Commit ·
9995a75
0
Parent(s):
Add: Apriel 1.6
Browse files- .gitattributes +36 -0
- README.md +904 -0
- chat_template.jinja +159 -0
- config.json +170 -0
- generation_config.json +6 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +664 -0
- preprocessor_config.json +27 -0
- processor_config.json +7 -0
- special_tokens_map.json +30 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,904 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
pipeline_tag: image-text-to-text
|
| 4 |
+
library_name: transformers
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
# Apriel-1.6-15B-Thinker: Cost-efficient Frontier Multimodal Performance
|
| 8 |
+
|
| 9 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/63d3095c2727d7888cbb54e2/Lt1t0tOO5emz1X23Azg-E.png" width="120" alt="thumbnail"/> `/ˈɑː.pri.əl/`
|
| 10 |
+
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Table of Contents
|
| 14 |
+
|
| 15 |
+
1. [Summary](#summary)
|
| 16 |
+
2. [Evaluation](#evaluation)
|
| 17 |
+
3. [Intended Use](#intended-use)
|
| 18 |
+
4. [How to Use](#how-to-use)
|
| 19 |
+
5. [Training Details](#training-details)
|
| 20 |
+
6. [Limitations](#limitations)
|
| 21 |
+
7. [Security and Responsible Use](#security-and-responsible-use)
|
| 22 |
+
8. [License](#license)
|
| 23 |
+
9. [Citation](#citation)
|
| 24 |
+
|
| 25 |
+
---
|
| 26 |
+
|
| 27 |
+
# Summary
|
| 28 |
+
|
| 29 |
+
**Apriel-1.6-15B-Thinker** is an updated multimodal reasoning model in ServiceNow’s Apriel SLM series, building on [**Apriel-1.5-15B-Thinker**](https://huggingface.co/ServiceNow-AI/Apriel-1.5-15b-Thinker).
|
| 30 |
+
With significantly improved text and image reasoning capabilities, Apriel-1.6 achieves competitive performance against models up to 10x its size.
|
| 31 |
+
Like its predecessor, it benefits from extensive continual pre-training across both text and image domains.
|
| 32 |
+
We additionally perform post-training that focuses on Supervised Finetuning (SFT) and Reinforcement Learning (RL).
|
| 33 |
+
Apriel-1.6 obtains frontier performance without sacrificing reasoning token efficiency.
|
| 34 |
+
The model improves or maintains task performance when compared with Apriel-1.5-15B-Thinker, while **reducing reasoning token usage by more than 30\%**.
|
| 35 |
+
|
| 36 |
+
**Highlights**
|
| 37 |
+
|
| 38 |
+
- Achieves a score of **57** on the Artificial Analysis index outperforming models like Gemini 2.5 Flash, Claude Haiku 4.5 and GPT OSS 20b. It obtains a score on par with Qwen3 235B A22B, while being significantly more efficient.
|
| 39 |
+
- **Reduces reasoning token usage by more than 30%**, delivering significantly better efficiency than Apriel-1.5-15B-Thinker.
|
| 40 |
+
- Scores **69** on Tau2 Bench Telecom and **69** on IFBench, which are key benchmarks for the enterprise domain.
|
| 41 |
+
- At 15B parameters, the model fits on a single GPU, making it highly memory-efficient.
|
| 42 |
+
- Based on community feedback on Apriel-1.5-15B-Thinker, we simplified the chat template by removing redundant tags and introduced four special tokens to the tokenizer (`<tool_calls>`, `</tool_calls>`, `[BEGIN FINAL RESPONSE]`, `<|end|>`) for easier output parsing.
|
| 43 |
+
|
| 44 |
+
Please see our [blog post](https://huggingface.co/blog/ServiceNow-AI/apriel-1p6-15b-thinker) for more details
|
| 45 |
+
|
| 46 |
+
---
|
| 47 |
+
|
| 48 |
+
# Evaluation
|
| 49 |
+
|
| 50 |
+
- Text benchmarks included in the Artificial Analysis Index v3.0 use scores reported by [Artificial Analysis](https://artificialanalysis.ai/). All other benchmarks were evaluated internally.
|
| 51 |
+
|
| 52 |
+
<table>
|
| 53 |
+
<tr>
|
| 54 |
+
<th>Category</th>
|
| 55 |
+
<th>Benchmark</th>
|
| 56 |
+
<th>Apriel-1.6-15B-Thinker</th>
|
| 57 |
+
<th>Apriel-1.5-15B-Thinker</th>
|
| 58 |
+
<th>GPT OSS 120B</th>
|
| 59 |
+
<th>DeepSeek R1 0528</th>
|
| 60 |
+
<th>Gemini 2.5 Flash (Sep)</th>
|
| 61 |
+
<th>GPT 5 mini (high)</th>
|
| 62 |
+
<th>Claude 4.5 Sonnet (thinking)</th>
|
| 63 |
+
<th>o3-mini (high)</th>
|
| 64 |
+
</tr>
|
| 65 |
+
|
| 66 |
+
<!-- Function Calling -->
|
| 67 |
+
<tr>
|
| 68 |
+
<td rowspan="5" class="category">Function Calling</td>
|
| 69 |
+
<td>BFCL v3 only</td>
|
| 70 |
+
<td>63.50</td>
|
| 71 |
+
<td>51.88</td>
|
| 72 |
+
<td>50.62</td>
|
| 73 |
+
<td>39.75</td>
|
| 74 |
+
<td>39.75</td>
|
| 75 |
+
<td>17.62</td>
|
| 76 |
+
<td>-</td>
|
| 77 |
+
<td>50</td>
|
| 78 |
+
</tr>
|
| 79 |
+
<tr>
|
| 80 |
+
<td>Tau2 bench Telecom</td>
|
| 81 |
+
<td>69</td>
|
| 82 |
+
<td>57.8</td>
|
| 83 |
+
<td>66</td>
|
| 84 |
+
<td>37</td>
|
| 85 |
+
<td>32</td>
|
| 86 |
+
<td>68</td>
|
| 87 |
+
<td>50.8</td>
|
| 88 |
+
<td>31</td>
|
| 89 |
+
</tr>
|
| 90 |
+
<tr>
|
| 91 |
+
<td>Tau2 bench Retail</td>
|
| 92 |
+
<td>66.67</td>
|
| 93 |
+
<td>46.78</td>
|
| 94 |
+
<td>61.4</td>
|
| 95 |
+
<td>59.94</td>
|
| 96 |
+
<td>61.69</td>
|
| 97 |
+
<td>73.39</td>
|
| 98 |
+
<td>69.8</td>
|
| 99 |
+
<td>75.73</td>
|
| 100 |
+
</tr>
|
| 101 |
+
<tr>
|
| 102 |
+
<td>Tau2 bench Airline</td>
|
| 103 |
+
<td>58</td>
|
| 104 |
+
<td>52</td>
|
| 105 |
+
<td>45.3</td>
|
| 106 |
+
<td>47.33</td>
|
| 107 |
+
<td>56.66</td>
|
| 108 |
+
<td>59.33</td>
|
| 109 |
+
<td>58</td>
|
| 110 |
+
<td>61.33</td>
|
| 111 |
+
</tr>
|
| 112 |
+
<tr>
|
| 113 |
+
<td>ComplexFuncBench</td>
|
| 114 |
+
<td>33.2</td>
|
| 115 |
+
<td>19</td>
|
| 116 |
+
<td>24.6</td>
|
| 117 |
+
<td>24.2</td>
|
| 118 |
+
<td>26.3</td>
|
| 119 |
+
<td>37.5</td>
|
| 120 |
+
<td>24.6</td>
|
| 121 |
+
<td>18.9</td>
|
| 122 |
+
</tr>
|
| 123 |
+
|
| 124 |
+
<!-- Instruction Following -->
|
| 125 |
+
<tr>
|
| 126 |
+
<td rowspan="4" class="category">Instruction Following</td>
|
| 127 |
+
<td>Agent IF</td>
|
| 128 |
+
<td>57.2</td>
|
| 129 |
+
<td>55</td>
|
| 130 |
+
<td>54.20</td>
|
| 131 |
+
<td>52.20</td>
|
| 132 |
+
<td>49.70</td>
|
| 133 |
+
<td>57.60</td>
|
| 134 |
+
<td>54.50</td>
|
| 135 |
+
<td>54.90</td>
|
| 136 |
+
</tr>
|
| 137 |
+
<tr>
|
| 138 |
+
<td>Multi IF</td>
|
| 139 |
+
<td>83.34</td>
|
| 140 |
+
<td>76.91</td>
|
| 141 |
+
<td>82.95</td>
|
| 142 |
+
<td>73.76</td>
|
| 143 |
+
<td>82.49</td>
|
| 144 |
+
<td>85.37</td>
|
| 145 |
+
<td>84.32</td>
|
| 146 |
+
<td>87.28</td>
|
| 147 |
+
</tr>
|
| 148 |
+
<tr>
|
| 149 |
+
<td>Multi-Challenge</td>
|
| 150 |
+
<td>46.15</td>
|
| 151 |
+
<td>41.39</td>
|
| 152 |
+
<td>46.90</td>
|
| 153 |
+
<td>44.50</td>
|
| 154 |
+
<td>49.08</td>
|
| 155 |
+
<td>57.90</td>
|
| 156 |
+
<td>42.49</td>
|
| 157 |
+
<td>38.46</td>
|
| 158 |
+
</tr>
|
| 159 |
+
<tr>
|
| 160 |
+
<td>IF Bench</td>
|
| 161 |
+
<td>69</td>
|
| 162 |
+
<td>62</td>
|
| 163 |
+
<td>69</td>
|
| 164 |
+
<td>40</td>
|
| 165 |
+
<td>50</td>
|
| 166 |
+
<td>75</td>
|
| 167 |
+
<td>57</td>
|
| 168 |
+
<td>70.07</td>
|
| 169 |
+
</tr>
|
| 170 |
+
|
| 171 |
+
<!-- Math -->
|
| 172 |
+
<tr>
|
| 173 |
+
<td class="category">Math</td>
|
| 174 |
+
<td>AIME 25</td>
|
| 175 |
+
<td>88</td>
|
| 176 |
+
<td>88</td>
|
| 177 |
+
<td>93</td>
|
| 178 |
+
<td>76</td>
|
| 179 |
+
<td>73</td>
|
| 180 |
+
<td>91</td>
|
| 181 |
+
<td>88</td>
|
| 182 |
+
<td>86.67</td>
|
| 183 |
+
</tr>
|
| 184 |
+
|
| 185 |
+
<!-- Coding -->
|
| 186 |
+
<tr>
|
| 187 |
+
<td rowspan="3" class="category">Coding</td>
|
| 188 |
+
<td>Struct Eval</td>
|
| 189 |
+
<td>79</td>
|
| 190 |
+
<td>48.50</td>
|
| 191 |
+
<td>71</td>
|
| 192 |
+
<td>73</td>
|
| 193 |
+
<td>70</td>
|
| 194 |
+
<td>69.92</td>
|
| 195 |
+
<td>76</td>
|
| 196 |
+
<td>73</td>
|
| 197 |
+
</tr>
|
| 198 |
+
<tr>
|
| 199 |
+
<td>LCB</td>
|
| 200 |
+
<td>81</td>
|
| 201 |
+
<td>73</td>
|
| 202 |
+
<td>65</td>
|
| 203 |
+
<td>77</td>
|
| 204 |
+
<td>70</td>
|
| 205 |
+
<td>84</td>
|
| 206 |
+
<td>71</td>
|
| 207 |
+
<td>73</td>
|
| 208 |
+
</tr>
|
| 209 |
+
<tr>
|
| 210 |
+
<td>SciCode</td>
|
| 211 |
+
<td>37</td>
|
| 212 |
+
<td>35</td>
|
| 213 |
+
<td>36</td>
|
| 214 |
+
<td>40</td>
|
| 215 |
+
<td>41</td>
|
| 216 |
+
<td>39</td>
|
| 217 |
+
<td>45</td>
|
| 218 |
+
<td>40</td>
|
| 219 |
+
</tr>
|
| 220 |
+
|
| 221 |
+
<!-- Agentic -->
|
| 222 |
+
<tr>
|
| 223 |
+
<td rowspan="7" class="category">Agentic</td>
|
| 224 |
+
<td>DeepresearchBench</td>
|
| 225 |
+
<td>36.47</td>
|
| 226 |
+
<td>32.73</td>
|
| 227 |
+
<td>36.30</td>
|
| 228 |
+
<td>34.19</td>
|
| 229 |
+
<td>38.15</td>
|
| 230 |
+
<td>-</td>
|
| 231 |
+
<td>-</td>
|
| 232 |
+
<td>33.40</td>
|
| 233 |
+
</tr>
|
| 234 |
+
<tr>
|
| 235 |
+
<td>GAIA</td>
|
| 236 |
+
<td>40</td>
|
| 237 |
+
<td>30.91</td>
|
| 238 |
+
<td>21.21</td>
|
| 239 |
+
<td>32.12</td>
|
| 240 |
+
<td>47.88</td>
|
| 241 |
+
<td>65.45</td>
|
| 242 |
+
<td>69.09</td>
|
| 243 |
+
<td>23.03</td>
|
| 244 |
+
</tr>
|
| 245 |
+
<tr>
|
| 246 |
+
<td>Work-Arena L1</td>
|
| 247 |
+
<td>58</td>
|
| 248 |
+
<td>51.5</td>
|
| 249 |
+
<td>50.9</td>
|
| 250 |
+
<td>63.9</td>
|
| 251 |
+
<td>51.8</td>
|
| 252 |
+
<td>65.5</td>
|
| 253 |
+
<td>62.7</td>
|
| 254 |
+
<td>52.4</td>
|
| 255 |
+
</tr>
|
| 256 |
+
<tr>
|
| 257 |
+
<td>OS World Small</td>
|
| 258 |
+
<td>16.70</td>
|
| 259 |
+
<td>13.90</td>
|
| 260 |
+
<td>16.70</td>
|
| 261 |
+
<td>25</td>
|
| 262 |
+
<td>19.40</td>
|
| 263 |
+
<td>22.20</td>
|
| 264 |
+
<td>30.60</td>
|
| 265 |
+
<td>19.40</td>
|
| 266 |
+
</tr>
|
| 267 |
+
<tr>
|
| 268 |
+
<td>SWE Bench Verified</td>
|
| 269 |
+
<td>23</td>
|
| 270 |
+
<td>16</td>
|
| 271 |
+
<td>31</td>
|
| 272 |
+
<td>29.60</td>
|
| 273 |
+
<td>34.20</td>
|
| 274 |
+
<td>61</td>
|
| 275 |
+
<td>64.2</td>
|
| 276 |
+
<td>22.60</td>
|
| 277 |
+
</tr>
|
| 278 |
+
<tr>
|
| 279 |
+
<td>Terminal Bench</td>
|
| 280 |
+
<td>14</td>
|
| 281 |
+
<td>10</td>
|
| 282 |
+
<td>22</td>
|
| 283 |
+
<td>15</td>
|
| 284 |
+
<td>13</td>
|
| 285 |
+
<td>31</td>
|
| 286 |
+
<td>33</td>
|
| 287 |
+
<td>5.67</td>
|
| 288 |
+
</tr>
|
| 289 |
+
<tr>
|
| 290 |
+
<td>Aider Polyglot</td>
|
| 291 |
+
<td>37.68</td>
|
| 292 |
+
<td>26.37</td>
|
| 293 |
+
<td>42</td>
|
| 294 |
+
<td>71.40</td>
|
| 295 |
+
<td>40</td>
|
| 296 |
+
<td>71.60</td>
|
| 297 |
+
<td>78</td>
|
| 298 |
+
<td>60.40</td>
|
| 299 |
+
</tr>
|
| 300 |
+
|
| 301 |
+
<!-- Knowledge -->
|
| 302 |
+
<tr>
|
| 303 |
+
<td class="category">Knowledge</td>
|
| 304 |
+
<td>MMLU Pro</td>
|
| 305 |
+
<td>79</td>
|
| 306 |
+
<td>77</td>
|
| 307 |
+
<td>85</td>
|
| 308 |
+
<td>85</td>
|
| 309 |
+
<td>83</td>
|
| 310 |
+
<td>84</td>
|
| 311 |
+
<td>88</td>
|
| 312 |
+
<td>80</td>
|
| 313 |
+
</tr>
|
| 314 |
+
|
| 315 |
+
<!-- Creative Writing -->
|
| 316 |
+
<tr>
|
| 317 |
+
<td class="category">Creative Writing</td>
|
| 318 |
+
<td>Creative writing v3 / EQ Bench</td>
|
| 319 |
+
<td>59.73</td>
|
| 320 |
+
<td>60.24</td>
|
| 321 |
+
<td>53.70</td>
|
| 322 |
+
<td>79.40</td>
|
| 323 |
+
<td>74.25</td>
|
| 324 |
+
<td>75.25</td>
|
| 325 |
+
<td>80.70</td>
|
| 326 |
+
<td>30.40</td>
|
| 327 |
+
</tr>
|
| 328 |
+
|
| 329 |
+
<!-- Others -->
|
| 330 |
+
<tr>
|
| 331 |
+
<td rowspan="2" class="category">Others</td>
|
| 332 |
+
<td>GPQA Diamond</td>
|
| 333 |
+
<td>73</td>
|
| 334 |
+
<td>71</td>
|
| 335 |
+
<td>78</td>
|
| 336 |
+
<td>81</td>
|
| 337 |
+
<td>79</td>
|
| 338 |
+
<td>83</td>
|
| 339 |
+
<td>83</td>
|
| 340 |
+
<td>77</td>
|
| 341 |
+
</tr>
|
| 342 |
+
<tr>
|
| 343 |
+
<td>HLE</td>
|
| 344 |
+
<td>10</td>
|
| 345 |
+
<td>12</td>
|
| 346 |
+
<td>18.5</td>
|
| 347 |
+
<td>14.9</td>
|
| 348 |
+
<td>11.1</td>
|
| 349 |
+
<td>19.7</td>
|
| 350 |
+
<td>17.3</td>
|
| 351 |
+
<td>12.3</td>
|
| 352 |
+
</tr>
|
| 353 |
+
|
| 354 |
+
<!-- Long Context -->
|
| 355 |
+
<tr>
|
| 356 |
+
<td class="category">Long Context</td>
|
| 357 |
+
<td>AA LCR</td>
|
| 358 |
+
<td>50*</td>
|
| 359 |
+
<td>20</td>
|
| 360 |
+
<td>51</td>
|
| 361 |
+
<td>55</td>
|
| 362 |
+
<td>62</td>
|
| 363 |
+
<td>68</td>
|
| 364 |
+
<td>66</td>
|
| 365 |
+
<td>-</td>
|
| 366 |
+
</tr>
|
| 367 |
+
</table>
|
| 368 |
+
|
| 369 |
+
|
| 370 |
+
|
| 371 |
+
\* AA LCR score in the table is with [DCA](https://arxiv.org/pdf/2402.17463) enabled. With default config, the model scores 36 on AA LCR.
|
| 372 |
+
|
| 373 |
+
---
|
| 374 |
+
|
| 375 |
+
- For image benchmarks, we report evaluations obtained by https://github.com/open-compass/VLMEvalKit
|
| 376 |
+
|
| 377 |
+
<table>
|
| 378 |
+
<tr>
|
| 379 |
+
<td><strong>Benchmark</strong>
|
| 380 |
+
</td>
|
| 381 |
+
<td><strong>Apriel-1.6-15B-Thinker</strong>
|
| 382 |
+
</td>
|
| 383 |
+
<td><strong>Apriel-1.5-15B-Thinker</strong>
|
| 384 |
+
</td>
|
| 385 |
+
<td><strong>GPT-5 (high)</strong>
|
| 386 |
+
</td>
|
| 387 |
+
<td><strong>GLM-4.5V (Thinking)</strong>
|
| 388 |
+
</td>
|
| 389 |
+
<td><strong>Gemini 2.5 Flash (high)</strong>
|
| 390 |
+
</td>
|
| 391 |
+
<td><strong>Claude Sonnet 3.7 (Thinking)</strong>
|
| 392 |
+
</td>
|
| 393 |
+
<td><strong>GPT-5 (Minimal)</strong>
|
| 394 |
+
</td>
|
| 395 |
+
<td><strong>Grok 4 Fast (Thinking)</strong>
|
| 396 |
+
</td>
|
| 397 |
+
</tr>
|
| 398 |
+
<tr>
|
| 399 |
+
<td> MMMU (validation)
|
| 400 |
+
</td>
|
| 401 |
+
<td> 72
|
| 402 |
+
</td>
|
| 403 |
+
<td> 70.22
|
| 404 |
+
</td>
|
| 405 |
+
<td> 81.33
|
| 406 |
+
</td>
|
| 407 |
+
<td> 74.33
|
| 408 |
+
</td>
|
| 409 |
+
<td> 70.66
|
| 410 |
+
</td>
|
| 411 |
+
<td> 73.66
|
| 412 |
+
</td>
|
| 413 |
+
<td> 66.66
|
| 414 |
+
</td>
|
| 415 |
+
<td> 70.11
|
| 416 |
+
</td>
|
| 417 |
+
</tr>
|
| 418 |
+
<tr>
|
| 419 |
+
<td>MMMU-PRO (10 choice)
|
| 420 |
+
</td>
|
| 421 |
+
<td> 60.28
|
| 422 |
+
</td>
|
| 423 |
+
<td> 55.38
|
| 424 |
+
</td>
|
| 425 |
+
<td> 74.73
|
| 426 |
+
</td>
|
| 427 |
+
<td> 64.16
|
| 428 |
+
</td>
|
| 429 |
+
<td> 67.86
|
| 430 |
+
</td>
|
| 431 |
+
<td> 64.50
|
| 432 |
+
</td>
|
| 433 |
+
<td> 66.06
|
| 434 |
+
</td>
|
| 435 |
+
<td> 61.61
|
| 436 |
+
</td>
|
| 437 |
+
</tr>
|
| 438 |
+
<tr>
|
| 439 |
+
<td>MMMU-PRO (Vision Only)
|
| 440 |
+
</td>
|
| 441 |
+
<td> 52.89
|
| 442 |
+
</td>
|
| 443 |
+
<td> 48.21
|
| 444 |
+
</td>
|
| 445 |
+
<td> 66.93
|
| 446 |
+
</td>
|
| 447 |
+
<td> 61.50
|
| 448 |
+
</td>
|
| 449 |
+
<td> 56.76
|
| 450 |
+
</td>
|
| 451 |
+
<td> 60.11
|
| 452 |
+
</td>
|
| 453 |
+
<td> 57.68
|
| 454 |
+
</td>
|
| 455 |
+
<td> 22.94
|
| 456 |
+
</td>
|
| 457 |
+
</tr>
|
| 458 |
+
<tr>
|
| 459 |
+
<td>LogicVista
|
| 460 |
+
</td>
|
| 461 |
+
<td> 58.61
|
| 462 |
+
</td>
|
| 463 |
+
<td> 58.39
|
| 464 |
+
</td>
|
| 465 |
+
<td> 69.35
|
| 466 |
+
</td>
|
| 467 |
+
<td> 63.53
|
| 468 |
+
</td>
|
| 469 |
+
<td> 63.75
|
| 470 |
+
</td>
|
| 471 |
+
<td> 69.12
|
| 472 |
+
</td>
|
| 473 |
+
<td> 44.51
|
| 474 |
+
</td>
|
| 475 |
+
<td> 47.42
|
| 476 |
+
</td>
|
| 477 |
+
</tr>
|
| 478 |
+
<tr>
|
| 479 |
+
<td>MathVision
|
| 480 |
+
</td>
|
| 481 |
+
<td> 60.85
|
| 482 |
+
</td>
|
| 483 |
+
<td> 50.99
|
| 484 |
+
</td>
|
| 485 |
+
<td> 67.10
|
| 486 |
+
</td>
|
| 487 |
+
<td> 59.53
|
| 488 |
+
</td>
|
| 489 |
+
<td> 59.21
|
| 490 |
+
</td>
|
| 491 |
+
<td> 50.32
|
| 492 |
+
</td>
|
| 493 |
+
<td> 35.52
|
| 494 |
+
</td>
|
| 495 |
+
<td> 48.35
|
| 496 |
+
</td>
|
| 497 |
+
</tr>
|
| 498 |
+
<tr>
|
| 499 |
+
<td>MathVista
|
| 500 |
+
</td>
|
| 501 |
+
<td> 79.90
|
| 502 |
+
</td>
|
| 503 |
+
<td> 75.50
|
| 504 |
+
</td>
|
| 505 |
+
<td> 83.30
|
| 506 |
+
</td>
|
| 507 |
+
<td> 83.60
|
| 508 |
+
</td>
|
| 509 |
+
<td> 78.50
|
| 510 |
+
</td>
|
| 511 |
+
<td> 74.60
|
| 512 |
+
</td>
|
| 513 |
+
<td> 61.20
|
| 514 |
+
</td>
|
| 515 |
+
<td> 68.20
|
| 516 |
+
</td>
|
| 517 |
+
</tr>
|
| 518 |
+
<tr>
|
| 519 |
+
<td>MathVerse (Vision Dominant)
|
| 520 |
+
</td>
|
| 521 |
+
<td> 66.75
|
| 522 |
+
</td>
|
| 523 |
+
<td> 58.38
|
| 524 |
+
</td>
|
| 525 |
+
<td> 79.82
|
| 526 |
+
</td>
|
| 527 |
+
<td> 68.65
|
| 528 |
+
</td>
|
| 529 |
+
<td> 70.68
|
| 530 |
+
</td>
|
| 531 |
+
<td> 56.09
|
| 532 |
+
</td>
|
| 533 |
+
<td> 39.84
|
| 534 |
+
</td>
|
| 535 |
+
<td> 54.69
|
| 536 |
+
</td>
|
| 537 |
+
</tr>
|
| 538 |
+
<tr>
|
| 539 |
+
<td>MathVerse (Text Dominant)
|
| 540 |
+
</td>
|
| 541 |
+
<td> 79.06
|
| 542 |
+
</td>
|
| 543 |
+
<td> 76.40
|
| 544 |
+
</td>
|
| 545 |
+
<td> 84.64
|
| 546 |
+
</td>
|
| 547 |
+
<td> 77.41
|
| 548 |
+
</td>
|
| 549 |
+
<td> 78.80
|
| 550 |
+
</td>
|
| 551 |
+
<td> 69.28
|
| 552 |
+
</td>
|
| 553 |
+
<td> 43.78
|
| 554 |
+
</td>
|
| 555 |
+
<td> 72.20
|
| 556 |
+
</td>
|
| 557 |
+
</tr>
|
| 558 |
+
<tr>
|
| 559 |
+
<td>MMStar
|
| 560 |
+
</td>
|
| 561 |
+
<td> 70.66
|
| 562 |
+
</td>
|
| 563 |
+
<td> 67.73
|
| 564 |
+
</td>
|
| 565 |
+
<td> 77.74
|
| 566 |
+
</td>
|
| 567 |
+
<td> 74.46
|
| 568 |
+
</td>
|
| 569 |
+
<td> 73.86
|
| 570 |
+
</td>
|
| 571 |
+
<td> 70
|
| 572 |
+
</td>
|
| 573 |
+
<td> 63.60
|
| 574 |
+
</td>
|
| 575 |
+
<td> 64.80
|
| 576 |
+
</td>
|
| 577 |
+
</tr>
|
| 578 |
+
<tr>
|
| 579 |
+
<td>CharXiv (descriptive)
|
| 580 |
+
</td>
|
| 581 |
+
<td> 89.85
|
| 582 |
+
</td>
|
| 583 |
+
<td> 88.20
|
| 584 |
+
</td>
|
| 585 |
+
<td> 91.25
|
| 586 |
+
</td>
|
| 587 |
+
<td> 90.80
|
| 588 |
+
</td>
|
| 589 |
+
<td> 83.60
|
| 590 |
+
</td>
|
| 591 |
+
<td> 93.27
|
| 592 |
+
</td>
|
| 593 |
+
<td> 82.45
|
| 594 |
+
</td>
|
| 595 |
+
<td> 68.15
|
| 596 |
+
</td>
|
| 597 |
+
</tr>
|
| 598 |
+
<tr>
|
| 599 |
+
<td>CharXiv (reasoning)
|
| 600 |
+
</td>
|
| 601 |
+
<td> 56.00
|
| 602 |
+
</td>
|
| 603 |
+
<td> 50.10
|
| 604 |
+
</td>
|
| 605 |
+
<td> 71.50
|
| 606 |
+
</td>
|
| 607 |
+
<td> 63.00
|
| 608 |
+
</td>
|
| 609 |
+
<td> 56.50
|
| 610 |
+
</td>
|
| 611 |
+
<td> 70.90
|
| 612 |
+
</td>
|
| 613 |
+
<td> 52.80
|
| 614 |
+
</td>
|
| 615 |
+
<td> 33.50
|
| 616 |
+
</td>
|
| 617 |
+
</tr>
|
| 618 |
+
<tr>
|
| 619 |
+
<td>AI2D Test
|
| 620 |
+
</td>
|
| 621 |
+
<td> 86.04
|
| 622 |
+
</td>
|
| 623 |
+
<td> 82.87
|
| 624 |
+
</td>
|
| 625 |
+
<td> 90.05
|
| 626 |
+
</td>
|
| 627 |
+
<td> 87.75
|
| 628 |
+
</td>
|
| 629 |
+
<td> 82.09
|
| 630 |
+
</td>
|
| 631 |
+
<td> 84.19
|
| 632 |
+
</td>
|
| 633 |
+
<td> 85.16
|
| 634 |
+
</td>
|
| 635 |
+
<td> 81.86
|
| 636 |
+
</td>
|
| 637 |
+
</tr>
|
| 638 |
+
<tr>
|
| 639 |
+
<td>BLINK
|
| 640 |
+
</td>
|
| 641 |
+
<td> 63.96
|
| 642 |
+
</td>
|
| 643 |
+
<td> 58.71
|
| 644 |
+
</td>
|
| 645 |
+
<td> 70.22
|
| 646 |
+
</td>
|
| 647 |
+
<td> 66.59
|
| 648 |
+
</td>
|
| 649 |
+
<td> 65.64
|
| 650 |
+
</td>
|
| 651 |
+
<td> 64.49
|
| 652 |
+
</td>
|
| 653 |
+
<td> 64.59
|
| 654 |
+
</td>
|
| 655 |
+
<td> 54.39
|
| 656 |
+
</td>
|
| 657 |
+
</tr>
|
| 658 |
+
</table>
|
| 659 |
+
|
| 660 |
+
---
|
| 661 |
+
|
| 662 |
+
# Intended Use
|
| 663 |
+
|
| 664 |
+
The Apriel family of models are designed for a variety of general-purpose instruction tasks, including:
|
| 665 |
+
|
| 666 |
+
- Code assistance and generation
|
| 667 |
+
- Logical reasoning and multi-step tasks
|
| 668 |
+
- Question answering and information retrieval
|
| 669 |
+
- Function calling, complex instruction following and agent use cases
|
| 670 |
+
|
| 671 |
+
They are **not intended** for use in safety-critical applications without human oversight or in scenarios requiring guaranteed factual accuracy.
|
| 672 |
+
|
| 673 |
+
---
|
| 674 |
+
# How to Use
|
| 675 |
+
|
| 676 |
+
```bash
|
| 677 |
+
pip install transformers
|
| 678 |
+
```
|
| 679 |
+
|
| 680 |
+
## Running the Reasoning model
|
| 681 |
+
|
| 682 |
+
|
| 683 |
+
Here is a code snippet demonstrating the model's usage with the transformers library's generate function:
|
| 684 |
+
|
| 685 |
+
```python
|
| 686 |
+
# Tested with transformers==4.48
|
| 687 |
+
|
| 688 |
+
import re
|
| 689 |
+
import requests
|
| 690 |
+
import torch
|
| 691 |
+
from PIL import Image
|
| 692 |
+
from transformers import AutoProcessor, AutoModelForImageTextToText
|
| 693 |
+
|
| 694 |
+
# Load model
|
| 695 |
+
model_id = "ServiceNow-AI/Apriel-1.6-15b-Thinker"
|
| 696 |
+
model = AutoModelForImageTextToText.from_pretrained(
|
| 697 |
+
model_id,
|
| 698 |
+
torch_dtype=torch.bfloat16,
|
| 699 |
+
device_map="auto"
|
| 700 |
+
)
|
| 701 |
+
processor = AutoProcessor.from_pretrained(model_id)
|
| 702 |
+
|
| 703 |
+
# Example 1: Text-only prompt
|
| 704 |
+
chat = [
|
| 705 |
+
{
|
| 706 |
+
"role": "user",
|
| 707 |
+
"content": [
|
| 708 |
+
{"type": "text", "text": "What is the capital for France?"},
|
| 709 |
+
],
|
| 710 |
+
}
|
| 711 |
+
]
|
| 712 |
+
|
| 713 |
+
inputs = processor.apply_chat_template(chat, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt")
|
| 714 |
+
inputs = {k: v.to(model.device) if isinstance(v, torch.Tensor) else v for k, v in inputs.items()}
|
| 715 |
+
inputs.pop("token_type_ids", None)
|
| 716 |
+
|
| 717 |
+
with torch.no_grad():
|
| 718 |
+
output_ids = model.generate(**inputs, max_new_tokens=1024, do_sample=True, temperature=0.6)
|
| 719 |
+
|
| 720 |
+
generated_ids = output_ids[:, inputs['input_ids'].shape[1]:]
|
| 721 |
+
output = processor.decode(generated_ids[0], skip_special_tokens=True)
|
| 722 |
+
response = re.findall(r"\[BEGIN FINAL RESPONSE\](.*?)(?:<\|end\|>)", output, re.DOTALL)[0].strip()
|
| 723 |
+
|
| 724 |
+
print("Text-only Response:", response)
|
| 725 |
+
|
| 726 |
+
# Example 2: Image understanding
|
| 727 |
+
url = "https://picsum.photos/id/237/200/300"
|
| 728 |
+
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")
|
| 729 |
+
|
| 730 |
+
chat = [
|
| 731 |
+
{
|
| 732 |
+
"role": "user",
|
| 733 |
+
"content": [
|
| 734 |
+
{"type": "text", "text": "Which animal is this?"},
|
| 735 |
+
{"type": "image"},
|
| 736 |
+
],
|
| 737 |
+
}
|
| 738 |
+
]
|
| 739 |
+
|
| 740 |
+
prompt = processor.apply_chat_template(chat, add_generation_prompt=True, tokenize=False)
|
| 741 |
+
inputs = processor(text=prompt, images=[image], return_tensors="pt").to(model.device)
|
| 742 |
+
|
| 743 |
+
with torch.no_grad():
|
| 744 |
+
output_ids = model.generate(**inputs, max_new_tokens=1024, do_sample=True, temperature=0.6)
|
| 745 |
+
|
| 746 |
+
generated_ids = output_ids[:, inputs['input_ids'].shape[1]:]
|
| 747 |
+
output = processor.decode(generated_ids[0], skip_special_tokens=True)
|
| 748 |
+
response = re.findall(r"\[BEGIN FINAL RESPONSE\](.*?)(?:<\|end\|>)", output, re.DOTALL)[0].strip()
|
| 749 |
+
|
| 750 |
+
print("Image Response:", response)
|
| 751 |
+
|
| 752 |
+
```
|
| 753 |
+
|
| 754 |
+
## Usage Guidelines
|
| 755 |
+
1. Use the model’s default chat template, which already includes a system prompt.
|
| 756 |
+
2. We recommend setting temperature to `0.6`.
|
| 757 |
+
3. We ensure the model starts with `Here are my reasoning steps:\n` during all our evaluations. This is implemented in the default chat template.
|
| 758 |
+
4. For multi-turn conversations, intermediate turns (historical model outputs) are expected to contain only the final response, without reasoning steps.
|
| 759 |
+
|
| 760 |
+
---
|
| 761 |
+
|
| 762 |
+
## Chat Template
|
| 763 |
+
|
| 764 |
+
|
| 765 |
+
```
|
| 766 |
+
<|begin_system|>
|
| 767 |
+
You are a thoughtful, systematic AI assistant from ServiceNow Language Models (SLAM) lab. Analyze each question carefully, present your reasoning step-by-step, then provide the final response after the marker [BEGIN FINAL RESPONSE].
|
| 768 |
+
<|begin_user|>
|
| 769 |
+
# user message here
|
| 770 |
+
<|begin_assistant|>
|
| 771 |
+
Here are my reasoning steps:
|
| 772 |
+
# thoughts here
|
| 773 |
+
[BEGIN FINAL RESPONSE]
|
| 774 |
+
# assistant response here
|
| 775 |
+
<|end|>
|
| 776 |
+
```
|
| 777 |
+
The model will first generate its thinking process and then generate its final response, starting with `[BEGIN FINAL RESPONSE]`. Here is a code snippet demonstrating the application of the chat template:
|
| 778 |
+
|
| 779 |
+
|
| 780 |
+
|
| 781 |
+
```python
|
| 782 |
+
from transformers import AutoTokenizer
|
| 783 |
+
model_name = "ServiceNow-AI/Apriel-1.6-15b-Thinker"
|
| 784 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 785 |
+
|
| 786 |
+
# prepare the model input
|
| 787 |
+
custom_system_prompt = "Answer like a pirate."
|
| 788 |
+
prompt = "You are an expert assistant in the implementation of customer experience management aspect of retail applications \n \nYou will be using Python as the programming language. \n \nYou will utilize a factory design pattern for the implementation and following the dependency inversion principle \n \nYou will modify the implementation based on user requirements. \n \nUpon user request, you will add, update, and remove the features & enhancements in the implementation provided by you. \n \nYou will ask whether the user wants to refactor the provided code or needs a sample implementation for reference. Upon user confirmation, I will proceed accordingly. \n \n**Guidelines:** \n 1. **User Requirements:** \n - You have to ask users about their requirements, clarify the user expectations, and suggest the best possible solution by providing examples of Python code snippets. \n - Ask users about which type of reports they need to assess the AI model's performance, accuracy, and reliability. \n - After providing the solution, you have to ask the user about the trial of the solution and modify the solution based on the user feedback. \n \n 2. **Libraries/Frameworks:** \n - You will be utilizing Python as a programming language. \n - You will be using Flask framework for REST APIS implementation \n \n 3. **Communication Gesture:** \n - Your conversation with the user should be interactive, supportive, courageous, and professional. \n - You have to break down the complex concepts into sub-concepts and try to explain them to the user. \n - You have to ask the user for the required parameters. If the user refuses to provide in 2 attempts, politely exit the conversation. \n - You have to provide your supported parameters to the user, if the user refuses to accept them then you have to put an apology note and exit the conversation. \n - You have to track the conversation about unasked questions by the user. If some/one of the questions remain then you have to remind the user about these questions and proceed to answer them based on the user's confirmation \n \n 4. **Implementation:** \n - Your code/implementations should be reliable, scaleable, modular, and reusable. \n - You will be providing unit tests for the implementation upon user request. \n - You will be following MVC architecture for the applications \n - Your implementations must be well-commented and readable \n \n \n- Today's date is 23rd August 2024. \n- The default sender email is sender-assistant@email.com.\nHi, I am conducting research on retail customer feedback systems and I need assistance with designing and implementing them. Could you kindly provide me with a list of general customer feedback system modules?"
|
| 789 |
+
messages = [
|
| 790 |
+
{"role": "user", "content": custom_system_prompt + "\n\n" + prompt}
|
| 791 |
+
]
|
| 792 |
+
# example tools
|
| 793 |
+
tools = [{"type": "function", "function": {"name": "getRetailFeedbackModules", "description": "Returns the list of modules usually present in the retail industry", "parameters": {"type": "object", "properties": {"page": {"type": "integer", "description": "The current page number.", "default": 1}, "page_size": {"type": "integer", "description": "The number of items per page.", "default": 3}}}}}, {"type": "function", "function": {"name": "verifyImplementation", "description": "Returns the list of modules usually present in the retail industry", "parameters": {"type": "object", "properties": {"coding_language": {"type": "string", "description": "The supported languages for verification of implementation.", "default": "python", "enum": ["python", "java", "php"]}, "code": {"type": "string", "description": "The code which needs verification"}, "design_pattern": {"type": "string", "description": "The design pattern to verify in the implementation", "enum": ["factory", "strategy", "singleton"]}, "verify_best_practices": {"type": "boolean", "description": "The verification of the coding style based on the language selected", "default": true}}}}}]
|
| 794 |
+
text = tokenizer.apply_chat_template(
|
| 795 |
+
messages,
|
| 796 |
+
tokenize=False,
|
| 797 |
+
add_generation_prompt=True,
|
| 798 |
+
tools=tools
|
| 799 |
+
)
|
| 800 |
+
model_inputs = tokenizer([text], return_tensors="pt")
|
| 801 |
+
```
|
| 802 |
+
|
| 803 |
+
---
|
| 804 |
+
|
| 805 |
+
## Running with vLLM
|
| 806 |
+
|
| 807 |
+
As the upstream PR is not yet merged, you can use this custom image as an alternate way to run the model with tool and reasoning parsers enabled.
|
| 808 |
+
|
| 809 |
+
### Docker Image
|
| 810 |
+
|
| 811 |
+
```
|
| 812 |
+
docker.io/amant555/vllm_apriel:latest
|
| 813 |
+
```
|
| 814 |
+
|
| 815 |
+
### Start Command
|
| 816 |
+
|
| 817 |
+
```bash
|
| 818 |
+
python3 -m vllm.entrypoints.openai.api_server \
|
| 819 |
+
--model ServiceNow-AI/Apriel-1.6-15b-Thinker \
|
| 820 |
+
--served-model-name Apriel-1p6-15B-Thinker \
|
| 821 |
+
--trust_remote_code \
|
| 822 |
+
--max-model-len 131072 \
|
| 823 |
+
--enable-auto-tool-choice \
|
| 824 |
+
--tool-call-parser apriel \
|
| 825 |
+
--reasoning-parser apriel
|
| 826 |
+
```
|
| 827 |
+
|
| 828 |
+
---
|
| 829 |
+
|
| 830 |
+
|
| 831 |
+
# Training Details
|
| 832 |
+
|
| 833 |
+
**Training stack:** [Fast-LLM](https://github.com/ServiceNow/Fast-LLM), [VERL](https://github.com/volcengine/verl)
|
| 834 |
+
|
| 835 |
+
**Continual Pre-training:** Billions of tokens covering math, code, science, logical reasoning, and multimodal image-text data
|
| 836 |
+
|
| 837 |
+
**SFT:** 2.4M samples spanning math, code, instruction-following, function calling, and conversation, followed by an incremental lightweight multimodal SFT.
|
| 838 |
+
|
| 839 |
+
**RL:** Multi-stage RL with verifiable rewards and [GSPO](https://arxiv.org/abs/2507.18071) on text and vision tasks. Our RL stage optimizes reasoning efficiency: using fewer tokens by discouraging unnecessary intermediate steps, stopping earlier when confident, and giving direct answers on simple queries.
|
| 840 |
+
|
| 841 |
+
For more details on our training methodology, see our [blog post](https://huggingface.co/blog/ServiceNow-AI/apriel-1p6-15b-thinker).
|
| 842 |
+
|
| 843 |
+
---
|
| 844 |
+
|
| 845 |
+
# Limitations
|
| 846 |
+
|
| 847 |
+
- **Factual accuracy:** May produce incorrect, misleading, or outdated content. Outputs should be verified before use in critical contexts.
|
| 848 |
+
- **Bias:** May reflect societal, cultural, or systemic biases present in training data.
|
| 849 |
+
- **Ethics:** Do not use the model to produce harmful, unlawful, or unethical content.
|
| 850 |
+
- **Language:** Strongest performance is in English. Output quality may degrade in underrepresented languages.
|
| 851 |
+
- **Critical use:** Not suitable for medical, legal, financial, or other high-risk applications without safeguards.
|
| 852 |
+
|
| 853 |
+
---
|
| 854 |
+
|
| 855 |
+
# Security and Responsible Use
|
| 856 |
+
|
| 857 |
+
**Security Responsibilities:**
|
| 858 |
+
Deployers and users are strongly encouraged to align their security practices with established frameworks and regulatory guidelines such as the EU AI Act and the NIST AI Risk Management Framework (RMF).
|
| 859 |
+
|
| 860 |
+
<details>
|
| 861 |
+
<summary>Guidelines for Deployers</summary>
|
| 862 |
+
|
| 863 |
+
- Regularly conduct robustness assessments to identify and mitigate adversarial inputs.
|
| 864 |
+
- Implement validation and filtering processes to prevent harmful or biased outputs.
|
| 865 |
+
- Continuously perform data privacy checks to guard against unintended data leaks.
|
| 866 |
+
- Document and communicate the model's limitations, intended usage, and known security risks to all end-users.
|
| 867 |
+
- Schedule periodic security reviews and updates to address emerging threats and vulnerabilities.
|
| 868 |
+
|
| 869 |
+
</details>
|
| 870 |
+
|
| 871 |
+
<details>
|
| 872 |
+
<summary>Guidelines for Users</summary>
|
| 873 |
+
|
| 874 |
+
- Follow established security policies and usage guidelines provided by deployers.
|
| 875 |
+
- Protect and manage sensitive information when interacting with the model.
|
| 876 |
+
- Report anomalies, suspicious behavior, or unsafe outputs to deployers or developers.
|
| 877 |
+
- Maintain human oversight and apply judgment to mitigate potential security or ethical risks during interactions.
|
| 878 |
+
|
| 879 |
+
</details>
|
| 880 |
+
|
| 881 |
+
**Disclaimer:**
|
| 882 |
+
Users accept responsibility for securely deploying, managing, and using this open-source LLM. The model is provided "as-is," without explicit or implied warranty regarding security or fitness for any specific application or environment.
|
| 883 |
+
|
| 884 |
+
---
|
| 885 |
+
|
| 886 |
+
# License
|
| 887 |
+
|
| 888 |
+
MIT
|
| 889 |
+
|
| 890 |
+
---
|
| 891 |
+
|
| 892 |
+
# Citation
|
| 893 |
+
|
| 894 |
+
```bibtex
|
| 895 |
+
@misc{radhakrishna2025apriel1515bthinker,
|
| 896 |
+
title={Apriel-1.5-15b-Thinker},
|
| 897 |
+
author={Shruthan Radhakrishna and Aman Tiwari and Aanjaneya Shukla and Masoud Hashemi and Rishabh Maheshwary and Shiva Krishna Reddy Malay and Jash Mehta and Pulkit Pattnaik and Saloni Mittal and Khalil Slimi and Kelechi Ogueji and Akintunde Oladipo and Soham Parikh and Oluwanifemi Bamgbose and Toby Liang and Ahmed Masry and Khyati Mahajan and Sai Rajeswar Mudumba and Vikas Yadav and Sathwik Tejaswi Madhusudhan and Torsten Scholak and Sagar Davasam and Srinivas Sunkara and Nicholas Chapados},
|
| 898 |
+
year={2025},
|
| 899 |
+
eprint={2510.01141},
|
| 900 |
+
archivePrefix={arXiv},
|
| 901 |
+
primaryClass={cs.AI},
|
| 902 |
+
url={https://arxiv.org/abs/2510.01141},
|
| 903 |
+
}
|
| 904 |
+
```
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{# ---------------------------------------------------------------------- #}
|
| 2 |
+
{# ƛƬ Default setup and flags #}
|
| 3 |
+
{# ---------------------------------------------------------------------- #}
|
| 4 |
+
{%- set messages = messages or [] -%}
|
| 5 |
+
{%- set tools = tools or [] -%}
|
| 6 |
+
{%- set add_generation_prompt = add_generation_prompt or false -%}
|
| 7 |
+
{%- set available_tool_string, add_tool_id = '', true -%}
|
| 8 |
+
{%- set add_thoughts = false -%} {# whether to include <thinking> reasoning blocks #}
|
| 9 |
+
{%- set add_generation_prompt = true -%} {# whether to emit reasoning starter before assistant response #}
|
| 10 |
+
{# Optional token placeholders (safe defaults) #}
|
| 11 |
+
{%- set bos_token = bos_token if (bos_token is defined) else '' -%}
|
| 12 |
+
{%- set eos_token = eos_token if (eos_token is defined) else '' -%}
|
| 13 |
+
{# ---------------------------------------------------------------------- #}
|
| 14 |
+
{# Core reasoning prompt and assistant reasoning prefix #}
|
| 15 |
+
{# ---------------------------------------------------------------------- #}
|
| 16 |
+
{%- set reasoning_prompt =
|
| 17 |
+
'You are a thoughtful, systematic AI assistant from ServiceNow Language Models (SLAM) lab. '
|
| 18 |
+
'Analyze each question carefully, present your reasoning step-by-step, then provide the final '
|
| 19 |
+
'response after the marker [BEGIN FINAL RESPONSE].'
|
| 20 |
+
-%}
|
| 21 |
+
{%- set reasoning_asst_turn_start = 'Here are my reasoning steps:\n' -%}
|
| 22 |
+
{# ---------------------------------------------------------------------- #}
|
| 23 |
+
{# Tool list and tool call output format #}
|
| 24 |
+
{# ---------------------------------------------------------------------- #}
|
| 25 |
+
{%- if tools is not none and tools|length > 0 -%}
|
| 26 |
+
{%- set available_tool_string -%}
|
| 27 |
+
You are provided with function signatures within <available_tools></available_tools> XML tags.
|
| 28 |
+
You may call one or more functions to assist with the user query.
|
| 29 |
+
Don't make assumptions about the arguments. You should infer the argument values from previous
|
| 30 |
+
user responses and the system message.
|
| 31 |
+
Here are the available tools:
|
| 32 |
+
<available_tools>
|
| 33 |
+
{% for tool in tools %}{{ tool|string }}{% endfor %}
|
| 34 |
+
|
| 35 |
+
</available_tools>.
|
| 36 |
+
|
| 37 |
+
Return all function calls as a list of JSON objects within <tool_calls></tool_calls> XML tags.
|
| 38 |
+
Each JSON object should contain a function name and arguments as follows:
|
| 39 |
+
<tool_calls>[
|
| 40 |
+
{"name": <function-name-1>, "arguments": <args-dict-1>},
|
| 41 |
+
{"name": <function-name-2>, "arguments": <args-dict-2>},
|
| 42 |
+
...
|
| 43 |
+
]</tool_calls>
|
| 44 |
+
{%- endset -%}
|
| 45 |
+
{%- endif -%}
|
| 46 |
+
{# ---------------------------------------------------------------------- #}
|
| 47 |
+
{# Start system block if first message is not system #}
|
| 48 |
+
{# ---------------------------------------------------------------------- #}
|
| 49 |
+
{%- if messages|length > 0 and messages[0]['role'] != 'system' -%}
|
| 50 |
+
{%- if tools is not none and tools|length > 0 -%}
|
| 51 |
+
{{ bos_token + '<|begin_system|>\n' + reasoning_prompt + '\n' + available_tool_string + '\n' }}
|
| 52 |
+
{%- else -%}
|
| 53 |
+
{{ bos_token + '<|begin_system|>\n' + reasoning_prompt + '\n' }}
|
| 54 |
+
{%- endif -%}
|
| 55 |
+
{%- endif -%}
|
| 56 |
+
{# ---------------------------------------------------------------------- #}
|
| 57 |
+
{# Iterate through messages #}
|
| 58 |
+
{# ---------------------------------------------------------------------- #}
|
| 59 |
+
{%- for message in messages -%}
|
| 60 |
+
|
| 61 |
+
{# ---------------- USER MESSAGE ---------------- #}
|
| 62 |
+
{%- if message['role'] == 'user' -%}
|
| 63 |
+
{{ '<|begin_user|>\n' }}
|
| 64 |
+
{%- if message['content'] is not string -%}
|
| 65 |
+
{%- for chunk in message['content'] -%}
|
| 66 |
+
{%- if chunk['type'] == 'text' -%}
|
| 67 |
+
{{ chunk['text'] }}
|
| 68 |
+
{%- elif chunk['type'] in ['image', 'image_url'] -%}
|
| 69 |
+
{{ '[IMG]' }}
|
| 70 |
+
{%- else -%}
|
| 71 |
+
{{ raise_exception('Unrecognized content type!') }}
|
| 72 |
+
{%- endif -%}
|
| 73 |
+
{%- endfor -%}
|
| 74 |
+
{%- else -%}
|
| 75 |
+
{{ message['content'] }}
|
| 76 |
+
{%- endif -%}
|
| 77 |
+
|
| 78 |
+
{# ---------------- SYSTEM MESSAGE ---------------- #}
|
| 79 |
+
{%- elif message['role'] == 'system' -%}
|
| 80 |
+
{%- if message['content'] is not none and message['content']|length > 0 -%}
|
| 81 |
+
{%- if message['content'] is string -%}
|
| 82 |
+
{%- set system_message = message['content'] -%}
|
| 83 |
+
{%- else -%}
|
| 84 |
+
{%- set system_message = message['content'][0]['text'] -%}
|
| 85 |
+
{%- endif -%}
|
| 86 |
+
{%- else -%}
|
| 87 |
+
{%- set system_message = '' -%}
|
| 88 |
+
{%- endif -%}
|
| 89 |
+
|
| 90 |
+
{%- if tools is not none and tools|length > 0 -%}
|
| 91 |
+
{{ bos_token + '<|begin_system|>\n' + reasoning_prompt + '\n' + system_message + '\n' + available_tool_string + '\n' }}
|
| 92 |
+
{%- else -%}
|
| 93 |
+
{{ bos_token + '<|begin_system|>\n' + reasoning_prompt + '\n' + system_message + '\n' }}
|
| 94 |
+
{%- endif -%}
|
| 95 |
+
|
| 96 |
+
{# ---------------- ASSISTANT MESSAGE ---------------- #}
|
| 97 |
+
{%- elif message['role'] == 'assistant' -%}
|
| 98 |
+
{%- if loop.last -%}
|
| 99 |
+
{%- set add_tool_id = false -%}
|
| 100 |
+
{%- endif -%}
|
| 101 |
+
|
| 102 |
+
{{ '\n<|begin_assistant|>\n' }}
|
| 103 |
+
|
| 104 |
+
{%- if add_thoughts and 'thought' in message and message['thought'] is not none -%}
|
| 105 |
+
<thinking>{{ message['thought'] }}</thinking>
|
| 106 |
+
{%- endif -%}
|
| 107 |
+
|
| 108 |
+
{%- if message['content'] is not none and message['content']|length > 0 -%}
|
| 109 |
+
{%- if message['content'] is not string -%}
|
| 110 |
+
{{ message['content'][0]['text'] }}
|
| 111 |
+
{%- else -%}
|
| 112 |
+
{{ message['content'] }}
|
| 113 |
+
{%- endif -%}
|
| 114 |
+
{%- elif message['chosen'] is not none and message['chosen']|length > 0 -%}
|
| 115 |
+
{{ message['chosen'][0] }}
|
| 116 |
+
{%- endif -%}
|
| 117 |
+
|
| 118 |
+
{# Tool call output #}
|
| 119 |
+
{%- if message['tool_calls'] is not none and message['tool_calls']|length > 0 -%}
|
| 120 |
+
{{ '\n<tool_calls>[' }}
|
| 121 |
+
{%- for tool_call in message['tool_calls'] -%}
|
| 122 |
+
{{ '{"name": "' + tool_call['function']['name'] + '", "arguments": ' + tool_call['function']['arguments']|string }}
|
| 123 |
+
{%- if add_tool_id == true and 'id' in tool_call -%}
|
| 124 |
+
{{ ', "id": "' + tool_call['id'] + '"' }}
|
| 125 |
+
{%- endif -%}
|
| 126 |
+
{{ '}' }}
|
| 127 |
+
{%- if not loop.last -%}{{ ', ' }}{%- endif -%}
|
| 128 |
+
{%- endfor -%}
|
| 129 |
+
{{ ']</tool_calls>' }}
|
| 130 |
+
{%- endif -%}
|
| 131 |
+
|
| 132 |
+
{%- if not loop.last or training_prompt -%}
|
| 133 |
+
{{ '\n<|end|>\n' }}
|
| 134 |
+
{%- endif -%}
|
| 135 |
+
|
| 136 |
+
{# ---------------- TOOL RESULT MESSAGE ---------------- #}
|
| 137 |
+
{%- elif message['role'] == 'tool' -%}
|
| 138 |
+
{%- if message['content'] is string -%}
|
| 139 |
+
{%- set tool_message = message['content'] -%}
|
| 140 |
+
{%- else -%}
|
| 141 |
+
{%- set tool_message = message['content'][0]['text'] -%}
|
| 142 |
+
{%- endif -%}
|
| 143 |
+
{{ '<|begin_tool_result|>\n' + tool_message|string + '\n' }}
|
| 144 |
+
|
| 145 |
+
{# ---------------- CONTENT MESSAGE ---------------- #}
|
| 146 |
+
{%- elif message['role'] == 'content' -%}
|
| 147 |
+
{%- if message['content'] is not string -%}
|
| 148 |
+
{{ '<|begin_content|>\n' + message['content'][0]['text'] + '\n' }}
|
| 149 |
+
{%- else -%}
|
| 150 |
+
{{ '<|begin_content|>\n' + message['content'] + '\n' }}
|
| 151 |
+
{%- endif -%}
|
| 152 |
+
{%- endif -%}
|
| 153 |
+
|
| 154 |
+
{# ---------------- REASONING PROMPT BEFORE NEXT ASSISTANT ---------------- #}
|
| 155 |
+
{%- if loop.last and add_generation_prompt and message['role'] != 'assistant' -%}
|
| 156 |
+
{{ '\n<|begin_assistant|>\n' + reasoning_asst_turn_start }}
|
| 157 |
+
{%- endif -%}
|
| 158 |
+
|
| 159 |
+
{%- endfor -%}
|
config.json
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlavaForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"ignore_index": -100,
|
| 6 |
+
"image_seq_length": 1,
|
| 7 |
+
"image_token_index": 10,
|
| 8 |
+
"model_type": "llava",
|
| 9 |
+
"multimodal_projector_bias": true,
|
| 10 |
+
"projector_hidden_act": "gelu",
|
| 11 |
+
"text_config": {
|
| 12 |
+
"_attn_implementation_autoset": false,
|
| 13 |
+
"_name_or_path": "",
|
| 14 |
+
"add_cross_attention": false,
|
| 15 |
+
"architectures": null,
|
| 16 |
+
"attention_dropout": 0.0,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"begin_suppress_tokens": null,
|
| 19 |
+
"bos_token_id": 1,
|
| 20 |
+
"chunk_size_feed_forward": 0,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"head_dim": 128,
|
| 33 |
+
"hidden_act": "silu",
|
| 34 |
+
"hidden_size": 5120,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 14336,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"length_penalty": 1.0,
|
| 48 |
+
"max_length": 20,
|
| 49 |
+
"max_position_embeddings": 262400,
|
| 50 |
+
"min_length": 0,
|
| 51 |
+
"model_type": "mistral",
|
| 52 |
+
"no_repeat_ngram_size": 0,
|
| 53 |
+
"num_attention_heads": 32,
|
| 54 |
+
"num_beam_groups": 1,
|
| 55 |
+
"num_beams": 1,
|
| 56 |
+
"num_hidden_layers": 48,
|
| 57 |
+
"num_key_value_heads": 8,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": null,
|
| 63 |
+
"prefix": null,
|
| 64 |
+
"problem_type": null,
|
| 65 |
+
"pruned_heads": {},
|
| 66 |
+
"remove_invalid_values": false,
|
| 67 |
+
"repetition_penalty": 1.0,
|
| 68 |
+
"return_dict": true,
|
| 69 |
+
"return_dict_in_generate": false,
|
| 70 |
+
"rms_norm_eps": 1e-05,
|
| 71 |
+
"rope_theta": 1000000000.0,
|
| 72 |
+
"sep_token_id": null,
|
| 73 |
+
"sliding_window": null,
|
| 74 |
+
"suppress_tokens": null,
|
| 75 |
+
"task_specific_params": null,
|
| 76 |
+
"temperature": 1.0,
|
| 77 |
+
"tf_legacy_loss": false,
|
| 78 |
+
"tie_encoder_decoder": false,
|
| 79 |
+
"tie_word_embeddings": false,
|
| 80 |
+
"tokenizer_class": null,
|
| 81 |
+
"top_k": 50,
|
| 82 |
+
"top_p": 1.0,
|
| 83 |
+
"torch_dtype": "bfloat16",
|
| 84 |
+
"torchscript": false,
|
| 85 |
+
"typical_p": 1.0,
|
| 86 |
+
"use_bfloat16": false,
|
| 87 |
+
"use_cache": true,
|
| 88 |
+
"vocab_size": 131072
|
| 89 |
+
},
|
| 90 |
+
"torch_dtype": "bfloat16",
|
| 91 |
+
"transformers_version": "4.49.0",
|
| 92 |
+
"vision_config": {
|
| 93 |
+
"_attn_implementation_autoset": false,
|
| 94 |
+
"_name_or_path": "",
|
| 95 |
+
"add_cross_attention": false,
|
| 96 |
+
"architectures": null,
|
| 97 |
+
"attention_dropout": 0.0,
|
| 98 |
+
"bad_words_ids": null,
|
| 99 |
+
"begin_suppress_tokens": null,
|
| 100 |
+
"bos_token_id": null,
|
| 101 |
+
"chunk_size_feed_forward": 0,
|
| 102 |
+
"cross_attention_hidden_size": null,
|
| 103 |
+
"decoder_start_token_id": null,
|
| 104 |
+
"diversity_penalty": 0.0,
|
| 105 |
+
"do_sample": false,
|
| 106 |
+
"early_stopping": false,
|
| 107 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 108 |
+
"eos_token_id": null,
|
| 109 |
+
"exponential_decay_length_penalty": null,
|
| 110 |
+
"finetuning_task": null,
|
| 111 |
+
"forced_bos_token_id": null,
|
| 112 |
+
"forced_eos_token_id": null,
|
| 113 |
+
"head_dim": 64,
|
| 114 |
+
"hidden_act": "silu",
|
| 115 |
+
"hidden_size": 1024,
|
| 116 |
+
"id2label": {
|
| 117 |
+
"0": "LABEL_0",
|
| 118 |
+
"1": "LABEL_1"
|
| 119 |
+
},
|
| 120 |
+
"image_size": 1024,
|
| 121 |
+
"initializer_range": 0.02,
|
| 122 |
+
"intermediate_size": 4096,
|
| 123 |
+
"is_decoder": false,
|
| 124 |
+
"is_encoder_decoder": false,
|
| 125 |
+
"label2id": {
|
| 126 |
+
"LABEL_0": 0,
|
| 127 |
+
"LABEL_1": 1
|
| 128 |
+
},
|
| 129 |
+
"length_penalty": 1.0,
|
| 130 |
+
"max_length": 20,
|
| 131 |
+
"min_length": 0,
|
| 132 |
+
"model_type": "pixtral",
|
| 133 |
+
"no_repeat_ngram_size": 0,
|
| 134 |
+
"num_attention_heads": 16,
|
| 135 |
+
"num_beam_groups": 1,
|
| 136 |
+
"num_beams": 1,
|
| 137 |
+
"num_channels": 3,
|
| 138 |
+
"num_hidden_layers": 24,
|
| 139 |
+
"num_return_sequences": 1,
|
| 140 |
+
"output_attentions": false,
|
| 141 |
+
"output_hidden_states": false,
|
| 142 |
+
"output_scores": false,
|
| 143 |
+
"pad_token_id": null,
|
| 144 |
+
"patch_size": 16,
|
| 145 |
+
"prefix": null,
|
| 146 |
+
"problem_type": null,
|
| 147 |
+
"pruned_heads": {},
|
| 148 |
+
"remove_invalid_values": false,
|
| 149 |
+
"repetition_penalty": 1.0,
|
| 150 |
+
"return_dict": true,
|
| 151 |
+
"return_dict_in_generate": false,
|
| 152 |
+
"rope_theta": 10000.0,
|
| 153 |
+
"sep_token_id": null,
|
| 154 |
+
"suppress_tokens": null,
|
| 155 |
+
"task_specific_params": null,
|
| 156 |
+
"temperature": 1.0,
|
| 157 |
+
"tf_legacy_loss": false,
|
| 158 |
+
"tie_encoder_decoder": false,
|
| 159 |
+
"tie_word_embeddings": true,
|
| 160 |
+
"tokenizer_class": null,
|
| 161 |
+
"top_k": 50,
|
| 162 |
+
"top_p": 1.0,
|
| 163 |
+
"torch_dtype": "bfloat16",
|
| 164 |
+
"torchscript": false,
|
| 165 |
+
"typical_p": 1.0,
|
| 166 |
+
"use_bfloat16": false
|
| 167 |
+
},
|
| 168 |
+
"vision_feature_layer": -1,
|
| 169 |
+
"vision_feature_select_strategy": "full"
|
| 170 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.49.0"
|
| 6 |
+
}
|
model-00001-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9149ddf3576f6158dc820e02d845fa5cd62799daf1cff11bb222f1c52f43885
|
| 3 |
+
size 4990957080
|
model-00002-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2ff720f335f220ede02d90b2dc26dacd6da47cead08211eb9273addea13c7e6
|
| 3 |
+
size 4959959696
|
model-00003-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5ff378334665cd4d603972dce1fc1859f3c92b2e30aa266f42bc5032b3e168b
|
| 3 |
+
size 4907530672
|
model-00004-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11edd8e8be8c42bb0ff2f0ee40f418b172f3d15e3f451a7e586a6d0afe7aedcb
|
| 3 |
+
size 4907530672
|
model-00005-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93bd3526a124d28a027d89ac344750d77e199a7f1a5ace95a26fff78fa25725a
|
| 3 |
+
size 4907530672
|
model-00006-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68c219bb05eaf34145f53f3dd173f9981afab86f14c46c8e028f23f7f7d8e1aa
|
| 3 |
+
size 3712120512
|
model-00007-of-00007.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c324e3a00f0ad9864e42dd972ac746e86654275aa71ad57164ce42bbd1d24e07
|
| 3 |
+
size 1342177424
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,664 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 29727719424
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"language_model.lm_head.weight": "model-00007-of-00007.safetensors",
|
| 7 |
+
"language_model.model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
| 8 |
+
"language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 9 |
+
"language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 10 |
+
"language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 11 |
+
"language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 12 |
+
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 13 |
+
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 14 |
+
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 15 |
+
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 16 |
+
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 17 |
+
"language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 18 |
+
"language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 19 |
+
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 20 |
+
"language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 21 |
+
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 22 |
+
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 23 |
+
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 24 |
+
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 25 |
+
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 26 |
+
"language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 27 |
+
"language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 28 |
+
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 29 |
+
"language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 30 |
+
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 31 |
+
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 32 |
+
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 33 |
+
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 34 |
+
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 35 |
+
"language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 36 |
+
"language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 37 |
+
"language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 38 |
+
"language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 39 |
+
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 40 |
+
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 41 |
+
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 42 |
+
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 43 |
+
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 44 |
+
"language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 45 |
+
"language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 46 |
+
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 47 |
+
"language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 48 |
+
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 49 |
+
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 50 |
+
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 51 |
+
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 52 |
+
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 53 |
+
"language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 54 |
+
"language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 55 |
+
"language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 56 |
+
"language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 57 |
+
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 58 |
+
"language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 59 |
+
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 60 |
+
"language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 61 |
+
"language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 62 |
+
"language_model.model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 63 |
+
"language_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 64 |
+
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 65 |
+
"language_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 66 |
+
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 67 |
+
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 68 |
+
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 69 |
+
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 70 |
+
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 71 |
+
"language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 72 |
+
"language_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 73 |
+
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 74 |
+
"language_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 75 |
+
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 76 |
+
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 77 |
+
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 78 |
+
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 79 |
+
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 80 |
+
"language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 81 |
+
"language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 82 |
+
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 83 |
+
"language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 84 |
+
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 85 |
+
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 86 |
+
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 87 |
+
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 88 |
+
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 89 |
+
"language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 90 |
+
"language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 91 |
+
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 92 |
+
"language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 93 |
+
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 94 |
+
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 95 |
+
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 96 |
+
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 97 |
+
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 98 |
+
"language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 99 |
+
"language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 100 |
+
"language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 101 |
+
"language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 102 |
+
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 103 |
+
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 104 |
+
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 105 |
+
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 106 |
+
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 107 |
+
"language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 108 |
+
"language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 109 |
+
"language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 110 |
+
"language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 111 |
+
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 112 |
+
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 113 |
+
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 114 |
+
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 115 |
+
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 116 |
+
"language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 117 |
+
"language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 118 |
+
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 119 |
+
"language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 120 |
+
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 121 |
+
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 122 |
+
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 123 |
+
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 124 |
+
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 125 |
+
"language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 126 |
+
"language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 127 |
+
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 128 |
+
"language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 129 |
+
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 130 |
+
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 131 |
+
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 132 |
+
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 133 |
+
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 134 |
+
"language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 135 |
+
"language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 136 |
+
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 137 |
+
"language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 138 |
+
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 139 |
+
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 140 |
+
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 141 |
+
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 142 |
+
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 143 |
+
"language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 144 |
+
"language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
| 145 |
+
"language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
| 146 |
+
"language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
| 147 |
+
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
| 148 |
+
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 149 |
+
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 150 |
+
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 151 |
+
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 152 |
+
"language_model.model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 153 |
+
"language_model.model.layers.23.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 154 |
+
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 155 |
+
"language_model.model.layers.23.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 156 |
+
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 157 |
+
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
| 158 |
+
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
| 159 |
+
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
| 160 |
+
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
| 161 |
+
"language_model.model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 162 |
+
"language_model.model.layers.24.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 163 |
+
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 164 |
+
"language_model.model.layers.24.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 165 |
+
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 166 |
+
"language_model.model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 167 |
+
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 168 |
+
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 169 |
+
"language_model.model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 170 |
+
"language_model.model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 171 |
+
"language_model.model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 172 |
+
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 173 |
+
"language_model.model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 174 |
+
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 175 |
+
"language_model.model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 176 |
+
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 177 |
+
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 178 |
+
"language_model.model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 179 |
+
"language_model.model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 180 |
+
"language_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 181 |
+
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 182 |
+
"language_model.model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 183 |
+
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 184 |
+
"language_model.model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 185 |
+
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 186 |
+
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 187 |
+
"language_model.model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 188 |
+
"language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 189 |
+
"language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 190 |
+
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 191 |
+
"language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 192 |
+
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 193 |
+
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 194 |
+
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 195 |
+
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 196 |
+
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 197 |
+
"language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 198 |
+
"language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 199 |
+
"language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 200 |
+
"language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 201 |
+
"language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 202 |
+
"language_model.model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 203 |
+
"language_model.model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 204 |
+
"language_model.model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 205 |
+
"language_model.model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 206 |
+
"language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 207 |
+
"language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 208 |
+
"language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 209 |
+
"language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 210 |
+
"language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 211 |
+
"language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 212 |
+
"language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 213 |
+
"language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 214 |
+
"language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 215 |
+
"language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 216 |
+
"language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 217 |
+
"language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 218 |
+
"language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 219 |
+
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 220 |
+
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 221 |
+
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 222 |
+
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 223 |
+
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 224 |
+
"language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 225 |
+
"language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 226 |
+
"language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 227 |
+
"language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 228 |
+
"language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 229 |
+
"language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 230 |
+
"language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 231 |
+
"language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 232 |
+
"language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 233 |
+
"language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 234 |
+
"language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
| 235 |
+
"language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
| 236 |
+
"language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
| 237 |
+
"language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
| 238 |
+
"language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 239 |
+
"language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 240 |
+
"language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 241 |
+
"language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 242 |
+
"language_model.model.layers.32.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 243 |
+
"language_model.model.layers.32.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 244 |
+
"language_model.model.layers.32.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 245 |
+
"language_model.model.layers.32.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 246 |
+
"language_model.model.layers.32.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 247 |
+
"language_model.model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
| 248 |
+
"language_model.model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
| 249 |
+
"language_model.model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
| 250 |
+
"language_model.model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
| 251 |
+
"language_model.model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 252 |
+
"language_model.model.layers.33.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 253 |
+
"language_model.model.layers.33.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 254 |
+
"language_model.model.layers.33.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 255 |
+
"language_model.model.layers.33.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 256 |
+
"language_model.model.layers.33.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 257 |
+
"language_model.model.layers.33.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 258 |
+
"language_model.model.layers.33.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 259 |
+
"language_model.model.layers.33.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 260 |
+
"language_model.model.layers.34.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 261 |
+
"language_model.model.layers.34.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 262 |
+
"language_model.model.layers.34.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 263 |
+
"language_model.model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 264 |
+
"language_model.model.layers.34.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 265 |
+
"language_model.model.layers.34.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 266 |
+
"language_model.model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 267 |
+
"language_model.model.layers.34.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 268 |
+
"language_model.model.layers.34.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 269 |
+
"language_model.model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 270 |
+
"language_model.model.layers.35.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 271 |
+
"language_model.model.layers.35.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 272 |
+
"language_model.model.layers.35.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 273 |
+
"language_model.model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 274 |
+
"language_model.model.layers.35.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 275 |
+
"language_model.model.layers.35.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 276 |
+
"language_model.model.layers.35.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 277 |
+
"language_model.model.layers.35.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 278 |
+
"language_model.model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 279 |
+
"language_model.model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 280 |
+
"language_model.model.layers.36.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 281 |
+
"language_model.model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 282 |
+
"language_model.model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 283 |
+
"language_model.model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 284 |
+
"language_model.model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 285 |
+
"language_model.model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 286 |
+
"language_model.model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 287 |
+
"language_model.model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 288 |
+
"language_model.model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 289 |
+
"language_model.model.layers.37.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 290 |
+
"language_model.model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 291 |
+
"language_model.model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 292 |
+
"language_model.model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 293 |
+
"language_model.model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 294 |
+
"language_model.model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 295 |
+
"language_model.model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 296 |
+
"language_model.model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 297 |
+
"language_model.model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 298 |
+
"language_model.model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 299 |
+
"language_model.model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 300 |
+
"language_model.model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 301 |
+
"language_model.model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 302 |
+
"language_model.model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 303 |
+
"language_model.model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 304 |
+
"language_model.model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 305 |
+
"language_model.model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 306 |
+
"language_model.model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 307 |
+
"language_model.model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 308 |
+
"language_model.model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 309 |
+
"language_model.model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 310 |
+
"language_model.model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 311 |
+
"language_model.model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 312 |
+
"language_model.model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 313 |
+
"language_model.model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 314 |
+
"language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 315 |
+
"language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 316 |
+
"language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 317 |
+
"language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 318 |
+
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
| 319 |
+
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 320 |
+
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 321 |
+
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 322 |
+
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 323 |
+
"language_model.model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 324 |
+
"language_model.model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
| 325 |
+
"language_model.model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
| 326 |
+
"language_model.model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
| 327 |
+
"language_model.model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
| 328 |
+
"language_model.model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 329 |
+
"language_model.model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 330 |
+
"language_model.model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 331 |
+
"language_model.model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 332 |
+
"language_model.model.layers.41.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 333 |
+
"language_model.model.layers.41.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 334 |
+
"language_model.model.layers.41.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 335 |
+
"language_model.model.layers.41.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 336 |
+
"language_model.model.layers.41.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 337 |
+
"language_model.model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
| 338 |
+
"language_model.model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
| 339 |
+
"language_model.model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
| 340 |
+
"language_model.model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
| 341 |
+
"language_model.model.layers.42.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 342 |
+
"language_model.model.layers.42.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 343 |
+
"language_model.model.layers.42.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 344 |
+
"language_model.model.layers.42.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 345 |
+
"language_model.model.layers.42.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 346 |
+
"language_model.model.layers.42.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 347 |
+
"language_model.model.layers.42.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 348 |
+
"language_model.model.layers.42.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 349 |
+
"language_model.model.layers.42.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 350 |
+
"language_model.model.layers.43.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 351 |
+
"language_model.model.layers.43.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 352 |
+
"language_model.model.layers.43.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 353 |
+
"language_model.model.layers.43.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 354 |
+
"language_model.model.layers.43.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 355 |
+
"language_model.model.layers.43.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 356 |
+
"language_model.model.layers.43.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 357 |
+
"language_model.model.layers.43.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 358 |
+
"language_model.model.layers.43.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 359 |
+
"language_model.model.layers.44.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 360 |
+
"language_model.model.layers.44.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 361 |
+
"language_model.model.layers.44.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 362 |
+
"language_model.model.layers.44.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 363 |
+
"language_model.model.layers.44.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 364 |
+
"language_model.model.layers.44.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 365 |
+
"language_model.model.layers.44.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 366 |
+
"language_model.model.layers.44.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 367 |
+
"language_model.model.layers.44.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 368 |
+
"language_model.model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 369 |
+
"language_model.model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 370 |
+
"language_model.model.layers.45.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 371 |
+
"language_model.model.layers.45.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 372 |
+
"language_model.model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 373 |
+
"language_model.model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 374 |
+
"language_model.model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 375 |
+
"language_model.model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 376 |
+
"language_model.model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 377 |
+
"language_model.model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 378 |
+
"language_model.model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 379 |
+
"language_model.model.layers.46.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 380 |
+
"language_model.model.layers.46.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 381 |
+
"language_model.model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 382 |
+
"language_model.model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 383 |
+
"language_model.model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 384 |
+
"language_model.model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 385 |
+
"language_model.model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 386 |
+
"language_model.model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 387 |
+
"language_model.model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
| 388 |
+
"language_model.model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
| 389 |
+
"language_model.model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
| 390 |
+
"language_model.model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
| 391 |
+
"language_model.model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
| 392 |
+
"language_model.model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
| 393 |
+
"language_model.model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
| 394 |
+
"language_model.model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
| 395 |
+
"language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 396 |
+
"language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 397 |
+
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 398 |
+
"language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 399 |
+
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 400 |
+
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 401 |
+
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 402 |
+
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 403 |
+
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 404 |
+
"language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 405 |
+
"language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 406 |
+
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 407 |
+
"language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 408 |
+
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 409 |
+
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 410 |
+
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 411 |
+
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 412 |
+
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 413 |
+
"language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 414 |
+
"language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 415 |
+
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 416 |
+
"language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 417 |
+
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 418 |
+
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 419 |
+
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 420 |
+
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 421 |
+
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 422 |
+
"language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 423 |
+
"language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 424 |
+
"language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 425 |
+
"language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 426 |
+
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 427 |
+
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 428 |
+
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 429 |
+
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 430 |
+
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 431 |
+
"language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 432 |
+
"language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
| 433 |
+
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
| 434 |
+
"language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
| 435 |
+
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
| 436 |
+
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
| 437 |
+
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
| 438 |
+
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
| 439 |
+
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
| 440 |
+
"language_model.model.norm.weight": "model-00006-of-00007.safetensors",
|
| 441 |
+
"multi_modal_projector.linear_1.bias": "model-00001-of-00007.safetensors",
|
| 442 |
+
"multi_modal_projector.linear_1.weight": "model-00001-of-00007.safetensors",
|
| 443 |
+
"multi_modal_projector.linear_2.bias": "model-00001-of-00007.safetensors",
|
| 444 |
+
"multi_modal_projector.linear_2.weight": "model-00001-of-00007.safetensors",
|
| 445 |
+
"vision_tower.ln_pre.weight": "model-00001-of-00007.safetensors",
|
| 446 |
+
"vision_tower.patch_conv.weight": "model-00001-of-00007.safetensors",
|
| 447 |
+
"vision_tower.transformer.layers.0.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 448 |
+
"vision_tower.transformer.layers.0.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 449 |
+
"vision_tower.transformer.layers.0.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 450 |
+
"vision_tower.transformer.layers.0.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 451 |
+
"vision_tower.transformer.layers.0.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 452 |
+
"vision_tower.transformer.layers.0.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 453 |
+
"vision_tower.transformer.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 454 |
+
"vision_tower.transformer.layers.0.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 455 |
+
"vision_tower.transformer.layers.0.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 456 |
+
"vision_tower.transformer.layers.1.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 457 |
+
"vision_tower.transformer.layers.1.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 458 |
+
"vision_tower.transformer.layers.1.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 459 |
+
"vision_tower.transformer.layers.1.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 460 |
+
"vision_tower.transformer.layers.1.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 461 |
+
"vision_tower.transformer.layers.1.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 462 |
+
"vision_tower.transformer.layers.1.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 463 |
+
"vision_tower.transformer.layers.1.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 464 |
+
"vision_tower.transformer.layers.1.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 465 |
+
"vision_tower.transformer.layers.10.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 466 |
+
"vision_tower.transformer.layers.10.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 467 |
+
"vision_tower.transformer.layers.10.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 468 |
+
"vision_tower.transformer.layers.10.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 469 |
+
"vision_tower.transformer.layers.10.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 470 |
+
"vision_tower.transformer.layers.10.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 471 |
+
"vision_tower.transformer.layers.10.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 472 |
+
"vision_tower.transformer.layers.10.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 473 |
+
"vision_tower.transformer.layers.10.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 474 |
+
"vision_tower.transformer.layers.11.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 475 |
+
"vision_tower.transformer.layers.11.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 476 |
+
"vision_tower.transformer.layers.11.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 477 |
+
"vision_tower.transformer.layers.11.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 478 |
+
"vision_tower.transformer.layers.11.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 479 |
+
"vision_tower.transformer.layers.11.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 480 |
+
"vision_tower.transformer.layers.11.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 481 |
+
"vision_tower.transformer.layers.11.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 482 |
+
"vision_tower.transformer.layers.11.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 483 |
+
"vision_tower.transformer.layers.12.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 484 |
+
"vision_tower.transformer.layers.12.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 485 |
+
"vision_tower.transformer.layers.12.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 486 |
+
"vision_tower.transformer.layers.12.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 487 |
+
"vision_tower.transformer.layers.12.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 488 |
+
"vision_tower.transformer.layers.12.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 489 |
+
"vision_tower.transformer.layers.12.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 490 |
+
"vision_tower.transformer.layers.12.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 491 |
+
"vision_tower.transformer.layers.12.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 492 |
+
"vision_tower.transformer.layers.13.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 493 |
+
"vision_tower.transformer.layers.13.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 494 |
+
"vision_tower.transformer.layers.13.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 495 |
+
"vision_tower.transformer.layers.13.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 496 |
+
"vision_tower.transformer.layers.13.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 497 |
+
"vision_tower.transformer.layers.13.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 498 |
+
"vision_tower.transformer.layers.13.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 499 |
+
"vision_tower.transformer.layers.13.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 500 |
+
"vision_tower.transformer.layers.13.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 501 |
+
"vision_tower.transformer.layers.14.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 502 |
+
"vision_tower.transformer.layers.14.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 503 |
+
"vision_tower.transformer.layers.14.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 504 |
+
"vision_tower.transformer.layers.14.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 505 |
+
"vision_tower.transformer.layers.14.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 506 |
+
"vision_tower.transformer.layers.14.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 507 |
+
"vision_tower.transformer.layers.14.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 508 |
+
"vision_tower.transformer.layers.14.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 509 |
+
"vision_tower.transformer.layers.14.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 510 |
+
"vision_tower.transformer.layers.15.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 511 |
+
"vision_tower.transformer.layers.15.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 512 |
+
"vision_tower.transformer.layers.15.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 513 |
+
"vision_tower.transformer.layers.15.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 514 |
+
"vision_tower.transformer.layers.15.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 515 |
+
"vision_tower.transformer.layers.15.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 516 |
+
"vision_tower.transformer.layers.15.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 517 |
+
"vision_tower.transformer.layers.15.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 518 |
+
"vision_tower.transformer.layers.15.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 519 |
+
"vision_tower.transformer.layers.16.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 520 |
+
"vision_tower.transformer.layers.16.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 521 |
+
"vision_tower.transformer.layers.16.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 522 |
+
"vision_tower.transformer.layers.16.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 523 |
+
"vision_tower.transformer.layers.16.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 524 |
+
"vision_tower.transformer.layers.16.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 525 |
+
"vision_tower.transformer.layers.16.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 526 |
+
"vision_tower.transformer.layers.16.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 527 |
+
"vision_tower.transformer.layers.16.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 528 |
+
"vision_tower.transformer.layers.17.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 529 |
+
"vision_tower.transformer.layers.17.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 530 |
+
"vision_tower.transformer.layers.17.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 531 |
+
"vision_tower.transformer.layers.17.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 532 |
+
"vision_tower.transformer.layers.17.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 533 |
+
"vision_tower.transformer.layers.17.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 534 |
+
"vision_tower.transformer.layers.17.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 535 |
+
"vision_tower.transformer.layers.17.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 536 |
+
"vision_tower.transformer.layers.17.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 537 |
+
"vision_tower.transformer.layers.18.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 538 |
+
"vision_tower.transformer.layers.18.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 539 |
+
"vision_tower.transformer.layers.18.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 540 |
+
"vision_tower.transformer.layers.18.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 541 |
+
"vision_tower.transformer.layers.18.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 542 |
+
"vision_tower.transformer.layers.18.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 543 |
+
"vision_tower.transformer.layers.18.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 544 |
+
"vision_tower.transformer.layers.18.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 545 |
+
"vision_tower.transformer.layers.18.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 546 |
+
"vision_tower.transformer.layers.19.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 547 |
+
"vision_tower.transformer.layers.19.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 548 |
+
"vision_tower.transformer.layers.19.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 549 |
+
"vision_tower.transformer.layers.19.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 550 |
+
"vision_tower.transformer.layers.19.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 551 |
+
"vision_tower.transformer.layers.19.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 552 |
+
"vision_tower.transformer.layers.19.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 553 |
+
"vision_tower.transformer.layers.19.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 554 |
+
"vision_tower.transformer.layers.19.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 555 |
+
"vision_tower.transformer.layers.2.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 556 |
+
"vision_tower.transformer.layers.2.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 557 |
+
"vision_tower.transformer.layers.2.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 558 |
+
"vision_tower.transformer.layers.2.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 559 |
+
"vision_tower.transformer.layers.2.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 560 |
+
"vision_tower.transformer.layers.2.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 561 |
+
"vision_tower.transformer.layers.2.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 562 |
+
"vision_tower.transformer.layers.2.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 563 |
+
"vision_tower.transformer.layers.2.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 564 |
+
"vision_tower.transformer.layers.20.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 565 |
+
"vision_tower.transformer.layers.20.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 566 |
+
"vision_tower.transformer.layers.20.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 567 |
+
"vision_tower.transformer.layers.20.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 568 |
+
"vision_tower.transformer.layers.20.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 569 |
+
"vision_tower.transformer.layers.20.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 570 |
+
"vision_tower.transformer.layers.20.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 571 |
+
"vision_tower.transformer.layers.20.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 572 |
+
"vision_tower.transformer.layers.20.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 573 |
+
"vision_tower.transformer.layers.21.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 574 |
+
"vision_tower.transformer.layers.21.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 575 |
+
"vision_tower.transformer.layers.21.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 576 |
+
"vision_tower.transformer.layers.21.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 577 |
+
"vision_tower.transformer.layers.21.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 578 |
+
"vision_tower.transformer.layers.21.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 579 |
+
"vision_tower.transformer.layers.21.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 580 |
+
"vision_tower.transformer.layers.21.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 581 |
+
"vision_tower.transformer.layers.21.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 582 |
+
"vision_tower.transformer.layers.22.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 583 |
+
"vision_tower.transformer.layers.22.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 584 |
+
"vision_tower.transformer.layers.22.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 585 |
+
"vision_tower.transformer.layers.22.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 586 |
+
"vision_tower.transformer.layers.22.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 587 |
+
"vision_tower.transformer.layers.22.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 588 |
+
"vision_tower.transformer.layers.22.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 589 |
+
"vision_tower.transformer.layers.22.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 590 |
+
"vision_tower.transformer.layers.22.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 591 |
+
"vision_tower.transformer.layers.23.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 592 |
+
"vision_tower.transformer.layers.23.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 593 |
+
"vision_tower.transformer.layers.23.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 594 |
+
"vision_tower.transformer.layers.23.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 595 |
+
"vision_tower.transformer.layers.23.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 596 |
+
"vision_tower.transformer.layers.23.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 597 |
+
"vision_tower.transformer.layers.23.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 598 |
+
"vision_tower.transformer.layers.23.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 599 |
+
"vision_tower.transformer.layers.23.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 600 |
+
"vision_tower.transformer.layers.3.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 601 |
+
"vision_tower.transformer.layers.3.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 602 |
+
"vision_tower.transformer.layers.3.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 603 |
+
"vision_tower.transformer.layers.3.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 604 |
+
"vision_tower.transformer.layers.3.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 605 |
+
"vision_tower.transformer.layers.3.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 606 |
+
"vision_tower.transformer.layers.3.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 607 |
+
"vision_tower.transformer.layers.3.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 608 |
+
"vision_tower.transformer.layers.3.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 609 |
+
"vision_tower.transformer.layers.4.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 610 |
+
"vision_tower.transformer.layers.4.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 611 |
+
"vision_tower.transformer.layers.4.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 612 |
+
"vision_tower.transformer.layers.4.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 613 |
+
"vision_tower.transformer.layers.4.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 614 |
+
"vision_tower.transformer.layers.4.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 615 |
+
"vision_tower.transformer.layers.4.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 616 |
+
"vision_tower.transformer.layers.4.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 617 |
+
"vision_tower.transformer.layers.4.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 618 |
+
"vision_tower.transformer.layers.5.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 619 |
+
"vision_tower.transformer.layers.5.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 620 |
+
"vision_tower.transformer.layers.5.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 621 |
+
"vision_tower.transformer.layers.5.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 622 |
+
"vision_tower.transformer.layers.5.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 623 |
+
"vision_tower.transformer.layers.5.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 624 |
+
"vision_tower.transformer.layers.5.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 625 |
+
"vision_tower.transformer.layers.5.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 626 |
+
"vision_tower.transformer.layers.5.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 627 |
+
"vision_tower.transformer.layers.6.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 628 |
+
"vision_tower.transformer.layers.6.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 629 |
+
"vision_tower.transformer.layers.6.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 630 |
+
"vision_tower.transformer.layers.6.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 631 |
+
"vision_tower.transformer.layers.6.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 632 |
+
"vision_tower.transformer.layers.6.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 633 |
+
"vision_tower.transformer.layers.6.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 634 |
+
"vision_tower.transformer.layers.6.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 635 |
+
"vision_tower.transformer.layers.6.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 636 |
+
"vision_tower.transformer.layers.7.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 637 |
+
"vision_tower.transformer.layers.7.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 638 |
+
"vision_tower.transformer.layers.7.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 639 |
+
"vision_tower.transformer.layers.7.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 640 |
+
"vision_tower.transformer.layers.7.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 641 |
+
"vision_tower.transformer.layers.7.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 642 |
+
"vision_tower.transformer.layers.7.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 643 |
+
"vision_tower.transformer.layers.7.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 644 |
+
"vision_tower.transformer.layers.7.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 645 |
+
"vision_tower.transformer.layers.8.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 646 |
+
"vision_tower.transformer.layers.8.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 647 |
+
"vision_tower.transformer.layers.8.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 648 |
+
"vision_tower.transformer.layers.8.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 649 |
+
"vision_tower.transformer.layers.8.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 650 |
+
"vision_tower.transformer.layers.8.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 651 |
+
"vision_tower.transformer.layers.8.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 652 |
+
"vision_tower.transformer.layers.8.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 653 |
+
"vision_tower.transformer.layers.8.ffn_norm.weight": "model-00001-of-00007.safetensors",
|
| 654 |
+
"vision_tower.transformer.layers.9.attention.k_proj.weight": "model-00001-of-00007.safetensors",
|
| 655 |
+
"vision_tower.transformer.layers.9.attention.o_proj.weight": "model-00001-of-00007.safetensors",
|
| 656 |
+
"vision_tower.transformer.layers.9.attention.q_proj.weight": "model-00001-of-00007.safetensors",
|
| 657 |
+
"vision_tower.transformer.layers.9.attention.v_proj.weight": "model-00001-of-00007.safetensors",
|
| 658 |
+
"vision_tower.transformer.layers.9.attention_norm.weight": "model-00001-of-00007.safetensors",
|
| 659 |
+
"vision_tower.transformer.layers.9.feed_forward.down_proj.weight": "model-00001-of-00007.safetensors",
|
| 660 |
+
"vision_tower.transformer.layers.9.feed_forward.gate_proj.weight": "model-00001-of-00007.safetensors",
|
| 661 |
+
"vision_tower.transformer.layers.9.feed_forward.up_proj.weight": "model-00001-of-00007.safetensors",
|
| 662 |
+
"vision_tower.transformer.layers.9.ffn_norm.weight": "model-00001-of-00007.safetensors"
|
| 663 |
+
}
|
| 664 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "PixtralImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"patch_size": {
|
| 18 |
+
"height": 16,
|
| 19 |
+
"width": 16
|
| 20 |
+
},
|
| 21 |
+
"processor_class": "PixtralProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 1024
|
| 26 |
+
}
|
| 27 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_break_token": "[IMG_BREAK]",
|
| 3 |
+
"image_end_token": "[IMG_END]",
|
| 4 |
+
"image_token": "[IMG]",
|
| 5 |
+
"patch_size": 16,
|
| 6 |
+
"processor_class": "PixtralProcessor"
|
| 7 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<pad>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50c4196bd3d61abf4a6f9d116435140b8ac0606e15eb4d02e235f9036257dc3e
|
| 3 |
+
size 17077327
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|