Commit ·
1937932
0
Parent(s):
Super-squash branch 'main' using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +41 -0
- README.md +59 -0
- qwen25-7b-oracle-q3_14b/added_tokens.json +24 -0
- qwen25-7b-oracle-q3_14b/config.json +29 -0
- qwen25-7b-oracle-q3_14b/generation_config.json +14 -0
- qwen25-7b-oracle-q3_14b/merges.txt +0 -0
- qwen25-7b-oracle-q3_14b/model-00001-of-00007.safetensors +3 -0
- qwen25-7b-oracle-q3_14b/model-00002-of-00007.safetensors +3 -0
- qwen25-7b-oracle-q3_14b/model-00003-of-00007.safetensors +3 -0
- qwen25-7b-oracle-q3_14b/model-00004-of-00007.safetensors +3 -0
- qwen25-7b-oracle-q3_14b/model-00005-of-00007.safetensors +3 -0
- qwen25-7b-oracle-q3_14b/model-00006-of-00007.safetensors +3 -0
- qwen25-7b-oracle-q3_14b/model-00007-of-00007.safetensors +3 -0
- qwen25-7b-oracle-q3_14b/model.safetensors.index.json +346 -0
- qwen25-7b-oracle-q3_14b/special_tokens_map.json +31 -0
- qwen25-7b-oracle-q3_14b/tokenizer.json +3 -0
- qwen25-7b-oracle-q3_14b/tokenizer_config.json +207 -0
- qwen25-7b-oracle-q3_14b/vocab.json +0 -0
- qwen25-7b-oracle-q3_32b/added_tokens.json +24 -0
- qwen25-7b-oracle-q3_32b/chat_template.jinja +54 -0
- qwen25-7b-oracle-q3_32b/config.json +29 -0
- qwen25-7b-oracle-q3_32b/generation_config.json +14 -0
- qwen25-7b-oracle-q3_32b/merges.txt +0 -0
- qwen25-7b-oracle-q3_32b/model-00001-of-00007.safetensors +3 -0
- qwen25-7b-oracle-q3_32b/model-00002-of-00007.safetensors +3 -0
- qwen25-7b-oracle-q3_32b/model-00003-of-00007.safetensors +3 -0
- qwen25-7b-oracle-q3_32b/model-00004-of-00007.safetensors +3 -0
- qwen25-7b-oracle-q3_32b/model-00005-of-00007.safetensors +3 -0
- qwen25-7b-oracle-q3_32b/model-00006-of-00007.safetensors +3 -0
- qwen25-7b-oracle-q3_32b/model-00007-of-00007.safetensors +3 -0
- qwen25-7b-oracle-q3_32b/model.safetensors.index.json +346 -0
- qwen25-7b-oracle-q3_32b/special_tokens_map.json +31 -0
- qwen25-7b-oracle-q3_32b/tokenizer.json +3 -0
- qwen25-7b-oracle-q3_32b/tokenizer_config.json +207 -0
- qwen25-7b-oracle-q3_32b/vocab.json +0 -0
- qwen25-7b-rep-q3_14b-clean/added_tokens.json +24 -0
- qwen25-7b-rep-q3_14b-clean/config.json +29 -0
- qwen25-7b-rep-q3_14b-clean/generation_config.json +14 -0
- qwen25-7b-rep-q3_14b-clean/merges.txt +0 -0
- qwen25-7b-rep-q3_14b-clean/model-00001-of-00007.safetensors +3 -0
- qwen25-7b-rep-q3_14b-clean/model-00002-of-00007.safetensors +3 -0
- qwen25-7b-rep-q3_14b-clean/model-00003-of-00007.safetensors +3 -0
- qwen25-7b-rep-q3_14b-clean/model-00004-of-00007.safetensors +3 -0
- qwen25-7b-rep-q3_14b-clean/model-00005-of-00007.safetensors +3 -0
- qwen25-7b-rep-q3_14b-clean/model-00006-of-00007.safetensors +3 -0
- qwen25-7b-rep-q3_14b-clean/model-00007-of-00007.safetensors +3 -0
- qwen25-7b-rep-q3_14b-clean/model.safetensors.index.json +346 -0
- qwen25-7b-rep-q3_14b-clean/special_tokens_map.json +31 -0
- qwen25-7b-rep-q3_14b-clean/tokenizer.json +3 -0
- qwen25-7b-rep-q3_14b-clean/tokenizer_config.json +207 -0
.gitattributes
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz 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 |
+
qwen25-7b-rep-q3_14b-original/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
qwen25-7b-oracle-q3_32b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
qwen25-7b-rep-q3_32b-original/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
qwen25-7b-oracle-q3_14b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
qwen25-7b-rep-q3_14b-clean/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
qwen25-7b-rep-q3_32b-clean/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
language: [en]
|
| 6 |
+
tags: [reasoning, distillation, math, reasoning-trace-exposure, rep]
|
| 7 |
+
datasets: [Chia-Mu-Lab/REP-datasets]
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# REP-models — students distilled from exposed reasoning traces
|
| 11 |
+
|
| 12 |
+
Checkpoints released with **"Hidden Thoughts Are Not Secret: Reasoning-Trace
|
| 13 |
+
Exposure in LLMs"** (EMNLP 2026, [arXiv:2606.00642](https://arxiv.org/abs/2606.00642)). Code: <https://github.com/0x-yuan/REP>.
|
| 14 |
+
|
| 15 |
+
Every student is `Qwen/Qwen2.5-7B-Instruct` fine-tuned on one of the corpora in
|
| 16 |
+
`Chia-Mu-Lab/REP-datasets`. One sub-folder per final model.
|
| 17 |
+
|
| 18 |
+
## Sub-folders
|
| 19 |
+
|
| 20 |
+
| Sub-folder | Supervision | Training data (config in `REP-datasets`) |
|
| 21 |
+
|---|---|---|
|
| 22 |
+
| `qwen25-7b-rep-q3_14b-clean` | REP-exposed trace of Qwen3-14B, answer-correct rows | `distill_q3_14b_clean` |
|
| 23 |
+
| `qwen25-7b-rep-q3_14b-original` | REP-exposed trace of Qwen3-14B, all structurally valid rows | `distill_q3_14b_original` |
|
| 24 |
+
| `qwen25-7b-rep-q3_32b-clean` | REP-exposed trace of Qwen3-32B, answer-correct rows | `distill_q3_32b_clean` |
|
| 25 |
+
| `qwen25-7b-rep-q3_32b-original` | REP-exposed trace of Qwen3-32B, all structurally valid rows | `distill_q3_32b_original` |
|
| 26 |
+
| `qwen25-7b-oracle-q3_14b` | Qwen3-14B **internal** trace (oracle upper bound) | Qwen3-14B internal traces (not released) |
|
| 27 |
+
| `qwen25-7b-oracle-q3_32b` | Qwen3-32B **internal** trace (oracle upper bound) | Qwen3-32B internal traces (not released) |
|
| 28 |
+
|
| 29 |
+
## Results (paper Table 2 protocol: n=3, T=0.5; JEE = math subset, strict / partial)
|
| 30 |
+
|
| 31 |
+
| Model | MATH500 | AIME24 | AIME25 | JEE-Math | LiveCodeBench |
|
| 32 |
+
|---|---|---|---|---|---|
|
| 33 |
+
| Qwen2.5-7B-Instruct (base) | 71.0 | 8.9 | 2.2 | 32.2 / 35.9 | 15.8 |
|
| 34 |
+
| `rep-q3_14b-clean` | **75.8** | 14.4 | 13.3 | 35.2 / 39.5 | **19.0** |
|
| 35 |
+
| `rep-q3_14b-original` | 72.4 | 12.2 | 13.3 | 33.5 / 38.9 | 18.3 |
|
| 36 |
+
| `rep-q3_32b-clean` | 72.8 | 14.4 | **17.8** | 36.4 / 41.1 | 15.8 |
|
| 37 |
+
| `rep-q3_32b-original` | 73.9 | 13.3 | 13.3 | **38.1 / 42.2** | 16.5 |
|
| 38 |
+
| `oracle-q3_14b` | 70.3 | 14.4 | 13.3 | 48.5 / 51.2 | 14.7 |
|
| 39 |
+
| `oracle-q3_32b` | 70.0 | 16.7 | 15.6 | 46.4 / 49.3 | 15.8 |
|
| 40 |
+
|
| 41 |
+
Traces exposed through prompting alone match or exceed the oracle internal
|
| 42 |
+
trace as distillation supervision on math; see the paper for the full analysis.
|
| 43 |
+
|
| 44 |
+
## Responsible use
|
| 45 |
+
|
| 46 |
+
Research artifact for studying reasoning-trace exposure and defenses. All
|
| 47 |
+
training data derive from open-weight models. See `ETHICS.md` in the code
|
| 48 |
+
release.
|
| 49 |
+
|
| 50 |
+
## Citation
|
| 51 |
+
|
| 52 |
+
```bibtex
|
| 53 |
+
@inproceedings{lu2026hiddenthoughts,
|
| 54 |
+
title = {Hidden Thoughts Are Not Secret: Reasoning-Trace Exposure in LLMs},
|
| 55 |
+
author = {Lu, Yu-An and Tsai, Ci-Yang and Tsai, Yu-Lin and Popa, Raluca Ada and Yu, Chia-Mu},
|
| 56 |
+
booktitle = {Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
|
| 57 |
+
year = {2026}
|
| 58 |
+
}
|
| 59 |
+
```
|
qwen25-7b-oracle-q3_14b/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
qwen25-7b-oracle-q3_14b/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 3584,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 18944,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 28,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 28,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 1000000.0,
|
| 22 |
+
"sliding_window": null,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.46.1",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"use_sliding_window": false,
|
| 28 |
+
"vocab_size": 152064
|
| 29 |
+
}
|
qwen25-7b-oracle-q3_14b/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.46.1"
|
| 14 |
+
}
|
qwen25-7b-oracle-q3_14b/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen25-7b-oracle-q3_14b/model-00001-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d031bee30543416e0f5031cd11e24f2a0a79b7b61f34a5af5e116a10a83cd28a
|
| 3 |
+
size 4976687216
|
qwen25-7b-oracle-q3_14b/model-00002-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d42c7041d956199e2a334f00ed8066e40641a9fa2df79021b28fd949ffe7727a
|
| 3 |
+
size 4778622352
|
qwen25-7b-oracle-q3_14b/model-00003-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95f7816712651441c7303be4f5e97b7c07cfdfba78aa55b9773a12623ce1d979
|
| 3 |
+
size 4932743960
|
qwen25-7b-oracle-q3_14b/model-00004-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8501e8fa90909ed6b12b721d94383bc46dd5ab788155b4780c878d4532a0ed6
|
| 3 |
+
size 4932743992
|
qwen25-7b-oracle-q3_14b/model-00005-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ad3a88379ed2f29ca07d0431a26ec816ca909f29f3ae9ed9472c1cc64501cff
|
| 3 |
+
size 4998852296
|
qwen25-7b-oracle-q3_14b/model-00006-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccc9236d15335cd421d2f32502624cb1a899197b088d8d4f15913bcb776fa29f
|
| 3 |
+
size 3662865184
|
qwen25-7b-oracle-q3_14b/model-00007-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c5ac96200968ac96f9c217c5eecf6ac03a5716e30fc2c4354eab78605c2c270
|
| 3 |
+
size 2179989632
|
qwen25-7b-oracle-q3_14b/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 30462466048
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00007-of-00007.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 260 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 272 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 284 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 296 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 308 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 320 |
+
"model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 332 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 344 |
+
"model.norm.weight": "model-00006-of-00007.safetensors"
|
| 345 |
+
}
|
| 346 |
+
}
|
qwen25-7b-oracle-q3_14b/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
qwen25-7b-oracle-q3_14b/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:873f9c3d5e28877c9915f09c76bbfc8a0b7ae244781692ab2b0877873b918022
|
| 3 |
+
size 11421996
|
qwen25-7b-oracle-q3_14b/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function 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><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
qwen25-7b-oracle-q3_14b/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen25-7b-oracle-q3_32b/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
qwen25-7b-oracle-q3_32b/chat_template.jinja
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 4 |
+
{{- messages[0]['content'] }}
|
| 5 |
+
{%- else %}
|
| 6 |
+
{{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 9 |
+
{%- for tool in tools %}
|
| 10 |
+
{{- "\n" }}
|
| 11 |
+
{{- tool | tojson }}
|
| 12 |
+
{%- endfor %}
|
| 13 |
+
{{- "\n</tools>\n\nFor each function 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><|im_end|>\n" }}
|
| 14 |
+
{%- else %}
|
| 15 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 16 |
+
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
| 17 |
+
{%- else %}
|
| 18 |
+
{{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
|
| 19 |
+
{%- endif %}
|
| 20 |
+
{%- endif %}
|
| 21 |
+
{%- for message in messages %}
|
| 22 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
| 23 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 24 |
+
{%- elif message.role == "assistant" %}
|
| 25 |
+
{{- '<|im_start|>' + message.role }}
|
| 26 |
+
{%- if message.content %}
|
| 27 |
+
{{- '\n' + message.content }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{%- for tool_call in message.tool_calls %}
|
| 30 |
+
{%- if tool_call.function is defined %}
|
| 31 |
+
{%- set tool_call = tool_call.function %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '\n<tool_call>\n{"name": "' }}
|
| 34 |
+
{{- tool_call.name }}
|
| 35 |
+
{{- '", "arguments": ' }}
|
| 36 |
+
{{- tool_call.arguments | tojson }}
|
| 37 |
+
{{- '}\n</tool_call>' }}
|
| 38 |
+
{%- endfor %}
|
| 39 |
+
{{- '<|im_end|>\n' }}
|
| 40 |
+
{%- elif message.role == "tool" %}
|
| 41 |
+
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
| 42 |
+
{{- '<|im_start|>user' }}
|
| 43 |
+
{%- endif %}
|
| 44 |
+
{{- '\n<tool_response>\n' }}
|
| 45 |
+
{{- message.content }}
|
| 46 |
+
{{- '\n</tool_response>' }}
|
| 47 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 48 |
+
{{- '<|im_end|>\n' }}
|
| 49 |
+
{%- endif %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{%- if add_generation_prompt %}
|
| 53 |
+
{{- '<|im_start|>assistant\n' }}
|
| 54 |
+
{%- endif %}
|
qwen25-7b-oracle-q3_32b/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 3584,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 18944,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 28,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 28,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 1000000.0,
|
| 22 |
+
"sliding_window": null,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.46.1",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"use_sliding_window": false,
|
| 28 |
+
"vocab_size": 152064
|
| 29 |
+
}
|
qwen25-7b-oracle-q3_32b/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.46.1"
|
| 14 |
+
}
|
qwen25-7b-oracle-q3_32b/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen25-7b-oracle-q3_32b/model-00001-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfcb4f3c9ac56b1987a3377b090f4dc86afb3edbff8d3768154166b7ad44ba55
|
| 3 |
+
size 4976687216
|
qwen25-7b-oracle-q3_32b/model-00002-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b441a8cbf01623200157f4a20ecd12ba7b368277496d692ad03558876d50912
|
| 3 |
+
size 4778622352
|
qwen25-7b-oracle-q3_32b/model-00003-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e26af805800e6f0b97e39aa538486753a795029bb87d33ee92ff1936f6e3bcff
|
| 3 |
+
size 4932743960
|
qwen25-7b-oracle-q3_32b/model-00004-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6ec001c6e0c0f3d75b2055b8839503d19e93045f5af6b9a10a9bcc4a7e94f27
|
| 3 |
+
size 4932743992
|
qwen25-7b-oracle-q3_32b/model-00005-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fa321f7c6cebe6873584b99c13c3416f6d56437816f2bd930ac0e73bd15435d
|
| 3 |
+
size 4998852296
|
qwen25-7b-oracle-q3_32b/model-00006-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4b734625ff8bb0cd960644a679936fbb86efbf491393dffbd495c957a054f8d
|
| 3 |
+
size 3662865184
|
qwen25-7b-oracle-q3_32b/model-00007-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c228cee1e7bce87e5df45bcb9c5605ef689c58568642d3748e8bebad25204642
|
| 3 |
+
size 2179989632
|
qwen25-7b-oracle-q3_32b/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 30462466048
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00007-of-00007.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 260 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 272 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 284 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 296 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 308 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 320 |
+
"model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 332 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 344 |
+
"model.norm.weight": "model-00006-of-00007.safetensors"
|
| 345 |
+
}
|
| 346 |
+
}
|
qwen25-7b-oracle-q3_32b/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
qwen25-7b-oracle-q3_32b/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
qwen25-7b-oracle-q3_32b/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"clean_up_tokenization_spaces": false,
|
| 199 |
+
"eos_token": "<|im_end|>",
|
| 200 |
+
"errors": "replace",
|
| 201 |
+
"extra_special_tokens": {},
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
qwen25-7b-oracle-q3_32b/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen25-7b-rep-q3_14b-clean/added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
qwen25-7b-rep-q3_14b-clean/config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 3584,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 18944,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 28,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 28,
|
| 17 |
+
"num_hidden_layers": 28,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 1000000.0,
|
| 22 |
+
"sliding_window": null,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.46.1",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"use_sliding_window": false,
|
| 28 |
+
"vocab_size": 152064
|
| 29 |
+
}
|
qwen25-7b-rep-q3_14b-clean/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_k": 20,
|
| 12 |
+
"top_p": 0.8,
|
| 13 |
+
"transformers_version": "4.46.1"
|
| 14 |
+
}
|
qwen25-7b-rep-q3_14b-clean/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
qwen25-7b-rep-q3_14b-clean/model-00001-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30ead2eef8e65b96489290db5d9163553e9fe6676557ad6baf330e3fd31149c0
|
| 3 |
+
size 4976687216
|
qwen25-7b-rep-q3_14b-clean/model-00002-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:389e4afbd8fa56605b6962a897b350382d5344bfcd0a13a5b0b708f4970de75b
|
| 3 |
+
size 4778622352
|
qwen25-7b-rep-q3_14b-clean/model-00003-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f28d1f83ea214a8b426c64723e10f5433f2046720c2d6c3d574f04f5ede8e76
|
| 3 |
+
size 4932743960
|
qwen25-7b-rep-q3_14b-clean/model-00004-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:580fc356c84698e895c649ef3e756477fcbef7ee83b45aad531a5aee5c898c91
|
| 3 |
+
size 4932743992
|
qwen25-7b-rep-q3_14b-clean/model-00005-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac531ad550767874fd9b50de070cec984ce14851bc8f1fcdb7c4904c4d7a50e2
|
| 3 |
+
size 4998852296
|
qwen25-7b-rep-q3_14b-clean/model-00006-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0efa08d2e4e022c603adcc248b2be05f49318cb045db5ef2c19ab94b2b68ce45
|
| 3 |
+
size 3662865184
|
qwen25-7b-rep-q3_14b-clean/model-00007-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0502868df22b7911b6636ca26851835c2d22f8f625c8680f30def1b1e457c94
|
| 3 |
+
size 2179989632
|
qwen25-7b-rep-q3_14b-clean/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 30462466048
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00007-of-00007.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 260 |
+
"model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 261 |
+
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 262 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 263 |
+
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 264 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 265 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 266 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 272 |
+
"model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 273 |
+
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 274 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 275 |
+
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 276 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 277 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 278 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 279 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 280 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 281 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 282 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 283 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 284 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 285 |
+
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 286 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 287 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 288 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 289 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 290 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 291 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 292 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 293 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 294 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 295 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 296 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 297 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 298 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 299 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 300 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 301 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 302 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 303 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 304 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 305 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 306 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 307 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 308 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 309 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 310 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 311 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 312 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 313 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 314 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 315 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 316 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 317 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 318 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 319 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 320 |
+
"model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 321 |
+
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 322 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 323 |
+
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 324 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 325 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
| 326 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 327 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 328 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
| 329 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 330 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
| 331 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 332 |
+
"model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 333 |
+
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 334 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 335 |
+
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
| 338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
| 341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
| 343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 344 |
+
"model.norm.weight": "model-00006-of-00007.safetensors"
|
| 345 |
+
}
|
| 346 |
+
}
|
qwen25-7b-rep-q3_14b-clean/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
qwen25-7b-rep-q3_14b-clean/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:873f9c3d5e28877c9915f09c76bbfc8a0b7ae244781692ab2b0877873b918022
|
| 3 |
+
size 11421996
|
qwen25-7b-rep-q3_14b-clean/tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function 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><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|