14
- The model takes as input a multi-turn conversation ending with assistant response,
15
- and provides a classification of whether the assistant's response is relevant to the
16
- user's final inquiry, as well as categorization of the relevance and reasoning for the conclusions.
17
-
18
-
19
- We provide two intrinsics implemented as LoRA adapters (LoRA/aLoRA) trained over
20
- Granite-3.3-2b-instruct, Granite-3.3-8b-instruct.
21
-
22
- - **Developer:** IBM Research
23
- - **Model type:** LoRA and aLoRA adapter for
24
- [ibm-granite/granite-3.3-2b-instruct](https://huggingface.co/ibm-granite/granite-3.3-2b-instruct),
25
- [ibm-granite/granite-3.3-8b-instruct](https://huggingface.co/ibm-granite/granite-3.3-8b-instruct)
26
- - **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
27
-
28
- ## Intended use
29
- This rag specific intrinsics is intended to be used to post-process the generated assistant response.
30
-
31
- - The binary classification of relevance can be used to determine if the assistance response is suitable
32
- to be given to the user, or a rewrite to a more relevant response is necessary.
33
- - The category and the analysis providing reasoning for the conclusion can be used to
34
- be incorporated into prompt for the answer relevance rewriter, indicating specific directions
35
- the rewrite must take to overcome the perceived deficiency in relevance.
36
-
37
- **Model input**: The input to the answer relevance classifier intrinsic is an
38
- OpenAI-compatible chat completion request, containing a list of conversation
39
- turns that can alternate between the `user` and `assistant` role and ending with
40
- a `assistant` turn.
41
-
42
- **Model output**: The output of the answer relevance classifier intrinsic is the result of the
43
- original chat completion request formatted as a JSON object of the following schema
44
-
45
- {
46
- answer_relevance_analysis: <Free text analysis of whether and in which ways the assistant response is relevant or not>
47
- answer_relevance_category: <One of a set of labels>
48
- answer_relevance_likelihood: <float between 0.0 and 1.0>
49
- }
50
-
51
- The set of labels for `answer_relevance_category` are:
52
- "Pertinent",
53
- "Pertinent with relevant extra",
54
- "Excessive unnecessary information",
55
- "Unduly restrictive",
56
- "Too vague or generic",
57
- "Contextual misalignment",
58
- "Misinterpreted inquiry",
59
- "No attempt"
60
-
61
- Please see the code snippets in the Quickstart Example section below for
62
- examples that illustrate the intrinsic's input/output.
63
-
64
- ## Quickstart Example
65
-
66
- The recommended way to call this intrinsic is through the [Mellea](https://mellea.ai) framework.
67
- Here is some example code for calling this intrinsic from Mellea:
68
- ```
69
- from mellea.backends.huggingface import LocalHFBackend
70
- from mellea.stdlib.base import ChatContext, Document
71
- from mellea.stdlib.chat import Message
72
- from mellea.stdlib.intrinsics import rag
73
-
74
-
75
- backend = LocalHFBackend(model_id="ibm-granite/granite-3.3-2b-instruct")
76
- context = ChatContext().add(Message("user", "Who attended the meeting?"))
77
- documents = [
78
- Document("Meeting attendees: Alice, Bob, Carol."),
79
- Document("Meeting time: 9:00 am to 11:00 am."),
80
- ]
81
- original_result = "Many people attended the meeting."
82
-
83
- print(f"Result before relevance intrinsic: {original_result}")
84
- result = rag.rewrite_answer_for_relevance(original_result, documents, context, backend)
85
- print(f"Result after relevance intrinsic: {result}")
86
- ```
87
-
88
- ## Training Details
89
-
90
- ### Training Data
91
-
92
- The training data is created in the following process
93
- 1. Take the synthetic rag-data-granite dataset, consisting of conversations between user and assistant.
94
- 2. Replace the assistant response by running granite-3.2-intrinsics at temperature 1.0.
95
- 3. Produce answer_relevance_classifier target output using mixtral-large with prompts with in-context examples.
96
- The conversation created in steps 1 and 2 are taken as training input. The json string from step 3
97
- is taken as train target output.
98
-
99
- #### Training Hyperparameters
100
-
101
- The LoRA adapter was fine-tuned using PEFT under the following regime: rank =
102
- 32, learning rate = 3.0e-06, number of epochs = 50.
103
-
104
- ## Evaluation
105
-
106
- ### Answer Relevance Classifier
107
-
108
- We evaluated the model on test data set generated by the same procedure as the training process,
109
- using GPT-4o as judge.
110
-
111
-
112
- The following table presents results comparing baselines and frontier models
113
- on the answer relevance classification task. The LoRAs perform on par with frontier models
114
- of much larger size and outperforms frontier models of comparable size.
115
-
116
- | | Not relevant | | | Relevant | | |
117
- |:------------------------|:----------|:-------|:------|:----------|:-------|:------|
118
- | | precision | recall | f1 | precision | recall | f1 |
119
- | mixtral-8x22b-v0.1 | 0.934 | 0.592 | 0.725 | 0.886 | 0.880 | 0.883 |
120
- | llama-3.3-70b | 0.895 | 0.829 | 0.861 | 0.898 | 0.939 | 0.918 |
121
- | gpt-oss-20b | 0.747 | 0.745 | 0.746 | 0.969 | 0.782 | 0.865 |
122
- | gpt-4o | 0.775 | 0.945 | 0.852 | 0.974 | 0.690 | 0.808 |
123
- | gpt-4o-mini | 0.818 | 0.921 | 0.866 | 0.948 | 0.872 | 0.908 |
124
- | | | | | | | |
125
- | granite-3.3-2b/lora | 0.743 | 0.861 | 0.798 | 0.909 | 0.806 | 0.855 |
126
- | granite-3.3-2b/alora | 0.761 | 0.821 | 0.790 | 0.894 | 0.833 | 0.862 |
127
- | granite-3.3-8b/lora | 0.783 | 0.900 | 0.837 | 0.931 | 0.842 | 0.884 |
128
- | granite-3.3-8b/alora | 0.793 | 0.879 | 0.834 | 0.919 | 0.856 | 0.886 |
129
-
130
-
131
- ### Comparing the Answer Relevance Classifier Intrinsics vs. Vanilla Granite Models
132
-
133
- We compare the performance of Granite 3.3-2b, Granite 3.3-8b Instruct
134
- vs. answer relevance classifier intrinsics implemented as LoRA adapters.
135
- It is seen that the LoRAs significantly out perform the base models.
136
-
137
- | | Not relevant | | | Relevant | | |
138
- |:------------------------|:----------|:-------|:------|:----------|:-------|:------|
139
- | | precision | recall | f1 | precision | recall | f1 |
140
- | granite-3.3-2b | | | | | | |
141
- | granite-3.3-2b/lora | 0.743 | 0.861 | 0.798 | 0.909 | 0.806 | 0.855 |
142
- | granite-3.3-2b/alora | 0.761 | 0.821 | 0.790 | 0.894 | 0.833 | 0.862 |
143
- | | | | | | | |
144
- | granite-3.3-8b | 0.798 | 0.542 | 0.646 | 0.813 | 0.770 | 0.791 |
145
- | granite-3.3-8b/lora | 0.783 | 0.900 | 0.837 | 0.931 | 0.842 | 0.884 |
146
- | granite-3.3-8b/alora | 0.793 | 0.879 | 0.834 | 0.919 | 0.856 | 0.886 |
147
-
148
-
149
-
150
- ## Model Card Authors
151
-
152
- [Huaiyu Zhu](mailto:huaiyu@us.ibm.com)
153
-
154
- ### Framework versions
155
-
156
- - PEFT 0.14.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_classifier/granite-3.3-8b-instruct/alora/adapter_config.json DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "alpha_pattern": {},
3
- "auto_mapping": null,
4
- "base_model_name_or_path": "ibm-granite/granite-3.3-8b-instruct",
5
- "bias": "none",
6
- "eva_config": null,
7
- "exclude_modules": null,
8
- "fan_in_fan_out": false,
9
- "inference_mode": true,
10
- "init_lora_weights": true,
11
- "layer_replication": null,
12
- "layers_pattern": null,
13
- "layers_to_transform": null,
14
- "loftq_config": {},
15
- "lora_alpha": 32,
16
- "lora_bias": false,
17
- "lora_dropout": 0.05,
18
- "megatron_config": null,
19
- "megatron_core": "megatron.core",
20
- "modules_to_save": null,
21
- "peft_type": "LORA",
22
- "r": 32,
23
- "rank_pattern": {},
24
- "revision": null,
25
- "target_modules": [
26
- "q_proj",
27
- "v_proj",
28
- "k_proj"
29
- ],
30
- "task_type": "CAUSAL_LM",
31
- "use_dora": false,
32
- "use_rslora": false
33
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_classifier/granite-3.3-8b-instruct/alora/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7847e2deca119b7dc535f7d260b3000fa4fc6ea3aabc6b7e033de8eb417a054a
3
- size 94404160
 
 
 
 
answer_relevance_classifier/granite-3.3-8b-instruct/alora/added_tokens.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "<|end_of_cite|>": 49156,
3
- "<|end_of_plugin|>": 49158,
4
- "<|end_of_role|>": 49153,
5
- "<|start_of_cite|>": 49155,
6
- "<|start_of_plugin|>": 49157,
7
- "<|start_of_role|>": 49152,
8
- "<|tool_call|>": 49154
9
- }
 
 
 
 
 
 
 
 
 
 
answer_relevance_classifier/granite-3.3-8b-instruct/alora/io.yaml DELETED
@@ -1,58 +0,0 @@
1
- # Model name string, or null to use whatever is provided in the chat completion request
2
- model: ~
3
- # JSON schema of the model's output
4
- response_format: |
5
- {
6
- "properties": {
7
- "answer_relevance_analysis": {
8
- "title": "Answer Relevance Analysis",
9
- "type": "string"
10
- },
11
- "answer_relevance_category": {
12
- "title": "Answer Relevance Category",
13
- "type": "string",
14
- "enum": [
15
- "Pertinent",
16
- "Pertinent with relevant extra",
17
- "Excessive unnecessary information",
18
- "Unduly restrictive",
19
- "Too vague or generic",
20
- "Contextual misalignment",
21
- "Misinterpreted inquiry",
22
- "No attempt"
23
- ]
24
- },
25
- "answer_relevance_judgment": {
26
- "title": "Answer Relevance Judgment",
27
- "type": "boolean"
28
- }
29
- },
30
- "required": [
31
- "answer_relevance_analysis",
32
- "answer_relevance_category",
33
- "answer_relevance_judgment"
34
- ],
35
- "title": "AnswerRelevanceRawOutput",
36
- "type": "object"
37
- }
38
- # Additional turn of instructions to add to the chat
39
- instruction: "answer_relevance"
40
- # Data transformations to perform during post-processing
41
- transformations:
42
- # Convert categorical answer to continuous value by decoding logprobs
43
- - type: likelihood
44
- categories_to_values:
45
- true: 1.0
46
- false: 0.0
47
- input_path: ["answer_relevance_judgment"]
48
- # Rename answer_relevance_judgment column to reflect likelihood transformation
49
- - type: project
50
- input_path: []
51
- retained_fields:
52
- "answer_relevance_analysis": "answer_relevance_analysis"
53
- "answer_relevance_category": "answer_relevance_category"
54
- "answer_relevance_judgment": "answer_relevance_likelihood"
55
- parameters:
56
- # Current LoRA can be quite verbose in its explanations.
57
- max_completion_tokens: 1024
58
- sentence_boundaries: ~
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_classifier/granite-3.3-8b-instruct/alora/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
answer_relevance_classifier/granite-3.3-8b-instruct/alora/special_tokens_map.json DELETED
@@ -1,39 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|start_of_role|>",
4
- "<|end_of_role|>",
5
- "<|tool_call|>",
6
- "<|start_of_cite|>",
7
- "<|end_of_cite|>",
8
- "<|start_of_plugin|>",
9
- "<|end_of_plugin|>"
10
- ],
11
- "bos_token": {
12
- "content": "<|end_of_text|>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false
17
- },
18
- "eos_token": {
19
- "content": "<|end_of_text|>",
20
- "lstrip": false,
21
- "normalized": false,
22
- "rstrip": false,
23
- "single_word": false
24
- },
25
- "pad_token": {
26
- "content": "<|end_of_text|>",
27
- "lstrip": false,
28
- "normalized": false,
29
- "rstrip": false,
30
- "single_word": false
31
- },
32
- "unk_token": {
33
- "content": "<|end_of_text|>",
34
- "lstrip": false,
35
- "normalized": false,
36
- "rstrip": false,
37
- "single_word": false
38
- }
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_classifier/granite-3.3-8b-instruct/alora/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
answer_relevance_classifier/granite-3.3-8b-instruct/alora/tokenizer_config.json DELETED
@@ -1,235 +0,0 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<|end_of_text|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<fim_prefix>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "<fim_middle>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "3": {
30
- "content": "<fim_suffix>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "4": {
38
- "content": "<fim_pad>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "5": {
46
- "content": "<filename>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "6": {
54
- "content": "<gh_stars>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "7": {
62
- "content": "<issue_start>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "8": {
70
- "content": "<issue_comment>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "9": {
78
- "content": "<issue_closed>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "10": {
86
- "content": "<jupyter_start>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "11": {
94
- "content": "<jupyter_text>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "12": {
102
- "content": "<jupyter_code>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "13": {
110
- "content": "<jupyter_output>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "14": {
118
- "content": "<empty_output>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": true
124
- },
125
- "15": {
126
- "content": "<commit_before>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": true
132
- },
133
- "16": {
134
- "content": "<commit_msg>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": true
140
- },
141
- "17": {
142
- "content": "<commit_after>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": true
148
- },
149
- "18": {
150
- "content": "<reponame>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": true
156
- },
157
- "49152": {
158
- "content": "<|start_of_role|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": true
164
- },
165
- "49153": {
166
- "content": "<|end_of_role|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": true
172
- },
173
- "49154": {
174
- "content": "<|tool_call|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": true
180
- },
181
- "49155": {
182
- "content": "<|start_of_cite|>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "49156": {
190
- "content": "<|end_of_cite|>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": true
196
- },
197
- "49157": {
198
- "content": "<|start_of_plugin|>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": true
204
- },
205
- "49158": {
206
- "content": "<|end_of_plugin|>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": true
212
- }
213
- },
214
- "additional_special_tokens": [
215
- "<|start_of_role|>",
216
- "<|end_of_role|>",
217
- "<|tool_call|>",
218
- "<|start_of_cite|>",
219
- "<|end_of_cite|>",
220
- "<|start_of_plugin|>",
221
- "<|end_of_plugin|>"
222
- ],
223
- "bos_token": "<|end_of_text|>",
224
- "chat_template": "{# Alias tools -> available_tools #}\n{%- if tools and not available_tools -%}\n {%- set available_tools = tools -%}\n{%- endif -%}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set loop_messages = messages[1:] %}\n {%- else %}\n {%- set system_message = \"Knowledge Cutoff Date: April 2024.\nToday's Date: \" + strftime_now('%B %d, %Y') + \".\nYou are Granite, developed by IBM.\" %}\n {%- if available_tools and documents %}\n {%- set system_message = system_message + \" You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.\nWrite the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.\" %}\n {%- elif available_tools %}\n {%- set system_message = system_message + \" You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.\" %}\n {%- elif documents %}\n {%- set system_message = system_message + \" Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.\" %}\n {%- elif thinking %}\n {%- set system_message = system_message + \" You are a helpful AI assistant.\nRespond to every user query in a comprehensive and detailed way. You can write down your thoughts and reasoning process before responding. In the thought process, engage in a comprehensive cycle of analysis, summarization, exploration, reassessment, reflection, backtracing, and iteration to develop well-considered thinking process. In the response section, based on various attempts, explorations, and reflections from the thoughts section, systematically present the final solution that you deem correct. The response should summarize the thought process. Write your thoughts between <think></think> and write your response between <response></response> for each user query.\" %}\n {%- else %}\n {%- set system_message = system_message + \" You are a helpful AI assistant.\" %}\n {%- endif %}\n {%- if 'citations' in controls and documents %}\n {%- set system_message = system_message + '\nUse the symbols <|start_of_cite|> and <|end_of_cite|> to indicate when a fact comes from a document in the search result, e.g <|start_of_cite|> {document_id: 1}my fact <|end_of_cite|> for a fact from document 1. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}\n {%- endif %}\n {%- if 'hallucinations' in controls and documents %}\n {%- set system_message = system_message + '\nFinally, after the response is written, include a numbered list of sentences from the response with a corresponding risk value that are hallucinated and not based in the documents.' %}\n {%- endif %}\n {%- set loop_messages = messages %}\n {%- endif %}\n {{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>\n' }}\n {%- if available_tools %}\n {{- '<|start_of_role|>available_tools<|end_of_role|>' }}\n {{- available_tools | tojson(indent=4) }}\n {{- '<|end_of_text|>\n' }}\n {%- endif %}\n {%- if documents %}\n {%- for document in documents %}\n {{- '<|start_of_role|>document {\"document_id\": \"' + document['doc_id'] | string + '\"}<|end_of_role|>\n' }}\n {{- document['text'] }}\n {{- '<|end_of_text|>\n' }}\n {%- endfor %}\n {%- endif %}\n {%- for message in loop_messages %}\n {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- if loop.last and add_generation_prompt %}\n {{- '<|start_of_role|>assistant' }}\n {%- if controls %}\n {{- ' ' + controls | tojson()}}\n {%- endif %}\n {{- '<|end_of_role|>' }}\n {%- endif %}\n {%- endfor %}",
225
- "clean_up_tokenization_spaces": true,
226
- "eos_token": "<|end_of_text|>",
227
- "errors": "replace",
228
- "extra_special_tokens": {},
229
- "model_max_length": 9223372036854775807,
230
- "pad_token": "<|end_of_text|>",
231
- "padding_side": "left",
232
- "tokenizer_class": "GPT2Tokenizer",
233
- "unk_token": "<|end_of_text|>",
234
- "vocab_size": 49152
235
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_classifier/granite-3.3-8b-instruct/alora/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
answer_relevance_classifier/granite-3.3-8b-instruct/lora/adapter_config.json DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "alpha_pattern": {},
3
- "auto_mapping": null,
4
- "base_model_name_or_path": "ibm-granite/granite-3.3-8b-instruct",
5
- "bias": "none",
6
- "eva_config": null,
7
- "exclude_modules": null,
8
- "fan_in_fan_out": false,
9
- "inference_mode": true,
10
- "init_lora_weights": true,
11
- "layer_replication": null,
12
- "layers_pattern": null,
13
- "layers_to_transform": null,
14
- "loftq_config": {},
15
- "lora_alpha": 32,
16
- "lora_bias": false,
17
- "lora_dropout": 0.05,
18
- "megatron_config": null,
19
- "megatron_core": "megatron.core",
20
- "modules_to_save": null,
21
- "peft_type": "LORA",
22
- "r": 32,
23
- "rank_pattern": {},
24
- "revision": null,
25
- "target_modules": [
26
- "k_proj",
27
- "q_proj",
28
- "v_proj"
29
- ],
30
- "task_type": "CAUSAL_LM",
31
- "use_dora": false,
32
- "use_rslora": false
33
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_classifier/granite-3.3-8b-instruct/lora/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:27c8cf16a5ea98e110df54e433c43432ee8f18373f673293989e1deacee29cd7
3
- size 94404160
 
 
 
 
answer_relevance_classifier/granite-3.3-8b-instruct/lora/added_tokens.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "<|end_of_cite|>": 49156,
3
- "<|end_of_plugin|>": 49158,
4
- "<|end_of_role|>": 49153,
5
- "<|start_of_cite|>": 49155,
6
- "<|start_of_plugin|>": 49157,
7
- "<|start_of_role|>": 49152,
8
- "<|tool_call|>": 49154
9
- }
 
 
 
 
 
 
 
 
 
 
answer_relevance_classifier/granite-3.3-8b-instruct/lora/io.yaml DELETED
@@ -1,58 +0,0 @@
1
- # Model name string, or null to use whatever is provided in the chat completion request
2
- model: ~
3
- # JSON schema of the model's output
4
- response_format: |
5
- {
6
- "properties": {
7
- "answer_relevance_analysis": {
8
- "title": "Answer Relevance Analysis",
9
- "type": "string"
10
- },
11
- "answer_relevance_category": {
12
- "title": "Answer Relevance Category",
13
- "type": "string",
14
- "enum": [
15
- "Pertinent",
16
- "Pertinent with relevant extra",
17
- "Excessive unnecessary information",
18
- "Unduly restrictive",
19
- "Too vague or generic",
20
- "Contextual misalignment",
21
- "Misinterpreted inquiry",
22
- "No attempt"
23
- ]
24
- },
25
- "answer_relevance_judgment": {
26
- "title": "Answer Relevance Judgment",
27
- "type": "boolean"
28
- }
29
- },
30
- "required": [
31
- "answer_relevance_analysis",
32
- "answer_relevance_category",
33
- "answer_relevance_judgment"
34
- ],
35
- "title": "AnswerRelevanceRawOutput",
36
- "type": "object"
37
- }
38
- # Additional turn of instructions to add to the chat
39
- instruction: "answer_relevance"
40
- # Data transformations to perform during post-processing
41
- transformations:
42
- # Convert categorical answer to continuous value by decoding logprobs
43
- - type: likelihood
44
- categories_to_values:
45
- true: 1.0
46
- false: 0.0
47
- input_path: ["answer_relevance_judgment"]
48
- # Rename answer_relevance_judgment column to reflect likelihood transformation
49
- - type: project
50
- input_path: []
51
- retained_fields:
52
- "answer_relevance_analysis": "answer_relevance_analysis"
53
- "answer_relevance_category": "answer_relevance_category"
54
- "answer_relevance_judgment": "answer_relevance_likelihood"
55
- parameters:
56
- # Current LoRA can be quite verbose in its explanations.
57
- max_completion_tokens: 1024
58
- sentence_boundaries: ~
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_classifier/granite-3.3-8b-instruct/lora/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
answer_relevance_classifier/granite-3.3-8b-instruct/lora/special_tokens_map.json DELETED
@@ -1,39 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|start_of_role|>",
4
- "<|end_of_role|>",
5
- "<|tool_call|>",
6
- "<|start_of_cite|>",
7
- "<|end_of_cite|>",
8
- "<|start_of_plugin|>",
9
- "<|end_of_plugin|>"
10
- ],
11
- "bos_token": {
12
- "content": "<|end_of_text|>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false
17
- },
18
- "eos_token": {
19
- "content": "<|end_of_text|>",
20
- "lstrip": false,
21
- "normalized": false,
22
- "rstrip": false,
23
- "single_word": false
24
- },
25
- "pad_token": {
26
- "content": "<|end_of_text|>",
27
- "lstrip": false,
28
- "normalized": false,
29
- "rstrip": false,
30
- "single_word": false
31
- },
32
- "unk_token": {
33
- "content": "<|end_of_text|>",
34
- "lstrip": false,
35
- "normalized": false,
36
- "rstrip": false,
37
- "single_word": false
38
- }
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_classifier/granite-3.3-8b-instruct/lora/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
answer_relevance_classifier/granite-3.3-8b-instruct/lora/tokenizer_config.json DELETED
@@ -1,235 +0,0 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<|end_of_text|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<fim_prefix>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "<fim_middle>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "3": {
30
- "content": "<fim_suffix>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "4": {
38
- "content": "<fim_pad>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "5": {
46
- "content": "<filename>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "6": {
54
- "content": "<gh_stars>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "7": {
62
- "content": "<issue_start>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "8": {
70
- "content": "<issue_comment>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "9": {
78
- "content": "<issue_closed>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "10": {
86
- "content": "<jupyter_start>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "11": {
94
- "content": "<jupyter_text>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "12": {
102
- "content": "<jupyter_code>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "13": {
110
- "content": "<jupyter_output>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "14": {
118
- "content": "<empty_output>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": true
124
- },
125
- "15": {
126
- "content": "<commit_before>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": true
132
- },
133
- "16": {
134
- "content": "<commit_msg>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": true
140
- },
141
- "17": {
142
- "content": "<commit_after>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": true
148
- },
149
- "18": {
150
- "content": "<reponame>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": true
156
- },
157
- "49152": {
158
- "content": "<|start_of_role|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": true
164
- },
165
- "49153": {
166
- "content": "<|end_of_role|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": true
172
- },
173
- "49154": {
174
- "content": "<|tool_call|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": true
180
- },
181
- "49155": {
182
- "content": "<|start_of_cite|>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "49156": {
190
- "content": "<|end_of_cite|>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": true
196
- },
197
- "49157": {
198
- "content": "<|start_of_plugin|>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": true
204
- },
205
- "49158": {
206
- "content": "<|end_of_plugin|>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": true
212
- }
213
- },
214
- "additional_special_tokens": [
215
- "<|start_of_role|>",
216
- "<|end_of_role|>",
217
- "<|tool_call|>",
218
- "<|start_of_cite|>",
219
- "<|end_of_cite|>",
220
- "<|start_of_plugin|>",
221
- "<|end_of_plugin|>"
222
- ],
223
- "bos_token": "<|end_of_text|>",
224
- "chat_template": "{# Alias tools -> available_tools #}\n{%- if tools and not available_tools -%}\n {%- set available_tools = tools -%}\n{%- endif -%}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set loop_messages = messages[1:] %}\n {%- else %}\n {%- set system_message = \"Knowledge Cutoff Date: April 2024.\nToday's Date: \" + strftime_now('%B %d, %Y') + \".\nYou are Granite, developed by IBM.\" %}\n {%- if available_tools and documents %}\n {%- set system_message = system_message + \" You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.\nWrite the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.\" %}\n {%- elif available_tools %}\n {%- set system_message = system_message + \" You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.\" %}\n {%- elif documents %}\n {%- set system_message = system_message + \" Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.\" %}\n {%- elif thinking %}\n {%- set system_message = system_message + \" You are a helpful AI assistant.\nRespond to every user query in a comprehensive and detailed way. You can write down your thoughts and reasoning process before responding. In the thought process, engage in a comprehensive cycle of analysis, summarization, exploration, reassessment, reflection, backtracing, and iteration to develop well-considered thinking process. In the response section, based on various attempts, explorations, and reflections from the thoughts section, systematically present the final solution that you deem correct. The response should summarize the thought process. Write your thoughts between <think></think> and write your response between <response></response> for each user query.\" %}\n {%- else %}\n {%- set system_message = system_message + \" You are a helpful AI assistant.\" %}\n {%- endif %}\n {%- if 'citations' in controls and documents %}\n {%- set system_message = system_message + '\nUse the symbols <|start_of_cite|> and <|end_of_cite|> to indicate when a fact comes from a document in the search result, e.g <|start_of_cite|> {document_id: 1}my fact <|end_of_cite|> for a fact from document 1. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}\n {%- endif %}\n {%- if 'hallucinations' in controls and documents %}\n {%- set system_message = system_message + '\nFinally, after the response is written, include a numbered list of sentences from the response with a corresponding risk value that are hallucinated and not based in the documents.' %}\n {%- endif %}\n {%- set loop_messages = messages %}\n {%- endif %}\n {{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>\n' }}\n {%- if available_tools %}\n {{- '<|start_of_role|>available_tools<|end_of_role|>' }}\n {{- available_tools | tojson(indent=4) }}\n {{- '<|end_of_text|>\n' }}\n {%- endif %}\n {%- if documents %}\n {%- for document in documents %}\n {{- '<|start_of_role|>document {\"document_id\": \"' + document['doc_id'] | string + '\"}<|end_of_role|>\n' }}\n {{- document['text'] }}\n {{- '<|end_of_text|>\n' }}\n {%- endfor %}\n {%- endif %}\n {%- for message in loop_messages %}\n {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- if loop.last and add_generation_prompt %}\n {{- '<|start_of_role|>assistant' }}\n {%- if controls %}\n {{- ' ' + controls | tojson()}}\n {%- endif %}\n {{- '<|end_of_role|>' }}\n {%- endif %}\n {%- endfor %}",
225
- "clean_up_tokenization_spaces": true,
226
- "eos_token": "<|end_of_text|>",
227
- "errors": "replace",
228
- "extra_special_tokens": {},
229
- "model_max_length": 9223372036854775807,
230
- "pad_token": "<|end_of_text|>",
231
- "padding_side": "left",
232
- "tokenizer_class": "GPT2Tokenizer",
233
- "unk_token": "<|end_of_text|>",
234
- "vocab_size": 49152
235
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_classifier/granite-3.3-8b-instruct/lora/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
answer_relevance_classifier/granite-4.0-micro/lora/adapter_config.json DELETED
@@ -1,42 +0,0 @@
1
- {
2
- "alora_invocation_tokens": null,
3
- "alpha_pattern": {},
4
- "arrow_config": null,
5
- "auto_mapping": null,
6
- "base_model_name_or_path": "ibm-granite/granite-4.0-micro",
7
- "bias": "none",
8
- "corda_config": null,
9
- "ensure_weight_tying": false,
10
- "eva_config": null,
11
- "exclude_modules": null,
12
- "fan_in_fan_out": false,
13
- "inference_mode": true,
14
- "init_lora_weights": true,
15
- "layer_replication": null,
16
- "layers_pattern": null,
17
- "layers_to_transform": null,
18
- "loftq_config": {},
19
- "lora_alpha": 32,
20
- "lora_bias": false,
21
- "lora_dropout": 0.05,
22
- "megatron_config": null,
23
- "megatron_core": "megatron.core",
24
- "modules_to_save": null,
25
- "peft_type": "LORA",
26
- "peft_version": "0.17.2.dev0@98a88c01a42be4bb2fa13a1c0dd5340c42f82c87",
27
- "qalora_group_size": 16,
28
- "r": 32,
29
- "rank_pattern": {},
30
- "revision": null,
31
- "target_modules": [
32
- "k_proj",
33
- "v_proj",
34
- "q_proj"
35
- ],
36
- "target_parameters": null,
37
- "task_type": "CAUSAL_LM",
38
- "trainable_token_indices": null,
39
- "use_dora": false,
40
- "use_qalora": false,
41
- "use_rslora": false
42
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_classifier/granite-4.0-micro/lora/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c2e3569f17bbe2ccd7f6d6c52ce879ae1f04258b0fba908bec4ee99fc4c0b6f
3
- size 57703888
 
 
 
 
answer_relevance_classifier/granite-4.0-micro/lora/chat_template.jinja DELETED
@@ -1,118 +0,0 @@
1
- {%- set tools_system_message_prefix = 'You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>' %}
2
- {%- set tools_system_message_suffix = '\n</tools>\n\nFor each tool call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call>. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.' %}
3
- {%- set documents_system_message_prefix = 'You are a helpful assistant with access to the following documents. You may use one or more documents to assist with the user query.\n\nYou are given a list of documents within <documents></documents> XML tags:\n<documents>' %}
4
- {%- set documents_system_message_suffix = '\n</documents>\n\nWrite the response to the user\'s input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.' %}
5
- {%- set g4_default_system_message = 'You are a helpful assistant. Please ensure responses are professional, accurate, and safe.' %}
6
- {%- if available_tools is defined and available_tools %}
7
- {%- set tools = available_tools %}
8
- {%- endif %}
9
- {%- set ns = namespace(tools_system_message=tools_system_message_prefix,
10
- documents_system_message=documents_system_message_prefix,
11
- default_system_message=g4_default_system_message,
12
- system_message=''
13
- ) %}
14
- {%- if tools %}
15
- {%- for tool in tools %}
16
- {%- set ns.tools_system_message = ns.tools_system_message + '\n' + (tool | tojson) %}
17
- {%- endfor %}
18
- {%- set ns.tools_system_message = ns.tools_system_message + tools_system_message_suffix %}
19
- {%- else %}
20
- {%- set ns.tools_system_message = '' %}
21
- {%- endif %}
22
- {%- if documents %}
23
- {%- for document in documents %}
24
- {%- set ns.documents_system_message = ns.documents_system_message + '\n' + (document | tojson) %}
25
- {%- endfor %}
26
- {%- set ns.documents_system_message = ns.documents_system_message + documents_system_message_suffix %}
27
- {%- else %}
28
- {%- set ns.documents_system_message = '' %}
29
- {%- endif %}
30
- {%- if messages[0].role == 'system' %}
31
- {%- if messages[0].content is string %}
32
- {%- set ns.system_message = messages[0].content %}
33
- {%- elif messages[0].content is iterable %}
34
- {%- for entry in messages[0].content %}
35
- {%- if entry.type== 'text' %}
36
- {%- if ns.system_message != '' %}
37
- {%- set ns.system_message = ns.system_message + '\n' %}
38
- {%- endif %}
39
- {%- set ns.system_message = ns.system_message + entry.text %}
40
- {%- endif %}
41
- {%- endfor %}
42
- {%- endif %}
43
- {%- if tools and documents %}
44
- {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message + '\n\n' + ns.documents_system_message %}
45
- {%- elif tools %}
46
- {%- set ns.system_message = ns.system_message + '\n\n' + ns.tools_system_message %}
47
- {%- elif documents %}
48
- {%- set ns.system_message = ns.system_message + '\n\n' + ns.documents_system_message %}
49
- {%- endif %}
50
- {%- else %}
51
- {%- if tools and documents %}
52
- {%- set ns.system_message = ns.tools_system_message + '\n\n' + ns.documents_system_message %}
53
- {%- elif tools %}
54
- {%- set ns.system_message = ns.tools_system_message %}
55
- {%- elif documents %}
56
- {%- set ns.system_message = ns.documents_system_message %}
57
- {%- endif %}
58
- {%- endif %}
59
- {%- if ns.system_message %}
60
- {{- '<|start_of_role|>system<|end_of_role|>' + ns.system_message + '<|end_of_text|>\n' }}
61
- {%- else %}
62
- {{- '<|start_of_role|>system<|end_of_role|>' + ns.default_system_message + '<|end_of_text|>\n' }}
63
- {%- endif %}
64
- {%- for message in messages %}
65
- {%- set content = namespace(val='') %}
66
- {%- if message.content is string %}
67
- {%- set content.val = message.content %}
68
- {%- else %}
69
- {%- if message.content is iterable %}
70
- {%- for entry in message.content %}
71
- {%- if entry.type== 'text' %}
72
- {%- if content.val != '' %}
73
- {%- set content.val = content.val + '\n' %}
74
- {%- endif %}
75
- {%- set content.val = content.val + entry.text %}
76
- {%- endif %}
77
- {%- endfor %}
78
- {%- endif %}
79
- {%- endif %}
80
- {%- if (message.role == 'user') or (message.role == 'system' and not loop.first) %}
81
- {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val + '<|end_of_text|>\n' }}
82
- {%- elif message.role == 'assistant' %}
83
- {{- '<|start_of_role|>' + message.role + '<|end_of_role|>' + content.val }}
84
- {%- if message.tool_calls %}
85
- {%- for tool_call in message.tool_calls %}
86
- {%- if (loop.first and content.val) or (not loop.first) %}
87
- {{- '\n' }}
88
- {%- endif %}
89
- {%- if tool_call.function %}
90
- {%- set tool_call = tool_call.function %}
91
- {%- endif %}
92
- {{- '<tool_call>\n{"name": "' }}
93
- {{- tool_call.name }}
94
- {{- '", "arguments": ' }}
95
- {%- if tool_call.arguments is string %}
96
- {{- tool_call.arguments }}
97
- {%- else %}
98
- {{- tool_call.arguments | tojson }}
99
- {%- endif %}
100
- {{- '}\n</tool_call>' }}
101
- {%- endfor %}
102
- {%- endif %}
103
- {{- '<|end_of_text|>\n' }}
104
- {%- elif message.role == 'tool' %}
105
- {%- if loop.first or (messages[loop.index0 - 1].role != 'tool') %}
106
- {{- '<|start_of_role|>user<|end_of_role|>' }}
107
- {%- endif %}
108
- {{- '\n<tool_response>\n' }}
109
- {{- content.val }}
110
- {{- '\n</tool_response>' }}
111
- {%- if loop.last or (messages[loop.index0 + 1].role != 'tool') %}
112
- {{- '<|end_of_text|>\n' }}
113
- {%- endif %}
114
- {%- endif %}
115
- {%- endfor %}
116
- {%- if add_generation_prompt %}
117
- {{- '<|start_of_role|>assistant<|end_of_role|>' }}
118
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_classifier/granite-4.0-micro/lora/io.yaml DELETED
@@ -1,58 +0,0 @@
1
- # Model name string, or null to use whatever is provided in the chat completion request
2
- model: ~
3
- # JSON schema of the model's output
4
- response_format: |
5
- {
6
- "properties": {
7
- "answer_relevance_analysis": {
8
- "title": "Answer Relevance Analysis",
9
- "type": "string"
10
- },
11
- "answer_relevance_category": {
12
- "title": "Answer Relevance Category",
13
- "type": "string",
14
- "enum": [
15
- "Pertinent",
16
- "Pertinent with relevant extra",
17
- "Excessive unnecessary information",
18
- "Unduly restrictive",
19
- "Too vague or generic",
20
- "Contextual misalignment",
21
- "Misinterpreted inquiry",
22
- "No attempt"
23
- ]
24
- },
25
- "answer_relevance_judgment": {
26
- "title": "Answer Relevance Judgment",
27
- "type": "boolean"
28
- }
29
- },
30
- "required": [
31
- "answer_relevance_analysis",
32
- "answer_relevance_category",
33
- "answer_relevance_judgment"
34
- ],
35
- "title": "AnswerRelevanceRawOutput",
36
- "type": "object"
37
- }
38
- # Additional turn of instructions to add to the chat
39
- instruction: "answer_relevance"
40
- # Data transformations to perform during post-processing
41
- transformations:
42
- # Convert categorical answer to continuous value by decoding logprobs
43
- - type: likelihood
44
- categories_to_values:
45
- true: 1.0
46
- false: 0.0
47
- input_path: ["answer_relevance_judgment"]
48
- # Rename answer_relevance_judgment column to reflect likelihood transformation
49
- - type: project
50
- input_path: []
51
- retained_fields:
52
- "answer_relevance_analysis": "answer_relevance_analysis"
53
- "answer_relevance_category": "answer_relevance_category"
54
- "answer_relevance_judgment": "answer_relevance_likelihood"
55
- parameters:
56
- # Current LoRA can be quite verbose in its explanations.
57
- max_completion_tokens: 1024
58
- sentence_boundaries: ~
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_classifier/granite-4.0-micro/lora/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
answer_relevance_classifier/granite-4.0-micro/lora/special_tokens_map.json DELETED
@@ -1,30 +0,0 @@
1
- {
2
- "bos_token": {
3
- "content": "<|end_of_text|>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "<|end_of_text|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
- "content": "<|pad|>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "unk_token": {
24
- "content": "<|unk|>",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- }
30
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_classifier/granite-4.0-micro/lora/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
answer_relevance_classifier/granite-4.0-micro/lora/tokenizer_config.json DELETED
@@ -1,783 +0,0 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "100256": {
6
- "content": "<|pad|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "100257": {
14
- "content": "<|end_of_text|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "100258": {
22
- "content": "<|fim_prefix|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": false
28
- },
29
- "100259": {
30
- "content": "<|fim_middle|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": false
36
- },
37
- "100260": {
38
- "content": "<|fim_suffix|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": false
44
- },
45
- "100261": {
46
- "content": "<|fim_pad|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": false
52
- },
53
- "100262": {
54
- "content": "<|filename|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": false
60
- },
61
- "100263": {
62
- "content": "<|reponame|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": false
68
- },
69
- "100264": {
70
- "content": "<|start_of_role|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "100265": {
78
- "content": "<|end_of_role|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "100266": {
86
- "content": "<|unused_1|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "100267": {
94
- "content": "<|start_of_plugin|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "100268": {
102
- "content": "<|end_of_plugin|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "100269": {
110
- "content": "<|unk|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "100270": {
118
- "content": "<tool_call>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- },
125
- "100271": {
126
- "content": "</tool_call>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": false
132
- },
133
- "100272": {
134
- "content": "<tool_response>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": false
140
- },
141
- "100273": {
142
- "content": "</tool_response>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": false
148
- },
149
- "100274": {
150
- "content": "<think>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": false
156
- },
157
- "100275": {
158
- "content": "</think>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": false
164
- },
165
- "100276": {
166
- "content": "<think_on>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": true
172
- },
173
- "100277": {
174
- "content": "<think_off>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": true
180
- },
181
- "100278": {
182
- "content": "<schema>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "100279": {
190
- "content": "</schema>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": true
196
- },
197
- "100280": {
198
- "content": "<tools>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": true
204
- },
205
- "100281": {
206
- "content": "</tools>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": true
212
- },
213
- "100282": {
214
- "content": "<documents>",
215
- "lstrip": false,
216
- "normalized": false,
217
- "rstrip": false,
218
- "single_word": false,
219
- "special": true
220
- },
221
- "100283": {
222
- "content": "</documents>",
223
- "lstrip": false,
224
- "normalized": false,
225
- "rstrip": false,
226
- "single_word": false,
227
- "special": true
228
- },
229
- "100284": {
230
- "content": "<|unused_15|>",
231
- "lstrip": false,
232
- "normalized": false,
233
- "rstrip": false,
234
- "single_word": false,
235
- "special": true
236
- },
237
- "100285": {
238
- "content": "<|unused_16|>",
239
- "lstrip": false,
240
- "normalized": false,
241
- "rstrip": false,
242
- "single_word": false,
243
- "special": true
244
- },
245
- "100286": {
246
- "content": "<|unused_17|>",
247
- "lstrip": false,
248
- "normalized": false,
249
- "rstrip": false,
250
- "single_word": false,
251
- "special": true
252
- },
253
- "100287": {
254
- "content": "<|unused_18|>",
255
- "lstrip": false,
256
- "normalized": false,
257
- "rstrip": false,
258
- "single_word": false,
259
- "special": true
260
- },
261
- "100288": {
262
- "content": "<|unused_19|>",
263
- "lstrip": false,
264
- "normalized": false,
265
- "rstrip": false,
266
- "single_word": false,
267
- "special": true
268
- },
269
- "100289": {
270
- "content": "<|unused_20|>",
271
- "lstrip": false,
272
- "normalized": false,
273
- "rstrip": false,
274
- "single_word": false,
275
- "special": true
276
- },
277
- "100290": {
278
- "content": "<|unused_21|>",
279
- "lstrip": false,
280
- "normalized": false,
281
- "rstrip": false,
282
- "single_word": false,
283
- "special": true
284
- },
285
- "100291": {
286
- "content": "<|unused_22|>",
287
- "lstrip": false,
288
- "normalized": false,
289
- "rstrip": false,
290
- "single_word": false,
291
- "special": true
292
- },
293
- "100292": {
294
- "content": "<|unused_23|>",
295
- "lstrip": false,
296
- "normalized": false,
297
- "rstrip": false,
298
- "single_word": false,
299
- "special": true
300
- },
301
- "100293": {
302
- "content": "<|unused_24|>",
303
- "lstrip": false,
304
- "normalized": false,
305
- "rstrip": false,
306
- "single_word": false,
307
- "special": true
308
- },
309
- "100294": {
310
- "content": "<|unused_25|>",
311
- "lstrip": false,
312
- "normalized": false,
313
- "rstrip": false,
314
- "single_word": false,
315
- "special": true
316
- },
317
- "100295": {
318
- "content": "<|unused_26|>",
319
- "lstrip": false,
320
- "normalized": false,
321
- "rstrip": false,
322
- "single_word": false,
323
- "special": true
324
- },
325
- "100296": {
326
- "content": "<|unused_27|>",
327
- "lstrip": false,
328
- "normalized": false,
329
- "rstrip": false,
330
- "single_word": false,
331
- "special": true
332
- },
333
- "100297": {
334
- "content": "<|unused_28|>",
335
- "lstrip": false,
336
- "normalized": false,
337
- "rstrip": false,
338
- "single_word": false,
339
- "special": true
340
- },
341
- "100298": {
342
- "content": "<|unused_29|>",
343
- "lstrip": false,
344
- "normalized": false,
345
- "rstrip": false,
346
- "single_word": false,
347
- "special": true
348
- },
349
- "100299": {
350
- "content": "<|unused_30|>",
351
- "lstrip": false,
352
- "normalized": false,
353
- "rstrip": false,
354
- "single_word": false,
355
- "special": true
356
- },
357
- "100300": {
358
- "content": "<|unused_31|>",
359
- "lstrip": false,
360
- "normalized": false,
361
- "rstrip": false,
362
- "single_word": false,
363
- "special": true
364
- },
365
- "100301": {
366
- "content": "<|unused_32|>",
367
- "lstrip": false,
368
- "normalized": false,
369
- "rstrip": false,
370
- "single_word": false,
371
- "special": true
372
- },
373
- "100302": {
374
- "content": "<|unused_33|>",
375
- "lstrip": false,
376
- "normalized": false,
377
- "rstrip": false,
378
- "single_word": false,
379
- "special": true
380
- },
381
- "100303": {
382
- "content": "<|unused_34|>",
383
- "lstrip": false,
384
- "normalized": false,
385
- "rstrip": false,
386
- "single_word": false,
387
- "special": true
388
- },
389
- "100304": {
390
- "content": "<|unused_35|>",
391
- "lstrip": false,
392
- "normalized": false,
393
- "rstrip": false,
394
- "single_word": false,
395
- "special": true
396
- },
397
- "100305": {
398
- "content": "<|unused_36|>",
399
- "lstrip": false,
400
- "normalized": false,
401
- "rstrip": false,
402
- "single_word": false,
403
- "special": true
404
- },
405
- "100306": {
406
- "content": "<|unused_37|>",
407
- "lstrip": false,
408
- "normalized": false,
409
- "rstrip": false,
410
- "single_word": false,
411
- "special": true
412
- },
413
- "100307": {
414
- "content": "<|unused_38|>",
415
- "lstrip": false,
416
- "normalized": false,
417
- "rstrip": false,
418
- "single_word": false,
419
- "special": true
420
- },
421
- "100308": {
422
- "content": "<|unused_39|>",
423
- "lstrip": false,
424
- "normalized": false,
425
- "rstrip": false,
426
- "single_word": false,
427
- "special": true
428
- },
429
- "100309": {
430
- "content": "<|unused_40|>",
431
- "lstrip": false,
432
- "normalized": false,
433
- "rstrip": false,
434
- "single_word": false,
435
- "special": true
436
- },
437
- "100310": {
438
- "content": "<|unused_41|>",
439
- "lstrip": false,
440
- "normalized": false,
441
- "rstrip": false,
442
- "single_word": false,
443
- "special": true
444
- },
445
- "100311": {
446
- "content": "<|unused_42|>",
447
- "lstrip": false,
448
- "normalized": false,
449
- "rstrip": false,
450
- "single_word": false,
451
- "special": true
452
- },
453
- "100312": {
454
- "content": "<|unused_43|>",
455
- "lstrip": false,
456
- "normalized": false,
457
- "rstrip": false,
458
- "single_word": false,
459
- "special": true
460
- },
461
- "100313": {
462
- "content": "<|unused_44|>",
463
- "lstrip": false,
464
- "normalized": false,
465
- "rstrip": false,
466
- "single_word": false,
467
- "special": true
468
- },
469
- "100314": {
470
- "content": "<|unused_45|>",
471
- "lstrip": false,
472
- "normalized": false,
473
- "rstrip": false,
474
- "single_word": false,
475
- "special": true
476
- },
477
- "100315": {
478
- "content": "<|unused_46|>",
479
- "lstrip": false,
480
- "normalized": false,
481
- "rstrip": false,
482
- "single_word": false,
483
- "special": true
484
- },
485
- "100316": {
486
- "content": "<|unused_47|>",
487
- "lstrip": false,
488
- "normalized": false,
489
- "rstrip": false,
490
- "single_word": false,
491
- "special": true
492
- },
493
- "100317": {
494
- "content": "<|unused_48|>",
495
- "lstrip": false,
496
- "normalized": false,
497
- "rstrip": false,
498
- "single_word": false,
499
- "special": true
500
- },
501
- "100318": {
502
- "content": "<|unused_49|>",
503
- "lstrip": false,
504
- "normalized": false,
505
- "rstrip": false,
506
- "single_word": false,
507
- "special": true
508
- },
509
- "100319": {
510
- "content": "<|unused_50|>",
511
- "lstrip": false,
512
- "normalized": false,
513
- "rstrip": false,
514
- "single_word": false,
515
- "special": true
516
- },
517
- "100320": {
518
- "content": "<|unused_51|>",
519
- "lstrip": false,
520
- "normalized": false,
521
- "rstrip": false,
522
- "single_word": false,
523
- "special": true
524
- },
525
- "100321": {
526
- "content": "<|unused_52|>",
527
- "lstrip": false,
528
- "normalized": false,
529
- "rstrip": false,
530
- "single_word": false,
531
- "special": true
532
- },
533
- "100322": {
534
- "content": "<|unused_53|>",
535
- "lstrip": false,
536
- "normalized": false,
537
- "rstrip": false,
538
- "single_word": false,
539
- "special": true
540
- },
541
- "100323": {
542
- "content": "<|unused_54|>",
543
- "lstrip": false,
544
- "normalized": false,
545
- "rstrip": false,
546
- "single_word": false,
547
- "special": true
548
- },
549
- "100324": {
550
- "content": "<|unused_55|>",
551
- "lstrip": false,
552
- "normalized": false,
553
- "rstrip": false,
554
- "single_word": false,
555
- "special": true
556
- },
557
- "100325": {
558
- "content": "<|unused_56|>",
559
- "lstrip": false,
560
- "normalized": false,
561
- "rstrip": false,
562
- "single_word": false,
563
- "special": true
564
- },
565
- "100326": {
566
- "content": "<|unused_57|>",
567
- "lstrip": false,
568
- "normalized": false,
569
- "rstrip": false,
570
- "single_word": false,
571
- "special": true
572
- },
573
- "100327": {
574
- "content": "<|unused_58|>",
575
- "lstrip": false,
576
- "normalized": false,
577
- "rstrip": false,
578
- "single_word": false,
579
- "special": true
580
- },
581
- "100328": {
582
- "content": "<|unused_59|>",
583
- "lstrip": false,
584
- "normalized": false,
585
- "rstrip": false,
586
- "single_word": false,
587
- "special": true
588
- },
589
- "100329": {
590
- "content": "<|unused_60|>",
591
- "lstrip": false,
592
- "normalized": false,
593
- "rstrip": false,
594
- "single_word": false,
595
- "special": true
596
- },
597
- "100330": {
598
- "content": "<|unused_61|>",
599
- "lstrip": false,
600
- "normalized": false,
601
- "rstrip": false,
602
- "single_word": false,
603
- "special": true
604
- },
605
- "100331": {
606
- "content": "<|unused_62|>",
607
- "lstrip": false,
608
- "normalized": false,
609
- "rstrip": false,
610
- "single_word": false,
611
- "special": true
612
- },
613
- "100332": {
614
- "content": "<|unused_63|>",
615
- "lstrip": false,
616
- "normalized": false,
617
- "rstrip": false,
618
- "single_word": false,
619
- "special": true
620
- },
621
- "100333": {
622
- "content": "<|unused_64|>",
623
- "lstrip": false,
624
- "normalized": false,
625
- "rstrip": false,
626
- "single_word": false,
627
- "special": true
628
- },
629
- "100334": {
630
- "content": "<|unused_65|>",
631
- "lstrip": false,
632
- "normalized": false,
633
- "rstrip": false,
634
- "single_word": false,
635
- "special": true
636
- },
637
- "100335": {
638
- "content": "<|unused_66|>",
639
- "lstrip": false,
640
- "normalized": false,
641
- "rstrip": false,
642
- "single_word": false,
643
- "special": true
644
- },
645
- "100336": {
646
- "content": "<|unused_67|>",
647
- "lstrip": false,
648
- "normalized": false,
649
- "rstrip": false,
650
- "single_word": false,
651
- "special": true
652
- },
653
- "100337": {
654
- "content": "<|unused_68|>",
655
- "lstrip": false,
656
- "normalized": false,
657
- "rstrip": false,
658
- "single_word": false,
659
- "special": true
660
- },
661
- "100338": {
662
- "content": "<|unused_69|>",
663
- "lstrip": false,
664
- "normalized": false,
665
- "rstrip": false,
666
- "single_word": false,
667
- "special": true
668
- },
669
- "100339": {
670
- "content": "<|unused_70|>",
671
- "lstrip": false,
672
- "normalized": false,
673
- "rstrip": false,
674
- "single_word": false,
675
- "special": true
676
- },
677
- "100340": {
678
- "content": "<|unused_71|>",
679
- "lstrip": false,
680
- "normalized": false,
681
- "rstrip": false,
682
- "single_word": false,
683
- "special": true
684
- },
685
- "100341": {
686
- "content": "<|unused_72|>",
687
- "lstrip": false,
688
- "normalized": false,
689
- "rstrip": false,
690
- "single_word": false,
691
- "special": true
692
- },
693
- "100342": {
694
- "content": "<|unused_73|>",
695
- "lstrip": false,
696
- "normalized": false,
697
- "rstrip": false,
698
- "single_word": false,
699
- "special": true
700
- },
701
- "100343": {
702
- "content": "<|unused_74|>",
703
- "lstrip": false,
704
- "normalized": false,
705
- "rstrip": false,
706
- "single_word": false,
707
- "special": true
708
- },
709
- "100344": {
710
- "content": "<|unused_75|>",
711
- "lstrip": false,
712
- "normalized": false,
713
- "rstrip": false,
714
- "single_word": false,
715
- "special": true
716
- },
717
- "100345": {
718
- "content": "<|unused_76|>",
719
- "lstrip": false,
720
- "normalized": false,
721
- "rstrip": false,
722
- "single_word": false,
723
- "special": true
724
- },
725
- "100346": {
726
- "content": "<|unused_77|>",
727
- "lstrip": false,
728
- "normalized": false,
729
- "rstrip": false,
730
- "single_word": false,
731
- "special": true
732
- },
733
- "100347": {
734
- "content": "<|unused_78|>",
735
- "lstrip": false,
736
- "normalized": false,
737
- "rstrip": false,
738
- "single_word": false,
739
- "special": true
740
- },
741
- "100348": {
742
- "content": "<|unused_79|>",
743
- "lstrip": false,
744
- "normalized": false,
745
- "rstrip": false,
746
- "single_word": false,
747
- "special": true
748
- },
749
- "100349": {
750
- "content": "<|unused_80|>",
751
- "lstrip": false,
752
- "normalized": false,
753
- "rstrip": false,
754
- "single_word": false,
755
- "special": true
756
- },
757
- "100350": {
758
- "content": "<|unused_81|>",
759
- "lstrip": false,
760
- "normalized": false,
761
- "rstrip": false,
762
- "single_word": false,
763
- "special": true
764
- },
765
- "100351": {
766
- "content": "<|unused_82|>",
767
- "lstrip": false,
768
- "normalized": false,
769
- "rstrip": false,
770
- "single_word": false,
771
- "special": true
772
- }
773
- },
774
- "bos_token": "<|end_of_text|>",
775
- "clean_up_tokenization_spaces": false,
776
- "eos_token": "<|end_of_text|>",
777
- "extra_special_tokens": {},
778
- "model_max_length": 1000000000000000019884624838656,
779
- "pad_token": "<|pad|>",
780
- "padding_side": "left",
781
- "tokenizer_class": "GPT2Tokenizer",
782
- "unk_token": "<|unk|>"
783
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_classifier/granite-4.0-micro/lora/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c26d41c07db17c2c6957479b74865d8ac3dfb39a7b8901bdf05e890b8d65cf2a
3
- size 6353
 
 
 
 
answer_relevance_classifier/granite-4.0-micro/lora/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
answer_relevance_classifier/granite4_micro/lora/Lora-q8_0.gguf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:05ab02c60a86272867f2912a7e5be3938d66a2e1c21dd82dfb8101d9a3672a32
3
- size 15335328
 
 
 
 
answer_relevance_classifier/granite4_micro/lora/Modelfile DELETED
@@ -1,2 +0,0 @@
1
- FROM granite4:micro
2
- ADAPTER Lora-q8_0.gguf
 
 
 
answer_relevance_classifier/granite4_micro/lora/io.yaml DELETED
@@ -1,50 +0,0 @@
1
- model: null
2
- response_format: null
3
- instruction: answer_relevance
4
- transformations:
5
- - type: likelihood
6
- categories_to_values:
7
- true: 1.0
8
- false: 0.0
9
- input_path:
10
- - answer_relevance_judgment
11
- - type: project
12
- input_path: []
13
- retained_fields:
14
- answer_relevance_analysis: answer_relevance_analysis
15
- answer_relevance_category: answer_relevance_category
16
- answer_relevance_judgment: answer_relevance_likelihood
17
- parameters:
18
- response_format:
19
- type: json_schema
20
- json_schema:
21
- schema:
22
- properties:
23
- answer_relevance_analysis:
24
- title: Answer Relevance Analysis
25
- type: string
26
- answer_relevance_category:
27
- title: Answer Relevance Category
28
- type: string
29
- enum:
30
- - Pertinent
31
- - Pertinent with relevant extra
32
- - Excessive unnecessary information
33
- - Unduly restrictive
34
- - Too vague or generic
35
- - Contextual misalignment
36
- - Misinterpreted inquiry
37
- - No attempt
38
- answer_relevance_judgment:
39
- title: Answer Relevance Judgment
40
- type: boolean
41
- required:
42
- - answer_relevance_analysis
43
- - answer_relevance_category
44
- - answer_relevance_judgment
45
- title: AnswerRelevanceRawOutput
46
- type: object
47
- strict: true
48
- max_tokens: 1024
49
- sentence_boundaries: null
50
- docs_as_message: roles
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_rewriter/README.md DELETED
@@ -1,157 +0,0 @@
1
- ---
2
- license: apache-2.0
3
- language:
4
- - en
5
- pipeline_tag: text-generation
6
- library_name: peft
7
- library_name: transformers
8
- ---
9
-
10
- # Intrinsics for Answer Relevance Rewriter
11
-
12
- ## Model Summary
13
- This is a RAG-specific intrinsic for answer relevance rewrite task.
14
- The model takes as input the chat completion from answer relevance classifier output
15
- consisting of conversation as well as answer_relevance_classification, together with grounding documents,
16
- and provides a rewritten assistant response that is more relevant to the user's final inquiry.
17
-
18
-
19
- We provide two intrinsics implemented as LoRA adapters (LoRA/aLoRA) trained over
20
- Granite-3.3-2b-instruct, Granite-3.3-8b-instruct.
21
-
22
- - **Developer:** IBM Research
23
- - **Model type:** LoRA and aLoRA adapter for
24
- [ibm-granite/granite-3.3-2b-instruct](https://huggingface.co/ibm-granite/granite-3.3-2b-instruct),
25
- [ibm-granite/granite-3.3-8b-instruct](https://huggingface.co/ibm-granite/granite-3.3-8b-instruct)
26
- - **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
27
-
28
- ## Intended use
29
- This rag specific intrinsics is intended to be used to post-process the generated assistant response.
30
- It should be used following the answer relevance classifier intrinsic, and should be applied to
31
- the cases where the `answer_relevance_likelihood` is below a certain threshold according to application criteria.
32
-
33
- For cases where the assistant answer is deemed not relevant (where `answer_relevance_likelihood` is below a
34
- given threshold), the answer relevance rewriter intrinsic can be used to rewrite the assistant response
35
- into a more relevant response. It takes as input the chat completion
36
- from answer relevance classifier output and the grounding documents. Its output is of the form
37
-
38
- {
39
- answer_relevance_rewrite: <Rewritten response>
40
- }
41
-
42
- The rewriter is instructed to only correct deficiencies in relevance as identified by the classifier,
43
- and ensure the rewritten response is grounded in the conversation and given documents.
44
-
45
- **Model input**: The input to the answer relevance rewriter intrinsic is an
46
- OpenAI-compatible chat completion request, containing a list of conversation
47
- turns that can alternate between the `user` and `assistant` role and ending with
48
- a `assistant` turn, plus two additional turns:
49
- - A conversation between user and assistant ending with assistant response
50
- - An additional user turn with content "answer_relevance"
51
-
52
- **Model output**: The output of the answer relevance rewriter intrinsic is the result of the
53
- original chat completion request formatted as a JSON object of the following schema
54
-
55
- {
56
- answer_relevance_rewrite: <Rewritten response>
57
- }
58
-
59
- Please see the code snippets in the Quickstart Example section below for
60
- examples that illustrate the intrinsic's input/output.
61
-
62
- ## Quickstart Example
63
-
64
- The recommended way to call this intrinsic is through the [Mellea](https://mellea.ai) framework.
65
- Here is some example code for calling this intrinsic from Mellea:
66
- ```
67
- from mellea.backends.huggingface import LocalHFBackend
68
- from mellea.stdlib.base import ChatContext, Document
69
- from mellea.stdlib.chat import Message
70
- from mellea.stdlib.intrinsics import rag
71
-
72
-
73
- backend = LocalHFBackend(model_id="ibm-granite/granite-3.3-2b-instruct")
74
- context = ChatContext().add(Message("user", "Who attended the meeting?"))
75
- documents = [
76
- Document("Meeting attendees: Alice, Bob, Carol."),
77
- Document("Meeting time: 9:00 am to 11:00 am."),
78
- ]
79
- original_result = "Many people attended the meeting."
80
-
81
- print(f"Result before relevance intrinsic: {original_result}")
82
- result = rag.rewrite_answer_for_relevance(original_result, documents, context, backend)
83
- print(f"Result after relevance intrinsic: {result}")
84
- ```
85
-
86
- ## Training Details
87
-
88
- ### Training Data
89
-
90
- The training data is created in the following process
91
- 1. Take the synthetic rag-data-granite dataset, consisting of conversations between user and assistant.
92
- 2. Replace the assistant response by running granite-3.2-intrinsics at temperature 1.0.
93
- 3. Produce answer_relevance_rewriter target output using mixtral-large with prompts with in-context examples.
94
- The conversation created in steps 1 and 2 are taken as training input. The json string from step 3
95
- is taken as train target output.
96
-
97
- #### Training Hyperparameters
98
-
99
- The LoRA adapter was fine-tuned using PEFT under the following regime: rank =
100
- 32, learning rate = 1.0e-04, number of epochs = 5.
101
-
102
- ## Evaluation
103
-
104
- ### Answer Relevance Rewriter
105
-
106
- We evaluated the model on test data set generated by the same procedure as the training process,
107
- using GPT-4o as judge.
108
-
109
-
110
- The following table presents results comparing baselines and frontier models
111
- on the answer relevance rewrite task. The data sets consists of those classified as irrelevant by
112
- mixtral-large. The evaluations are first divided into two parts, those that are truly irrelevant,
113
- for which we measure the rate of rewrite becoming relevant, and those that are false irrelevant,
114
- for which we measure the rate of rewrite becoming irrelevant. Then the overall rate flipping
115
- irrelevant to relevant and flipping relevant to irrelevant are calculated, and well as the net gain
116
- of relevance and resulting final relevance.
117
-
118
- The LoRAs out perform the best of frontier models
119
-
120
- | | True irrelevant <br> flip to relevant | False irrelevant <br> flip to irrelevant| Overall <br> flip irrelevant <br> to relevant | Overall <br> flip relevant <br> to irrelevant| net gain | Result <br>relevance |
121
- |:---------------------|:--------------|:---------|:------------------------------|:---------|:---------|:--------------|
122
- | mixtral-8x22b-v0.1 | 0.416 | 0.101 | 0.286 | 0.032 | 0.254 | 0.566 |
123
- | llama-3.3-70b | 0.804 | 0.041 | 0.554 | 0.013 | 0.541 | 0.853 |
124
- | gpt-oss-20b | 0.902 | 0.034 | 0.621 | 0.011 | 0.610 | 0.922 |
125
- | gpt-4o | 0.960 | 0.014 | 0.661 | 0.004 | 0.657 | 0.968 |
126
- | gpt-4o-mini | 0.758 | 0.027 | 0.522 | 0.008 | 0.514 | 0.825 |
127
- | | | | | | | |
128
- | granite-3.3-2b/lora | 0.972 | 0.027 | 0.669 | 0.008 | 0.661 | 0.973 |
129
- | granite-3.3-2b/alora | 0.972 | 0.007 | 0.669 | 0.002 | 0.667 | 0.979 |
130
- | granite-3.3-8b/lora | 0.969 | 0.014 | 0.667 | 0.004 | 0.663 | 0.975 |
131
- | granite-3.3-8b/alora | 0.966 | 0.027 | 0.665 | 0.008 | 0.657 | 0.968 |
132
- | | | | | | | |
133
-
134
- ### Comparing the Answer Relevance Rewriter Intrinsics vs. Vanilla Granite Models
135
-
136
- We compare the performance of Granite 3.3-2b, Granite 3.3-8b Instruct
137
- vs. answer relevance rewriter intrinsics implemented as LoRA adapters.
138
- It is seen that the LoRAs significantly out perform the base models.
139
- | | True irrelevant <br> flip to relevant | False irrelevant <br> flip to irrelevant| Overall <br> flip irrelevant <br> to relevant | Overall <br> flip relevant <br> to irrelevant| net gain | Result relevance |
140
- |:---------------------|:--------------|:---------|:------------------------------|:---------|:---------|:--------------|
141
- | granite-3.3-2b | 0.346 | 0.169 | 0.238 | 0.053 | 0.185 | 0.497 |
142
- | granite-3.3-2b/lora | 0.972 | 0.027 | 0.669 | 0.008 | 0.661 | 0.973 |
143
- | granite-3.3-2b/alora | 0.972 | 0.007 | 0.669 | 0.002 | 0.667 | 0.979 |
144
- | | | | | | | |
145
- | granite-3.3-8b | 0.266 | 0.277 | 0.183 | 0.086 | 0.097 | 0.408 |
146
- | granite-3.3-8b/lora | 0.969 | 0.014 | 0.667 | 0.004 | 0.663 | 0.975 |
147
- | granite-3.3-8b/alora | 0.966 | 0.027 | 0.665 | 0.008 | 0.657 | 0.968 |
148
- | | | | | | | |
149
-
150
-
151
- ## Model Card Authors
152
-
153
- [Huaiyu Zhu](mailto:huaiyu@us.ibm.com)
154
-
155
- ### Framework versions
156
-
157
- - PEFT 0.14.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_rewriter/granite-3.3-8b-instruct/alora/adapter_config.json DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "alpha_pattern": {},
3
- "auto_mapping": null,
4
- "base_model_name_or_path": "ibm-granite/granite-3.3-8b-instruct",
5
- "bias": "none",
6
- "eva_config": null,
7
- "exclude_modules": null,
8
- "fan_in_fan_out": false,
9
- "inference_mode": true,
10
- "init_lora_weights": true,
11
- "layer_replication": null,
12
- "layers_pattern": null,
13
- "layers_to_transform": null,
14
- "loftq_config": {},
15
- "lora_alpha": 32,
16
- "lora_bias": false,
17
- "lora_dropout": 0.05,
18
- "megatron_config": null,
19
- "megatron_core": "megatron.core",
20
- "modules_to_save": null,
21
- "peft_type": "LORA",
22
- "r": 32,
23
- "rank_pattern": {},
24
- "revision": null,
25
- "target_modules": [
26
- "q_proj",
27
- "v_proj",
28
- "k_proj"
29
- ],
30
- "task_type": "CAUSAL_LM",
31
- "use_dora": false,
32
- "use_rslora": false
33
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_rewriter/granite-3.3-8b-instruct/alora/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ae2de12b4b4b123cb14088257b9689124265916a51a911d05ed115e2603446b
3
- size 94404160
 
 
 
 
answer_relevance_rewriter/granite-3.3-8b-instruct/alora/added_tokens.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "<|end_of_cite|>": 49156,
3
- "<|end_of_plugin|>": 49158,
4
- "<|end_of_role|>": 49153,
5
- "<|start_of_cite|>": 49155,
6
- "<|start_of_plugin|>": 49157,
7
- "<|start_of_role|>": 49152,
8
- "<|tool_call|>": 49154
9
- }
 
 
 
 
 
 
 
 
 
 
answer_relevance_rewriter/granite-3.3-8b-instruct/alora/io.yaml DELETED
@@ -1,29 +0,0 @@
1
- # Model name string, or null to use whatever is provided in the chat completion request
2
- model: ~
3
- # JSON schema of the model's output, or null if constrained decoding is not needed
4
- response_format: |
5
- {
6
- "properties": {
7
- "answer_relevance_rewrite": {
8
- "title": "Rewritten answer",
9
- "type": "string"
10
- }
11
- },
12
- "required": [
13
- "answer_relevance_rewrite"
14
- ],
15
- "type": "object"
16
- }
17
- # Additional turn of instructions to add to the chat
18
- instruction: |
19
- Rewrite the response for relevance.
20
- The last assistant response is considered not fully relevant to the last user inquiry due to {answer_relevance_category}: {answer_relevance_analysis}
21
- Decide if you agree with this assessment, then act according to the following instructions:
22
- If you disagree with the assessment, provide a verbatim copy of the original response. DO NOT attempt to correct any other perceived defects in the response.
23
- If you agree with the assessment, provide an updated response that no longer fit the label {answer_relevance_category}, by {correction_method}. Your response should be entirely based on the provided documents and should not rely on other prior knowledge. Your response should be suitable to be directly provided to the user. It should NOT contain meta information regarding the original response, its assessment, or this instruction. The user does not see any of these. Your response is the only response they will see to their inquiry, in place of the original response.
24
- # Data transformations to perform during post-processing
25
- transformations: ~
26
- parameters:
27
- # Rewritten response could be long.
28
- max_completion_tokens: 1024
29
- sentence_boundaries: ~
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_rewriter/granite-3.3-8b-instruct/alora/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
answer_relevance_rewriter/granite-3.3-8b-instruct/alora/special_tokens_map.json DELETED
@@ -1,39 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|start_of_role|>",
4
- "<|end_of_role|>",
5
- "<|tool_call|>",
6
- "<|start_of_cite|>",
7
- "<|end_of_cite|>",
8
- "<|start_of_plugin|>",
9
- "<|end_of_plugin|>"
10
- ],
11
- "bos_token": {
12
- "content": "<|end_of_text|>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false
17
- },
18
- "eos_token": {
19
- "content": "<|end_of_text|>",
20
- "lstrip": false,
21
- "normalized": false,
22
- "rstrip": false,
23
- "single_word": false
24
- },
25
- "pad_token": {
26
- "content": "<|end_of_text|>",
27
- "lstrip": false,
28
- "normalized": false,
29
- "rstrip": false,
30
- "single_word": false
31
- },
32
- "unk_token": {
33
- "content": "<|end_of_text|>",
34
- "lstrip": false,
35
- "normalized": false,
36
- "rstrip": false,
37
- "single_word": false
38
- }
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_rewriter/granite-3.3-8b-instruct/alora/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
answer_relevance_rewriter/granite-3.3-8b-instruct/alora/tokenizer_config.json DELETED
@@ -1,235 +0,0 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<|end_of_text|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<fim_prefix>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "<fim_middle>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "3": {
30
- "content": "<fim_suffix>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "4": {
38
- "content": "<fim_pad>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "5": {
46
- "content": "<filename>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "6": {
54
- "content": "<gh_stars>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "7": {
62
- "content": "<issue_start>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "8": {
70
- "content": "<issue_comment>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "9": {
78
- "content": "<issue_closed>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "10": {
86
- "content": "<jupyter_start>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "11": {
94
- "content": "<jupyter_text>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "12": {
102
- "content": "<jupyter_code>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "13": {
110
- "content": "<jupyter_output>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "14": {
118
- "content": "<empty_output>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": true
124
- },
125
- "15": {
126
- "content": "<commit_before>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": true
132
- },
133
- "16": {
134
- "content": "<commit_msg>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": true
140
- },
141
- "17": {
142
- "content": "<commit_after>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": true
148
- },
149
- "18": {
150
- "content": "<reponame>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": true
156
- },
157
- "49152": {
158
- "content": "<|start_of_role|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": true
164
- },
165
- "49153": {
166
- "content": "<|end_of_role|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": true
172
- },
173
- "49154": {
174
- "content": "<|tool_call|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": true
180
- },
181
- "49155": {
182
- "content": "<|start_of_cite|>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "49156": {
190
- "content": "<|end_of_cite|>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": true
196
- },
197
- "49157": {
198
- "content": "<|start_of_plugin|>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": true
204
- },
205
- "49158": {
206
- "content": "<|end_of_plugin|>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": true
212
- }
213
- },
214
- "additional_special_tokens": [
215
- "<|start_of_role|>",
216
- "<|end_of_role|>",
217
- "<|tool_call|>",
218
- "<|start_of_cite|>",
219
- "<|end_of_cite|>",
220
- "<|start_of_plugin|>",
221
- "<|end_of_plugin|>"
222
- ],
223
- "bos_token": "<|end_of_text|>",
224
- "chat_template": "{# Alias tools -> available_tools #}\n{%- if tools and not available_tools -%}\n {%- set available_tools = tools -%}\n{%- endif -%}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set loop_messages = messages[1:] %}\n {%- else %}\n {%- set system_message = \"Knowledge Cutoff Date: April 2024.\nToday's Date: \" + strftime_now('%B %d, %Y') + \".\nYou are Granite, developed by IBM.\" %}\n {%- if available_tools and documents %}\n {%- set system_message = system_message + \" You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.\nWrite the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.\" %}\n {%- elif available_tools %}\n {%- set system_message = system_message + \" You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.\" %}\n {%- elif documents %}\n {%- set system_message = system_message + \" Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.\" %}\n {%- elif thinking %}\n {%- set system_message = system_message + \" You are a helpful AI assistant.\nRespond to every user query in a comprehensive and detailed way. You can write down your thoughts and reasoning process before responding. In the thought process, engage in a comprehensive cycle of analysis, summarization, exploration, reassessment, reflection, backtracing, and iteration to develop well-considered thinking process. In the response section, based on various attempts, explorations, and reflections from the thoughts section, systematically present the final solution that you deem correct. The response should summarize the thought process. Write your thoughts between <think></think> and write your response between <response></response> for each user query.\" %}\n {%- else %}\n {%- set system_message = system_message + \" You are a helpful AI assistant.\" %}\n {%- endif %}\n {%- if 'citations' in controls and documents %}\n {%- set system_message = system_message + '\nUse the symbols <|start_of_cite|> and <|end_of_cite|> to indicate when a fact comes from a document in the search result, e.g <|start_of_cite|> {document_id: 1}my fact <|end_of_cite|> for a fact from document 1. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}\n {%- endif %}\n {%- if 'hallucinations' in controls and documents %}\n {%- set system_message = system_message + '\nFinally, after the response is written, include a numbered list of sentences from the response with a corresponding risk value that are hallucinated and not based in the documents.' %}\n {%- endif %}\n {%- set loop_messages = messages %}\n {%- endif %}\n {{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>\n' }}\n {%- if available_tools %}\n {{- '<|start_of_role|>available_tools<|end_of_role|>' }}\n {{- available_tools | tojson(indent=4) }}\n {{- '<|end_of_text|>\n' }}\n {%- endif %}\n {%- if documents %}\n {%- for document in documents %}\n {{- '<|start_of_role|>document {\"document_id\": \"' + document['doc_id'] | string + '\"}<|end_of_role|>\n' }}\n {{- document['text'] }}\n {{- '<|end_of_text|>\n' }}\n {%- endfor %}\n {%- endif %}\n {%- for message in loop_messages %}\n {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- if loop.last and add_generation_prompt %}\n {{- '<|start_of_role|>assistant' }}\n {%- if controls %}\n {{- ' ' + controls | tojson()}}\n {%- endif %}\n {{- '<|end_of_role|>' }}\n {%- endif %}\n {%- endfor %}",
225
- "clean_up_tokenization_spaces": true,
226
- "eos_token": "<|end_of_text|>",
227
- "errors": "replace",
228
- "extra_special_tokens": {},
229
- "model_max_length": 9223372036854775807,
230
- "pad_token": "<|end_of_text|>",
231
- "padding_side": "left",
232
- "tokenizer_class": "GPT2Tokenizer",
233
- "unk_token": "<|end_of_text|>",
234
- "vocab_size": 49152
235
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_rewriter/granite-3.3-8b-instruct/alora/vocab.json DELETED
The diff for this file is too large to render. See raw diff
 
answer_relevance_rewriter/granite-3.3-8b-instruct/lora/adapter_config.json DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "alpha_pattern": {},
3
- "auto_mapping": null,
4
- "base_model_name_or_path": "ibm-granite/granite-3.3-8b-instruct",
5
- "bias": "none",
6
- "eva_config": null,
7
- "exclude_modules": null,
8
- "fan_in_fan_out": false,
9
- "inference_mode": true,
10
- "init_lora_weights": true,
11
- "layer_replication": null,
12
- "layers_pattern": null,
13
- "layers_to_transform": null,
14
- "loftq_config": {},
15
- "lora_alpha": 32,
16
- "lora_bias": false,
17
- "lora_dropout": 0.05,
18
- "megatron_config": null,
19
- "megatron_core": "megatron.core",
20
- "modules_to_save": null,
21
- "peft_type": "LORA",
22
- "r": 32,
23
- "rank_pattern": {},
24
- "revision": null,
25
- "target_modules": [
26
- "q_proj",
27
- "k_proj",
28
- "v_proj"
29
- ],
30
- "task_type": "CAUSAL_LM",
31
- "use_dora": false,
32
- "use_rslora": false
33
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_rewriter/granite-3.3-8b-instruct/lora/adapter_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:74db6518798528a2cb2ecd620825a95db228c54a87393e88a5832218e77044ce
3
- size 94404160
 
 
 
 
answer_relevance_rewriter/granite-3.3-8b-instruct/lora/added_tokens.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "<|end_of_cite|>": 49156,
3
- "<|end_of_plugin|>": 49158,
4
- "<|end_of_role|>": 49153,
5
- "<|start_of_cite|>": 49155,
6
- "<|start_of_plugin|>": 49157,
7
- "<|start_of_role|>": 49152,
8
- "<|tool_call|>": 49154
9
- }
 
 
 
 
 
 
 
 
 
 
answer_relevance_rewriter/granite-3.3-8b-instruct/lora/io.yaml DELETED
@@ -1,29 +0,0 @@
1
- # Model name string, or null to use whatever is provided in the chat completion request
2
- model: ~
3
- # JSON schema of the model's output, or null if constrained decoding is not needed
4
- response_format: |
5
- {
6
- "properties": {
7
- "answer_relevance_rewrite": {
8
- "title": "Rewritten answer",
9
- "type": "string"
10
- }
11
- },
12
- "required": [
13
- "answer_relevance_rewrite"
14
- ],
15
- "type": "object"
16
- }
17
- # Additional turn of instructions to add to the chat
18
- instruction: |
19
- Rewrite the response for relevance.
20
- The last assistant response is considered not fully relevant to the last user inquiry due to {answer_relevance_category}: {answer_relevance_analysis}
21
- Decide if you agree with this assessment, then act according to the following instructions:
22
- If you disagree with the assessment, provide a verbatim copy of the original response. DO NOT attempt to correct any other perceived defects in the response.
23
- If you agree with the assessment, provide an updated response that no longer fit the label {answer_relevance_category}, by {correction_method}. Your response should be entirely based on the provided documents and should not rely on other prior knowledge. Your response should be suitable to be directly provided to the user. It should NOT contain meta information regarding the original response, its assessment, or this instruction. The user does not see any of these. Your response is the only response they will see to their inquiry, in place of the original response.
24
- # Data transformations to perform during post-processing
25
- transformations: ~
26
- parameters:
27
- # Rewritten response could be long.
28
- max_completion_tokens: 1024
29
- sentence_boundaries: ~
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_rewriter/granite-3.3-8b-instruct/lora/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
answer_relevance_rewriter/granite-3.3-8b-instruct/lora/special_tokens_map.json DELETED
@@ -1,39 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|start_of_role|>",
4
- "<|end_of_role|>",
5
- "<|tool_call|>",
6
- "<|start_of_cite|>",
7
- "<|end_of_cite|>",
8
- "<|start_of_plugin|>",
9
- "<|end_of_plugin|>"
10
- ],
11
- "bos_token": {
12
- "content": "<|end_of_text|>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false
17
- },
18
- "eos_token": {
19
- "content": "<|end_of_text|>",
20
- "lstrip": false,
21
- "normalized": false,
22
- "rstrip": false,
23
- "single_word": false
24
- },
25
- "pad_token": {
26
- "content": "<|end_of_text|>",
27
- "lstrip": false,
28
- "normalized": false,
29
- "rstrip": false,
30
- "single_word": false
31
- },
32
- "unk_token": {
33
- "content": "<|end_of_text|>",
34
- "lstrip": false,
35
- "normalized": false,
36
- "rstrip": false,
37
- "single_word": false
38
- }
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
answer_relevance_rewriter/granite-3.3-8b-instruct/lora/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
answer_relevance_rewriter/granite-3.3-8b-instruct/lora/tokenizer_config.json DELETED
@@ -1,235 +0,0 @@
1
- {
2
- "add_bos_token": false,
3
- "add_prefix_space": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<|end_of_text|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<fim_prefix>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "<fim_middle>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "3": {
30
- "content": "<fim_suffix>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "4": {
38
- "content": "<fim_pad>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "5": {
46
- "content": "<filename>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "6": {
54
- "content": "<gh_stars>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "7": {
62
- "content": "<issue_start>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "8": {
70
- "content": "<issue_comment>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": false,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "9": {
78
- "content": "<issue_closed>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": false,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "10": {
86
- "content": "<jupyter_start>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": false,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "11": {
94
- "content": "<jupyter_text>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": false,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "12": {
102
- "content": "<jupyter_code>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": false,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "13": {
110
- "content": "<jupyter_output>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": false,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "14": {
118
- "content": "<empty_output>",
119
- "lstrip": false,
120
- "normalized": false,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": true
124
- },
125
- "15": {
126
- "content": "<commit_before>",
127
- "lstrip": false,
128
- "normalized": false,
129
- "rstrip": false,
130
- "single_word": false,
131
- "special": true
132
- },
133
- "16": {
134
- "content": "<commit_msg>",
135
- "lstrip": false,
136
- "normalized": false,
137
- "rstrip": false,
138
- "single_word": false,
139
- "special": true
140
- },
141
- "17": {
142
- "content": "<commit_after>",
143
- "lstrip": false,
144
- "normalized": false,
145
- "rstrip": false,
146
- "single_word": false,
147
- "special": true
148
- },
149
- "18": {
150
- "content": "<reponame>",
151
- "lstrip": false,
152
- "normalized": false,
153
- "rstrip": false,
154
- "single_word": false,
155
- "special": true
156
- },
157
- "49152": {
158
- "content": "<|start_of_role|>",
159
- "lstrip": false,
160
- "normalized": false,
161
- "rstrip": false,
162
- "single_word": false,
163
- "special": true
164
- },
165
- "49153": {
166
- "content": "<|end_of_role|>",
167
- "lstrip": false,
168
- "normalized": false,
169
- "rstrip": false,
170
- "single_word": false,
171
- "special": true
172
- },
173
- "49154": {
174
- "content": "<|tool_call|>",
175
- "lstrip": false,
176
- "normalized": false,
177
- "rstrip": false,
178
- "single_word": false,
179
- "special": true
180
- },
181
- "49155": {
182
- "content": "<|start_of_cite|>",
183
- "lstrip": false,
184
- "normalized": false,
185
- "rstrip": false,
186
- "single_word": false,
187
- "special": true
188
- },
189
- "49156": {
190
- "content": "<|end_of_cite|>",
191
- "lstrip": false,
192
- "normalized": false,
193
- "rstrip": false,
194
- "single_word": false,
195
- "special": true
196
- },
197
- "49157": {
198
- "content": "<|start_of_plugin|>",
199
- "lstrip": false,
200
- "normalized": false,
201
- "rstrip": false,
202
- "single_word": false,
203
- "special": true
204
- },
205
- "49158": {
206
- "content": "<|end_of_plugin|>",
207
- "lstrip": false,
208
- "normalized": false,
209
- "rstrip": false,
210
- "single_word": false,
211
- "special": true
212
- }
213
- },
214
- "additional_special_tokens": [
215
- "<|start_of_role|>",
216
- "<|end_of_role|>",
217
- "<|tool_call|>",
218
- "<|start_of_cite|>",
219
- "<|end_of_cite|>",
220
- "<|start_of_plugin|>",
221
- "<|end_of_plugin|>"
222
- ],
223
- "bos_token": "<|end_of_text|>",
224
- "chat_template": "{# Alias tools -> available_tools #}\n{%- if tools and not available_tools -%}\n {%- set available_tools = tools -%}\n{%- endif -%}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set loop_messages = messages[1:] %}\n {%- else %}\n {%- set system_message = \"Knowledge Cutoff Date: April 2024.\nToday's Date: \" + strftime_now('%B %d, %Y') + \".\nYou are Granite, developed by IBM.\" %}\n {%- if available_tools and documents %}\n {%- set system_message = system_message + \" You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.\nWrite the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.\" %}\n {%- elif available_tools %}\n {%- set system_message = system_message + \" You are a helpful assistant with access to the following tools. When a tool is required to answer the user's query, respond only with <|tool_call|> followed by a JSON list of tools used. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.\" %}\n {%- elif documents %}\n {%- set system_message = system_message + \" Write the response to the user's input by strictly aligning with the facts in the provided documents. If the information needed to answer the question is not available in the documents, inform the user that the question cannot be answered based on the available data.\" %}\n {%- elif thinking %}\n {%- set system_message = system_message + \" You are a helpful AI assistant.\nRespond to every user query in a comprehensive and detailed way. You can write down your thoughts and reasoning process before responding. In the thought process, engage in a comprehensive cycle of analysis, summarization, exploration, reassessment, reflection, backtracing, and iteration to develop well-considered thinking process. In the response section, based on various attempts, explorations, and reflections from the thoughts section, systematically present the final solution that you deem correct. The response should summarize the thought process. Write your thoughts between <think></think> and write your response between <response></response> for each user query.\" %}\n {%- else %}\n {%- set system_message = system_message + \" You are a helpful AI assistant.\" %}\n {%- endif %}\n {%- if 'citations' in controls and documents %}\n {%- set system_message = system_message + '\nUse the symbols <|start_of_cite|> and <|end_of_cite|> to indicate when a fact comes from a document in the search result, e.g <|start_of_cite|> {document_id: 1}my fact <|end_of_cite|> for a fact from document 1. Afterwards, list all the citations with their corresponding documents in an ordered list.' %}\n {%- endif %}\n {%- if 'hallucinations' in controls and documents %}\n {%- set system_message = system_message + '\nFinally, after the response is written, include a numbered list of sentences from the response with a corresponding risk value that are hallucinated and not based in the documents.' %}\n {%- endif %}\n {%- set loop_messages = messages %}\n {%- endif %}\n {{- '<|start_of_role|>system<|end_of_role|>' + system_message + '<|end_of_text|>\n' }}\n {%- if available_tools %}\n {{- '<|start_of_role|>available_tools<|end_of_role|>' }}\n {{- available_tools | tojson(indent=4) }}\n {{- '<|end_of_text|>\n' }}\n {%- endif %}\n {%- if documents %}\n {%- for document in documents %}\n {{- '<|start_of_role|>document {\"document_id\": \"' + document['doc_id'] | string + '\"}<|end_of_role|>\n' }}\n {{- document['text'] }}\n {{- '<|end_of_text|>\n' }}\n {%- endfor %}\n {%- endif %}\n {%- for message in loop_messages %}\n {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>\n' }}\n {%- if loop.last and add_generation_prompt %}\n {{- '<|start_of_role|>assistant' }}\n {%- if controls %}\n {{- ' ' + controls | tojson()}}\n {%- endif %}\n {{- '<|end_of_role|>' }}\n {%- endif %}\n {%- endfor %}",
225
- "clean_up_tokenization_spaces": true,
226
- "eos_token": "<|end_of_text|>",
227
- "errors": "replace",
228
- "extra_special_tokens": {},
229
- "model_max_length": 9223372036854775807,
230
- "pad_token": "<|end_of_text|>",
231
- "padding_side": "left",
232
- "tokenizer_class": "GPT2Tokenizer",
233
- "unk_token": "<|end_of_text|>",
234
- "vocab_size": 49152
235
- }