初始化项目，由ModelHub XC社区提供模型
Model: Dingdust/VibeThinker-3B-heretic Source: Original Platform
This commit is contained in:
ModelHub XC
43
.gitattributes
vendored
Normal file
43
.gitattributes
vendored
Normal file
@@ -0,0 +1,43 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
animation-VibeThinker-3B.gif filter=lfs diff=lfs merge=lfs -text
|
||||
pictures/Abstrct.png filter=lfs diff=lfs merge=lfs -text
|
||||
pictures/Acc_and_Scale.png filter=lfs diff=lfs merge=lfs -text
|
||||
pictures/Architecture.png filter=lfs diff=lfs merge=lfs -text
|
||||
pictures/LeetCode.png filter=lfs diff=lfs merge=lfs -text
|
||||
pictures/VibeThiinker-3B.png filter=lfs diff=lfs merge=lfs -text
|
||||
pictures/VibeThinker-3B+CLR.png filter=lfs diff=lfs merge=lfs -text
|
||||
257
README.md
Normal file
257
README.md
Normal file
@@ -0,0 +1,257 @@
|
||||
---
|
||||
license: mit
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- Qwen/Qwen2.5-Coder-3B
|
||||
tags:
|
||||
- math
|
||||
- code
|
||||
- reasoning
|
||||
- gpqa
|
||||
- instruction-following
|
||||
- heretic
|
||||
- uncensored
|
||||
- decensored
|
||||
- abliterated
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
---
|
||||
# This is a decensored version of a model, made using [Heretic](https://heretic-project.org) v1.4.0
|
||||
|
||||
## Abliteration parameters
|
||||
|
||||
| Parameter | Value |
|
||||
| :-------- | :---: |
|
||||
| **direction_index** | 23.30 |
|
||||
| **attn.o_proj.max_weight** | 1.26 |
|
||||
| **attn.o_proj.max_weight_position** | 21.83 |
|
||||
| **attn.o_proj.min_weight** | 1.20 |
|
||||
| **attn.o_proj.min_weight_distance** | 13.99 |
|
||||
| **mlp.down_proj.max_weight** | 1.49 |
|
||||
| **mlp.down_proj.max_weight_position** | 21.32 |
|
||||
| **mlp.down_proj.min_weight** | 0.86 |
|
||||
| **mlp.down_proj.min_weight_distance** | 13.56 |
|
||||
|
||||
## Performance
|
||||
|
||||
| Metric | This model | Original model (a model) |
|
||||
| :----- | :--------: | :---------------------------: |
|
||||
| **KL divergence** | 0.0255 | 0 *(by definition)* |
|
||||
| **Refusals** | 9/100 | 64/100 |
|
||||
|
||||
## Residual Geometry
|
||||
|
||||
| Layer | S(g,b) | S(g*,b*) | S(g,r) | S(g*,r*) | S(b,r) | S(b*,r*) | \|g\| | \|g*\| | \|b\| | \|b*\| | \|r\| | \|r*\| | Silh |
|
||||
| ----- | ------ | -------- | ------- | -------- | ------ | -------- | ------ | ------ | ------ | ------ | ----- | ------ | ------ |
|
||||
| 1 | 0.9994 | 0.9994 | 0.1419 | 0.1613 | 0.1773 | 0.1966 | 12.07 | 12.06 | 12.14 | 12.14 | 0.44 | 0.44 | 0.0582 |
|
||||
| 2 | 0.9994 | 0.9994 | 0.1141 | 0.1236 | 0.1484 | 0.1577 | 15.81 | 15.80 | 15.88 | 15.88 | 0.55 | 0.55 | 0.0670 |
|
||||
| 3 | 0.9987 | 0.9987 | 0.0273 | 0.0306 | 0.0785 | 0.0816 | 16.28 | 16.28 | 16.33 | 16.33 | 0.84 | 0.83 | 0.0788 |
|
||||
| 4 | 0.9979 | 0.9979 | 0.0460 | 0.0506 | 0.1110 | 0.1152 | 16.28 | 16.28 | 16.36 | 16.36 | 1.07 | 1.06 | 0.0868 |
|
||||
| 5 | 0.9973 | 0.9974 | 0.1027 | 0.1029 | 0.1750 | 0.1743 | 16.83 | 16.83 | 17.00 | 17.01 | 1.25 | 1.23 | 0.0941 |
|
||||
| 6 | 0.9975 | 0.9976 | 0.0628 | 0.0623 | 0.1332 | 0.1319 | 17.63 | 17.63 | 17.75 | 17.76 | 1.26 | 1.24 | 0.0956 |
|
||||
| 7 | 0.9964 | 0.9964 | -0.0058 | -0.0099 | 0.0794 | 0.0748 | 18.16 | 18.18 | 18.22 | 18.23 | 1.55 | 1.54 | 0.0870 |
|
||||
| 8 | 0.9941 | 0.9941 | 0.0083 | 0.0045 | 0.1172 | 0.1131 | 18.91 | 18.93 | 19.04 | 19.06 | 2.07 | 2.07 | 0.0952 |
|
||||
| 9 | 0.9849 | 0.9852 | -0.0096 | -0.0132 | 0.1636 | 0.1582 | 19.40 | 19.44 | 19.66 | 19.68 | 3.40 | 3.37 | 0.1217 |
|
||||
| 10 | 0.9854 | 0.9857 | -0.0042 | -0.0089 | 0.1660 | 0.1596 | 20.51 | 20.56 | 20.80 | 20.83 | 3.54 | 3.51 | 0.1232 |
|
||||
| 11 | 0.9869 | 0.9871 | 0.0023 | -0.0012 | 0.1637 | 0.1587 | 20.92 | 20.97 | 21.20 | 21.23 | 3.42 | 3.39 | 0.1262 |
|
||||
| 12 | 0.9860 | 0.9862 | -0.0215 | -0.0283 | 0.1455 | 0.1377 | 25.71 | 25.78 | 25.98 | 26.02 | 4.33 | 4.31 | 0.1191 |
|
||||
| 13 | 0.9838 | 0.9839 | -0.1014 | -0.1188 | 0.0786 | 0.0605 | 25.86 | 25.96 | 25.80 | 25.82 | 4.65 | 4.65 | 0.1191 |
|
||||
| 14 | 0.9837 | 0.9839 | -0.0898 | -0.1108 | 0.0906 | 0.0685 | 26.00 | 26.12 | 26.00 | 26.02 | 4.69 | 4.68 | 0.1131 |
|
||||
| 15 | 0.9830 | 0.9833 | -0.0709 | -0.0856 | 0.1133 | 0.0971 | 26.07 | 26.18 | 26.17 | 26.21 | 4.81 | 4.79 | 0.1106 |
|
||||
| 16 | 0.9808 | 0.9813 | 0.0049 | -0.0102 | 0.1995 | 0.1825 | 26.02 | 26.17 | 26.56 | 26.61 | 5.17 | 5.13 | 0.1142 |
|
||||
| 17 | 0.9858 | 0.9862 | 0.0985 | 0.0796 | 0.2640 | 0.2438 | 29.96 | 30.13 | 30.91 | 30.97 | 5.21 | 5.15 | 0.1160 |
|
||||
| 18 | 0.9857 | 0.9861 | 0.0173 | 0.0000 | 0.1854 | 0.1664 | 29.06 | 29.21 | 29.57 | 29.63 | 4.98 | 4.93 | 0.1078 |
|
||||
| 19 | 0.9863 | 0.9867 | 0.0289 | 0.0055 | 0.1935 | 0.1679 | 31.16 | 31.35 | 31.75 | 31.80 | 5.24 | 5.17 | 0.1101 |
|
||||
| 20 | 0.9856 | 0.9860 | 0.0036 | -0.0164 | 0.1727 | 0.1508 | 30.69 | 30.85 | 31.16 | 31.20 | 5.27 | 5.21 | 0.1071 |
|
||||
| 21 | 0.9810 | 0.9813 | 0.1356 | 0.1211 | 0.3253 | 0.3100 | 36.41 | 36.57 | 38.15 | 38.19 | 7.47 | 7.41 | 0.1585 |
|
||||
| 22 | 0.9789 | 0.9792 | 0.1084 | 0.0922 | 0.3092 | 0.2923 | 38.37 | 38.60 | 40.11 | 40.19 | 8.24 | 8.19 | 0.1662 |
|
||||
| 23 | 0.9724 | 0.9727 | 0.0068 | -0.0035 | 0.2401 | 0.2288 | 37.52 | 37.71 | 38.65 | 38.74 | 9.02 | 8.99 | 0.1715 |
|
||||
| 24 | 0.9685 | 0.9685 | -0.0140 | -0.0286 | 0.2355 | 0.2212 | 40.01 | 40.24 | 41.17 | 41.24 | 10.25 | 10.27 | 0.1857 |
|
||||
| 25 | 0.9549 | 0.9544 | -0.1280 | -0.1385 | 0.1722 | 0.1636 | 42.07 | 42.28 | 42.35 | 42.44 | 12.68 | 12.80 | 0.2114 |
|
||||
| 26 | 0.9512 | 0.9504 | -0.1326 | -0.1426 | 0.1798 | 0.1723 | 44.42 | 44.64 | 44.76 | 44.85 | 13.94 | 14.09 | 0.2190 |
|
||||
| 27 | 0.9524 | 0.9513 | -0.1822 | -0.1915 | 0.1263 | 0.1202 | 51.97 | 52.19 | 51.51 | 51.60 | 15.97 | 16.20 | 0.2333 |
|
||||
| 28 | 0.9331 | 0.9309 | -0.1472 | -0.1589 | 0.2182 | 0.2126 | 53.06 | 53.29 | 53.77 | 53.85 | 19.55 | 19.92 | 0.2326 |
|
||||
| 29 | 0.9280 | 0.9251 | -0.1168 | -0.1313 | 0.2617 | 0.2551 | 61.41 | 61.77 | 63.19 | 63.33 | 23.71 | 24.26 | 0.2238 |
|
||||
| 30 | 0.9122 | 0.9090 | -0.1673 | -0.1811 | 0.2514 | 0.2452 | 66.16 | 66.62 | 67.40 | 67.58 | 28.01 | 28.64 | 0.2210 |
|
||||
| 31 | 0.9066 | 0.9034 | -0.1648 | -0.1825 | 0.2669 | 0.2567 | 82.24 | 83.01 | 84.17 | 84.45 | 36.02 | 36.82 | 0.2197 |
|
||||
| 32 | 0.9124 | 0.9102 | -0.0878 | -0.1084 | 0.3275 | 0.3132 | 112.01 | 113.23 | 118.09 | 118.53 | 48.51 | 49.39 | 0.2145 |
|
||||
| 33 | 0.9271 | 0.9252 | -0.1205 | -0.1459 | 0.2604 | 0.2405 | 146.74 | 148.56 | 150.88 | 151.41 | 56.96 | 58.08 | 0.2068 |
|
||||
| 34 | 0.9447 | 0.9435 | -0.0870 | -0.1083 | 0.2446 | 0.2272 | 177.54 | 179.19 | 182.41 | 182.92 | 60.06 | 60.97 | 0.2024 |
|
||||
| 35 | 0.9363 | 0.9350 | -0.1146 | -0.1319 | 0.2415 | 0.2282 | 180.56 | 182.04 | 184.84 | 185.34 | 65.32 | 66.30 | 0.2059 |
|
||||
| 36 | 0.8726 | 0.8711 | -0.1135 | -0.1285 | 0.3862 | 0.3750 | 86.94 | 87.92 | 93.65 | 94.06 | 46.04 | 46.57 | 0.1981 |
|
||||
|
||||
g = mean of residual vectors for good prompts
|
||||
|
||||
g* = geometric median of residual vectors for good prompts
|
||||
|
||||
b = mean of residual vectors for bad prompts
|
||||
|
||||
b* = geometric median of residual vectors for bad prompts
|
||||
|
||||
r = refusal direction for means (i.e., b - g)
|
||||
|
||||
r* = refusal direction for geometric medians (i.e., b* - g*)
|
||||
|
||||
S(x,y) = cosine similarity of x and y
|
||||
|
||||
|x| = L2 norm of x
|
||||
|
||||
Silh = Mean silhouette coefficient of residuals for good/bad clusters
|
||||
|
||||
## Residual Vectors Visualization
|
||||
|
||||
|
||||
|
||||
-----
|
||||
|
||||
|
||||
# VibeThinker-3B
|
||||
|
||||
<p align="center"><a href="https://github.com/WeiboAI/VibeThinker">GitHub</a> | <a href="https://huggingface.co/WeiboAI/VibeThinker-3B">Hugging Face</a> | <a href="https://huggingface.co/papers/2606.16140">Technical Report</a></p>
|
||||
|
||||
## Introduction
|
||||
|
||||
VibeThinker-3B is a further exploration of the VibeThinker series at the 3B-parameter scale, focusing on challenging reasoning tasks with clear verification signals, such as mathematics, coding, and STEM. By systematically optimizing the Spectrum-to-Signal Principle (SSP) post-training pipeline introduced in VibeThinker-1.5B, VibeThinker-3B achieves strong performance on AIME, HMMT, IMO-AnswerBench, LiveCodeBench, and recent LeetCode contests, reaching the performance range of top-tier frontier reasoning models, including Qwen3.6 Plus, Gemini 3 Pro, GLM-5, and Kimi K2.5, on verifiable reasoning benchmarks.
|
||||
|
||||
Motivated by these observations, we propose the Parametric Compression-Coverage Hypothesis: different capabilities depend on model parameters in fundamentally different ways. Verifiable reasoning is closer to a highly compressible, parameter-dense capability, centered on multi-step reasoning, constraint satisfaction, self-correction, and answer verification. When the task space is sufficiently structured and feedback signals are sufficiently reliable, compact models may also carry near-frontier reasoning capabilities. In contrast, open-domain knowledge, general-purpose dialogue, and long-tail scenario understanding rely more heavily on large-scale parameters to broadly cover facts, concepts, and world knowledge.
|
||||
|
||||
From VibeThinker-1.5B to VibeThinker-3B, our goal is not to build a small model that replaces large-scale models, but to examine the real boundaries of small models along specific capability dimensions. With VibeThinker-3B, we aim to show that small models should not be viewed merely as a compromise for reducing deployment costs. For capability domains with clear feedback and verification mechanisms, SLMs emerge as a promising research trajectory toward frontier-level performance that is fundamentally complementary to the traditional parameter scaling paradigm.
|
||||
|
||||
|
||||
|
||||
## Key Performance Data
|
||||
|
||||
📏 In terms of reasoning accuracy relative to model scale, VibeThinker-3B reaches 76.4 on IMO-AnswerBench, a highly challenging benchmark with 400 IMO-level problems, with only 3B parameters, and improves to 80.6 with Claim-Level Reliability Assessment (CLR), a test-time scaling strategy for answer-verifiable reasoning tasks. This demonstrates that a model within a strictly small-model regime can reach the performance range of substantially larger models, such as DeepSeek V3.2 (78.3, 671B), GLM-5 (82.5, 744B), and Kimi K2.5 (81.8, 1T).
|
||||
|
||||
|
||||
|
||||
💡 VibeThinker-3B achieves strong results across mathematics, coding, knowledge, and instruction-following benchmarks.
|
||||
|
||||
|
||||
|
||||
🔁 VibeThinker-3B achieves competitive results against first-tier reasoning models and reaches the performance range of top-tier systems on several verifiable reasoning benchmarks.
|
||||
|
||||
|
||||
|
||||
🏆 To further test the model's out-of-distribution performance, we evaluate VibeThinker-3B on recent unseen LeetCode weekly and biweekly contests (Python) from Apr. 25 to May 31, 2026. VibeThinker-3B passes **123/128** first-attempt submissions, corresponding to a **96.1%** acceptance rate.
|
||||
|
||||
|
||||
|
||||
|
||||
## Training Pipeline
|
||||
|
||||
VibeThinker-3B follows the **Spectrum-to-Signal Principle (SSP)** introduced in VibeThinker-1.5B. The SFT stage constructs a broad spectrum of valid reasoning trajectories, while the RL stage amplifies correct reasoning signals using verifiable rewards.
|
||||
|
||||
|
||||
|
||||
The training pipeline contains the following stages:
|
||||
|
||||
1. **Curriculum-based two-stage SFT**
|
||||
- Stage 1 focuses on broad capability coverage across math, code, STEM reasoning, general dialogue, and instruction following.
|
||||
- Stage 2 shifts toward harder and longer-horizon reasoning samples.
|
||||
- Diversity-Exploring Distillation is used to preserve multiple valid solution paths.
|
||||
|
||||
2. **Multi-domain Reasoning RL**
|
||||
- VibeThinker-3B reuses MaxEnt-Guided Policy Optimization (MGPO).
|
||||
- RL is applied sequentially to math, code, and STEM reasoning tasks.
|
||||
- Training uses a single 64K long-context window to preserve complete long-horizon reasoning trajectories.
|
||||
|
||||
3. **Offline Self-Distillation**
|
||||
- High-quality trajectories from Math, Code, and STEM RL checkpoints are filtered and distilled back into a unified student model.
|
||||
- A learning-potential score is used to prioritize traces that are correct but not yet well modeled by the student.
|
||||
|
||||
4. **Instruct RL**
|
||||
- The final stage improves controllability on user-facing prompts.
|
||||
- Rule-based validators and rubric-based reward models are used for format-sensitive and open-ended instruction data.
|
||||
|
||||
## Usage Guidelines
|
||||
|
||||
We recommend using VibeThinker-3B for competitive-style math, coding, STEM reasoning, and other tasks where the target answer can be verified. For broad open-domain knowledge tasks, larger general-purpose models may still be more suitable.
|
||||
|
||||
For benchmark-style evaluation, the technical report uses vLLM with:
|
||||
|
||||
- `temperature=1.0`
|
||||
- `top_p=0.95`
|
||||
- `top_k=-1`
|
||||
|
||||
## Quick Start
|
||||
|
||||
Required: **transformers>=4.54.0**
|
||||
|
||||
Recommended for better inference performance: **vLLM==0.10.1 or SGLang>=0.4.9.post6**
|
||||
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
|
||||
|
||||
|
||||
class VibeThinker:
|
||||
def __init__(self, model_path):
|
||||
self.model_path = model_path
|
||||
self.model = AutoModelForCausalLM.from_pretrained(
|
||||
self.model_path,
|
||||
low_cpu_mem_usage=True,
|
||||
torch_dtype="bfloat16",
|
||||
device_map="auto",
|
||||
)
|
||||
self.tokenizer = AutoTokenizer.from_pretrained(
|
||||
self.model_path,
|
||||
trust_remote_code=True,
|
||||
)
|
||||
|
||||
def infer_text(self, prompt):
|
||||
messages = [{"role": "user", "content": prompt}]
|
||||
text = self.tokenizer.apply_chat_template(
|
||||
messages,
|
||||
tokenize=False,
|
||||
add_generation_prompt=True,
|
||||
)
|
||||
model_inputs = self.tokenizer([text], return_tensors="pt").to(self.model.device)
|
||||
|
||||
generation_config = dict(
|
||||
max_new_tokens=102400,
|
||||
do_sample=True,
|
||||
temperature=1.0,
|
||||
top_p=0.95,
|
||||
top_k=None,
|
||||
)
|
||||
generated_ids = self.model.generate(
|
||||
**model_inputs,
|
||||
generation_config=GenerationConfig(**generation_config),
|
||||
)
|
||||
generated_ids = [
|
||||
output_ids[len(input_ids):]
|
||||
for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
||||
]
|
||||
|
||||
return self.tokenizer.batch_decode(
|
||||
generated_ids,
|
||||
skip_special_tokens=True,
|
||||
)[0]
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
model = VibeThinker("WeiboAI/VibeThinker-3B")
|
||||
prompt = "Your Prompt"
|
||||
print(model.infer_text(prompt))
|
||||
```
|
||||
|
||||
## License
|
||||
|
||||
The model repository is licensed under the MIT License.
|
||||
|
||||
## Citations & References
|
||||
|
||||
If you use VibeThinker-3B in your research or product, please cite:
|
||||
|
||||
```bibtex
|
||||
@misc{xu2026vibethinker3bexploringfrontierverifiable,
|
||||
title={VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models},
|
||||
author={Sen Xu and Shixi Liu and Wei Wang and Jixin Min and Yingwei Dai and Zhibin Yin and Yirong Chen and Xin Zhou and Junlin Zhang},
|
||||
year={2026},
|
||||
eprint={2606.16140},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.AI},
|
||||
url={https://arxiv.org/abs/2606.16140},
|
||||
}
|
||||
```
|
||||
54
chat_template.jinja
Normal file
54
chat_template.jinja
Normal file
@@ -0,0 +1,54 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- messages[0]['content'] }}
|
||||
{%- else %}
|
||||
{{- 'You are a helpful assistant.' }}
|
||||
{%- endif %}
|
||||
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- for message in messages %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{{- '<|im_start|>' + message.role }}
|
||||
{%- if message.content %}
|
||||
{{- '\n' + message.content }}
|
||||
{%- endif %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if tool_call.function is defined %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- message.content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- endif %}
|
||||
69
config.json
Normal file
69
config.json
Normal file
@@ -0,0 +1,69 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151643,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 131072,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 2,
|
||||
"pad_token_id": null,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 1000000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.14.1",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151643,
|
||||
"max_new_tokens": 2048,
|
||||
"transformers_version": "5.14.1"
|
||||
}
|
||||
3
model-00001-of-00007.safetensors
Normal file
3
model-00001-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3b6cb803b8954f9b2b7efd057b83e575ee287e380d97a3d93a0ba5aae7a15423
|
||||
size 975733736
|
||||
3
model-00002-of-00007.safetensors
Normal file
3
model-00002-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:508605e4e1fe696e580456a635446162e37624b1682a61d1adb27f5a30db2258
|
||||
size 970020872
|
||||
3
model-00003-of-00007.safetensors
Normal file
3
model-00003-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:10e7602799b62c47116cdd934675026da87b8dbacd6e63e0dbee6ca96dc173de
|
||||
size 988909616
|
||||
3
model-00004-of-00007.safetensors
Normal file
3
model-00004-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:635b205643cd9b584bff98cac9d230c8213158e536cf5e101b63c300cdec7809
|
||||
size 970020952
|
||||
3
model-00005-of-00007.safetensors
Normal file
3
model-00005-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:32df3f2004fbf31597c43980e61b26bf0588395452d44f4a38c19d94515b50bc
|
||||
size 970020944
|
||||
3
model-00006-of-00007.safetensors
Normal file
3
model-00006-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d60b60b83378808607b68f679f3bb37c570adda5f67cb2ec2e6a49cb7c7e92b5
|
||||
size 988909632
|
||||
3
model-00007-of-00007.safetensors
Normal file
3
model-00007-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1a7def49b1496bfa4eda358b1b0b219ea626ab60cedb05de4f995a07bee29100
|
||||
size 308310688
|
||||
442
model.safetensors.index.json
Normal file
442
model.safetensors.index.json
Normal file
@@ -0,0 +1,442 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 3085938688,
|
||||
"total_size": 6171877376
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.norm.weight": "model-00007-of-00007.safetensors"
|
||||
}
|
||||
}
|
||||
3
pictures/Abstrct.png
Normal file
3
pictures/Abstrct.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6c800e55c302c62ef138726a1db09fa5d3a7c60e964b4769cedc491bc0dd7254
|
||||
size 215002
|
||||
3
pictures/Acc_and_Scale.png
Normal file
3
pictures/Acc_and_Scale.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e05d10eb97ec6044e03cf4ce1c7eeb94f392e618049490700ea26c994b6978a9
|
||||
size 103916
|
||||
3
pictures/Architecture.png
Normal file
3
pictures/Architecture.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:71f5f02ff71fe4b47be25c94e0e7dceeb813ce8baf7f3f69d93a613b11ede15e
|
||||
size 125754
|
||||
3
pictures/LeetCode.png
Normal file
3
pictures/LeetCode.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8d7f23be2515c6be4228983e48697b90a89de0f1b5dbc636e64872f164176a59
|
||||
size 228922
|
||||
3
pictures/VibeThiinker-3B.png
Normal file
3
pictures/VibeThiinker-3B.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4ae18631f39b472cfab1f327c659a4ea2c4d111b6e739fc4764709cfbaa49a06
|
||||
size 248723
|
||||
3
pictures/VibeThinker-3B+CLR.png
Normal file
3
pictures/VibeThinker-3B+CLR.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9ce66aa2fb3c5c93f1b8c7746c65d2217aedce19218d96f10b16092c0bfe0508
|
||||
size 213442
|
||||
3
pictures/animation-VibeThinker-3B.gif
Normal file
3
pictures/animation-VibeThinker-3B.gif
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5451de26ea2fe763a8240bdee3ea4a8d4e89b083aea247b274887605918cd987
|
||||
size 11715037
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:287f2606720ee3cee69948de373ad0f1a741765bbd4a729d27e0c2b4037bd206
|
||||
size 11422430
|
||||
16
tokenizer_config.json
Normal file
16
tokenizer_config.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"is_local": true,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "left",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
Reference in New Issue
Block a user