Hugging Face's logo

nelsondiasandre
/
qwen25-1.5b-pt-qa-lora

Text Generation
PEFT
Safetensors
Portuguese
lora
portuguese
question-answering
instruction-tuning
qwen2.5
pt-pt
conversational
Eval Results (legacy)
Model card Files
xet
 Community
nelsondiasandre commited on
Commit
945db9a
·
verified ·
1 Parent(s): 4d38d14

Upload model

Browse files
Files changed (3) hide show
  1. README.md +45 -27
  2. adapter_config.json +30 -44
  3. adapter_model.safetensors +2 -2
README.md CHANGED
@@ -1,39 +1,57 @@
1
  ---
2
  license: apache-2.0
3
  language:
4
- - pt
5
  library_name: peft
6
  base_model: Qwen/Qwen2.5-1.5B-Instruct
7
  pipeline_tag: text-generation
8
  tags:
9
- - peft
10
- - lora
11
- - portuguese
12
- - question-answering
13
- - instruction-tuning
14
- - qwen2.5
15
- - pt-pt
16
  datasets:
17
- - nelsondiasandre/portuguese-qa-instruct-500
18
- model-index:
19
- - name: qwen25-1.5b-pt-qa-lora
20
- results:
21
- - task:
22
- type: text-generation
23
- dataset:
24
- name: portuguese-qa-instruct-500
25
- type: nelsondiasandre/portuguese-qa-instruct-500
26
- metrics:
27
- - type: perplexity
28
- name: Perplexity (eval set, 100 examples)
29
- value: 1.86
30
  widget:
31
- - text: "<|im_start|>user\nQual e a capital de Portugal?<|im_end|>\n<|im_start|>assistant\n"
32
- example_title: "Capital de Portugal"
33
- - text: "<|im_start|>user\nO que e a fotossintese?<|im_end|>\n<|im_start|>assistant\n"
34
- example_title: "Ciencias"
35
- - text: "<|im_start|>user\nQuem escreveu Os Lusiadas?<|im_end|>\n<|im_start|>assistant\n"
36
- example_title: "Literatura Portuguesa"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  ---
38
 
39
  # Qwen2.5-1.5B PT-PT Q&A LoRA
 
1
  ---
2
  license: apache-2.0
3
  language:
4
+ - pt
5
  library_name: peft
6
  base_model: Qwen/Qwen2.5-1.5B-Instruct
7
  pipeline_tag: text-generation
8
  tags:
9
+ - peft
10
+ - lora
11
+ - portuguese
12
+ - question-answering
13
+ - instruction-tuning
14
+ - qwen2.5
15
+ - pt-pt
16
  datasets:
17
+ - nelsondiasandre/portuguese-qa-instruct-500
 
 
 
 
 
 
 
 
 
 
 
 
18
  widget:
19
+ - text: '<|im_start|>user
20
+
21
+ Qual e a capital de Portugal?<|im_end|>
22
+
23
+ <|im_start|>assistant
24
+
25
+ '
26
+ example_title: Capital de Portugal
27
+ - text: '<|im_start|>user
28
+
29
+ O que e a fotossintese?<|im_end|>
30
+
31
+ <|im_start|>assistant
32
+
33
+ '
34
+ example_title: Ciencias
35
+ - text: '<|im_start|>user
36
+
37
+ Quem escreveu Os Lusiadas?<|im_end|>
38
+
39
+ <|im_start|>assistant
40
+
41
+ '
42
+ example_title: Literatura Portuguesa
43
+ model-index:
44
+ - name: qwen25-1.5b-pt-qa-lora
45
+ results:
46
+ - task:
47
+ type: text-generation
48
+ dataset:
49
+ name: portuguese-qa-instruct-500
50
+ type: nelsondiasandre/portuguese-qa-instruct-500
51
+ metrics:
52
+ - type: perplexity
53
+ value: 1.86
54
+ name: Perplexity (eval set, 100 examples)
55
  ---
56
 
57
  # Qwen2.5-1.5B PT-PT Q&A LoRA
adapter_config.json CHANGED
@@ -1,45 +1,31 @@
1
- {
2
- "alora_invocation_tokens": null,
3
- "alpha_pattern": {},
4
- "arrow_config": null,
5
- "auto_mapping": null,
6
- "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
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": 16,
20
- "lora_bias": false,
21
- "lora_dropout": 0.05,
22
- "lora_ga_config": null,
23
- "megatron_config": null,
24
- "megatron_core": "megatron.core",
25
- "modules_to_save": null,
26
- "peft_type": "LORA",
27
- "peft_version": "0.19.1",
28
- "qalora_group_size": 16,
29
- "r": 8,
30
- "rank_pattern": {},
31
- "revision": null,
32
- "target_modules": [
33
- "o_proj",
34
- "q_proj",
35
- "k_proj",
36
- "v_proj"
37
- ],
38
- "target_parameters": null,
39
- "task_type": "CAUSAL_LM",
40
- "trainable_token_indices": null,
41
- "use_bdlora": null,
42
- "use_dora": false,
43
- "use_qalora": false,
44
- "use_rslora": false
45
  }
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "q_proj",
24
+ "k_proj",
25
+ "v_proj",
26
+ "o_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_dora": false,
30
+ "use_rslora": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecec0422e1869e9d9879268f839ffe090002c6cb922ec3b173c504c3d9a97d09
3
- size 8745704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:591df00138dec457908a8c6065b61ec9f4c0ed7d6061c9d272fe51cd67250215
3
+ size 17462432