Hugging Face's logo

anipanii
/
AskWise-PromptEngineer-1.5B-q4f16_1-MLC

MLC-LLM
askwise
prompt-engineering
qwen2
mlc
webgpu
Model card Files
xet
 Community
anipanii commited on
Commit
42c7486
·
verified ·
1 Parent(s): b0d053b

Upload folder using huggingface_hub

Browse files
Files changed (36) hide show
  1. .gitattributes +1 -0
  2. README.md +26 -0
  3. mlc-chat-config.json +86 -0
  4. params_shard_0.bin +3 -0
  5. params_shard_1.bin +3 -0
  6. params_shard_10.bin +3 -0
  7. params_shard_11.bin +3 -0
  8. params_shard_12.bin +3 -0
  9. params_shard_13.bin +3 -0
  10. params_shard_14.bin +3 -0
  11. params_shard_15.bin +3 -0
  12. params_shard_16.bin +3 -0
  13. params_shard_17.bin +3 -0
  14. params_shard_18.bin +3 -0
  15. params_shard_19.bin +3 -0
  16. params_shard_2.bin +3 -0
  17. params_shard_20.bin +3 -0
  18. params_shard_21.bin +3 -0
  19. params_shard_22.bin +3 -0
  20. params_shard_23.bin +3 -0
  21. params_shard_24.bin +3 -0
  22. params_shard_25.bin +3 -0
  23. params_shard_26.bin +3 -0
  24. params_shard_27.bin +3 -0
  25. params_shard_28.bin +3 -0
  26. params_shard_29.bin +3 -0
  27. params_shard_3.bin +3 -0
  28. params_shard_4.bin +3 -0
  29. params_shard_5.bin +3 -0
  30. params_shard_6.bin +3 -0
  31. params_shard_7.bin +3 -0
  32. params_shard_8.bin +3 -0
  33. params_shard_9.bin +3 -0
  34. tensor-cache.json +0 -0
  35. tokenizer.json +3 -0
  36. tokenizer_config.json +30 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: mlc-llm
4
+ tags:
5
+ - askwise
6
+ - prompt-engineering
7
+ - qwen2
8
+ - mlc
9
+ - webgpu
10
+ base_model: Qwen/Qwen2.5-1.5B-Instruct
11
+ ---
12
+
13
+ # AskWise-PromptEngineer-1.5B (MLC q4f16_1)
14
+
15
+ Fine-tuned **Qwen2.5-1.5B-Instruct** for AskWise Advanced rewrites:
16
+ messy user text → JSON `{"structured","advanced"}` prompt improvements (does **not** answer the task).
17
+
18
+ ## Use with AskWise Chrome extension
19
+
20
+ These are **MLC WebLLM weights** (`q4f16_1`). The extension reuses its packaged
21
+ Qwen2.5-1.5B WebGPU wasm — only this weight folder is downloaded from Hugging Face.
22
+
23
+ ## Converted with
24
+
25
+ - LoRA / QLoRA SFT on AskWise Instant seeds + synthetic prompt-engineering data
26
+ - `mlc_llm convert_weight … --quantization q4f16_1`
mlc-chat-config.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.1.0",
3
+ "model_type": "qwen2",
4
+ "quantization": "q4f16_1",
5
+ "model_config": {
6
+ "hidden_act": "silu",
7
+ "hidden_size": 1536,
8
+ "intermediate_size": 8960,
9
+ "num_attention_heads": 12,
10
+ "num_hidden_layers": 28,
11
+ "num_key_value_heads": 2,
12
+ "rms_norm_eps": 1e-06,
13
+ "rope_theta": 1000000.0,
14
+ "vocab_size": 151936,
15
+ "tie_word_embeddings": true,
16
+ "context_window_size": 32768,
17
+ "prefill_chunk_size": 8192,
18
+ "tensor_parallel_shards": 1,
19
+ "head_dim": 128,
20
+ "dtype": "bfloat16",
21
+ "max_batch_size": 128
22
+ },
23
+ "vocab_size": 151936,
24
+ "context_window_size": 32768,
25
+ "sliding_window_size": -1,
26
+ "prefill_chunk_size": 8192,
27
+ "attention_sink_size": -1,
28
+ "tensor_parallel_shards": 1,
29
+ "pipeline_parallel_stages": 1,
30
+ "active_vocab_size": 151665,
31
+ "temperature": 0.7,
32
+ "presence_penalty": 0.0,
33
+ "frequency_penalty": 0.0,
34
+ "repetition_penalty": 1.1,
35
+ "top_p": 0.8,
36
+ "tokenizer_files": [
37
+ "tokenizer.json",
38
+ "tokenizer_config.json"
39
+ ],
40
+ "tokenizer_info": {
41
+ "token_postproc_method": "byte_level",
42
+ "prepend_space_in_encode": false,
43
+ "strip_space_in_decode": false
44
+ },
45
+ "conv_template": {
46
+ "name": "qwen2",
47
+ "system_template": "<|im_start|>system\n{system_message}<|im_end|>\n",
48
+ "system_message": "You are a helpful assistant.",
49
+ "system_prefix_token_ids": null,
50
+ "add_role_after_system_message": true,
51
+ "roles": {
52
+ "user": "<|im_start|>user",
53
+ "assistant": "<|im_start|>assistant"
54
+ },
55
+ "role_templates": {
56
+ "user": "{user_message}",
57
+ "assistant": "{assistant_message}",
58
+ "tool": "{tool_message}"
59
+ },
60
+ "messages": [],
61
+ "seps": [
62
+ "<|im_end|>\n"
63
+ ],
64
+ "role_content_sep": "\n",
65
+ "role_empty_sep": "\n",
66
+ "stop_str": [
67
+ "<|endoftext|>",
68
+ "<|im_end|>"
69
+ ],
70
+ "stop_token_ids": [
71
+ 151643,
72
+ 151645
73
+ ],
74
+ "strip_reasoning_in_history": false,
75
+ "function_string": "",
76
+ "use_function_calling": false
77
+ },
78
+ "pad_token_id": 151643,
79
+ "bos_token_id": 151643,
80
+ "eos_token_id": [
81
+ 151645,
82
+ 151643
83
+ ],
84
+ "model_task": "chat",
85
+ "embedding_metadata": null
86
+ }
params_shard_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aadd5d49f95ef08d7d322f269bd9fb42fcb6d0c62dacb985969e7579455927eb
3
+ size 116686848
params_shard_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf960e2349d1f33ce2ac970963739fab673908024e9e31d4933bd80cc9f2c2cb
3
+ size 22330368
params_shard_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1711372a502aaac5943b93cc478c47d2fb289cbdc24de95539c2c718f52d44a0
3
+ size 26331136
params_shard_11.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6407965b8b2a239e12a53f4657f4affa655e1460c5d7120da3e713ad9aafe918
3
+ size 26331136
params_shard_12.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cac8d496bc571a829296bf8479a3b3a2aa4c8d3f758d2db6255ac14916c587e
3
+ size 26331136
params_shard_13.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b263021d8c442c85cef5c6d9b1ab5220fe9c4bbf1809f5cfccd7dd3dff469b9d
3
+ size 26331136
params_shard_14.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55e109e1662914d294042b1ceb82d6c699f6c918979bd95458303651b1b4f417
3
+ size 26331136
params_shard_15.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:526dad3f1565c3fc4088abecebb29266a4c25eaa7cd1b20a6327e283c8c27657
3
+ size 26331136
params_shard_16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57d63aceb8fe05092a68e9a7abd95c5e8998a6c124a522ee0da73ff967ee5bfd
3
+ size 26331136
params_shard_17.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4923fd4bf94a4442486f073c19709206742eb2df6699189ecce755b4e0fd6460
3
+ size 26331136
params_shard_18.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36eaf3bef9702773b37c923528279f25bb33ccc9b628901b0e5960baa9efa8ef
3
+ size 26331136
params_shard_19.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64d73f1d64a5bf173896f1379c308f1d0616cc5c7e55d80230749f7cc419eb28
3
+ size 26331136
params_shard_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd82ff2b9d570d241bdf6080720ee0e62ef52250c659e402dde7b28328edb36b
3
+ size 26331136
params_shard_20.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39c71e6b67f35d9d7c4fe71c364b48d22aa9c9e16cef7186514573d406cec7d7
3
+ size 26331136
params_shard_21.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f84a5cad27c021a939220a4b6eef71433ffaaf6377ab80db918c402b060baef3
3
+ size 26331136
params_shard_22.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93977f77ee7663c35223d57f4177c1e78eb33ae48749d3a381c0daf1a5eaa6e0
3
+ size 26331136
params_shard_23.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e9602148ba14de82a9264863eb0771a889cba21408e914960751c2ac4e6160e
3
+ size 26331136
params_shard_24.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4ef684ee6bfb92056f104d95e4f53105cd62c2133c1976317edfa75f88350d0
3
+ size 26331136
params_shard_25.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:705390b58e3bc98df28699b300a1346be6aa27a234a077d392be7d29799b2679
3
+ size 26331136
params_shard_26.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c2ea014fa80201453fe1a83149830b8ffb97ad61239a43ae18d6f54ff9190aa
3
+ size 26331136
params_shard_27.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0ee2dc1c9e2e90790677fe8bdc34c127f794a78bc7262604cb809fc28e6f07a
3
+ size 26331136
params_shard_28.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ade5e868c5018073cecb576ed7fab34fa7df5ba09c5f05859cea5862f91fe058
3
+ size 26331136
params_shard_29.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b969f1c4335d4e496a6704b217c9fbf09a0380093e71135b159e61be818dd66d
3
+ size 18589696
params_shard_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d7286277d5e8e6e75cf33a530eecb3ec3810b600ea0d5c07b61f1449c3af362
3
+ size 26331136
params_shard_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87464ca8279170e027229a0b7261f456184de9ef600c45125d6d35ab739634d1
3
+ size 26331136
params_shard_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b86a2ba1f50fe5780f2bdc0bff9bbb5b2891aaf24da133966f72f84cc0766d71
3
+ size 26331136
params_shard_6.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff707d863a07e2a8817767e7f5af7f53574c0e92fcfbd1107b8752d6a1318686
3
+ size 26331136
params_shard_7.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a4757126ed8b473025eae286d90f0d53b3e1f2ce968eefc20780946ea191a52
3
+ size 26331136
params_shard_8.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22e8f9f8d2dc47339d821fa9cafad4c2b0c046197611301bdde7174cab92b85a
3
+ size 26331136
params_shard_9.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3752b540bc075fc3b7a671621ddf7d2260e6e3940ad05e53d189950b7ce3a09
3
+ size 26331136
tensor-cache.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
3
+ size 11421892
tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": false,
24
+ "local_files_only": false,
25
+ "model_max_length": 131072,
26
+ "pad_token": "<|endoftext|>",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null
30
+ }