初始化项目，由ModelHub XC社区提供模型
Model: XiaomiMiMo/MiMo-7B-RL Source: Original Platform
This commit is contained in:
ModelHub XC
49
.gitattributes
vendored
Normal file
49
.gitattributes
vendored
Normal file
@@ -0,0 +1,49 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 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
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack 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
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* 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
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||||
|
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm 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
|
||||||
277
README.md
Normal file
277
README.md
Normal file
@@ -0,0 +1,277 @@
|
|||||||
|
---
|
||||||
|
license: mit
|
||||||
|
library_name: transformers
|
||||||
|
---
|
||||||
|
<div align="center">
|
||||||
|
<picture>
|
||||||
|
<source srcset="https://github.com/XiaomiMiMo/MiMo/raw/main/figures/Xiaomi_MiMo_darkmode.png?raw=true" media="(prefers-color-scheme: dark)">
|
||||||
|
<img src="https://github.com/XiaomiMiMo/MiMo/raw/main/figures/Xiaomi_MiMo.png?raw=true" width="60%" alt="Xiaomi-MiMo" />
|
||||||
|
</picture>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<h3 align="center">
|
||||||
|
<b>
|
||||||
|
<span>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━</span>
|
||||||
|
<br/>
|
||||||
|
Unlocking the Reasoning Potential of Language Model<br/>From Pretraining to Posttraining
|
||||||
|
<br/>
|
||||||
|
<span>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━</span>
|
||||||
|
<br/>
|
||||||
|
</b>
|
||||||
|
</h3>
|
||||||
|
|
||||||
|
<br/>
|
||||||
|
|
||||||
|
<div align="center" style="line-height: 1;">
|
||||||
|
|
|
||||||
|
<a href="https://huggingface.co/XiaomiMiMo" target="_blank">🤗 HuggingFace</a>
|
||||||
|
|
|
||||||
|
<a href="https://www.modelscope.cn/organization/XiaomiMiMo" target="_blank">🤖️ ModelScope</a>
|
||||||
|
|
|
||||||
|
<a href="https://arxiv.org/abs/2505.07608" target="_blank">📔 Technical Report</a>
|
||||||
|
|
|
||||||
|
<br/>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<br/>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## Updates
|
||||||
|
|
||||||
|
[2025.05.30] We scaled the SFT dataset from approximately 500K to 6M instances and continuously expanding the RL training window size from 32K to 48K, the performance of [MiMo-7B-RL-0530](https://huggingface.co/XiaomiMiMo/MiMo-7B-RL-0530) on AIME24 can be continuously improved and eventually surpass that of DeepSeek R1 (79.8).
|
||||||
|
|
||||||
|
<table>
|
||||||
|
<thead>
|
||||||
|
<tr>
|
||||||
|
<th>Benchmark</th>
|
||||||
|
<th>MiMo-7B-RL</th>
|
||||||
|
<th>MiMo-7B-RL-0530</th>
|
||||||
|
</tr>
|
||||||
|
</thead>
|
||||||
|
<tbody>
|
||||||
|
<tr>
|
||||||
|
<td colspan="3"><strong>Mathematics</strong></td>
|
||||||
|
<p align="center">
|
||||||
|
<td rowspan="11"><img width="80%" src="https://github.com/XiaomiMiMo/MiMo/raw/main/figures/length.jpg?raw=true"></td>
|
||||||
|
</p>
|
||||||
|
</tr>
|
||||||
|
<tr><td>MATH500<br/>(Pass@1)</td><td>95.8</td><td>97.2</td></tr>
|
||||||
|
<tr><td>AIME 2024<br/>(Pass@1)</td><td>68.2</td><td>80.1</td></tr>
|
||||||
|
<tr><td>AIME 2025<br/>(Pass@1)</td><td>55.4</td><td>70.2</td></tr>
|
||||||
|
<tr><td colspan="3"><strong>Code</strong></td></tr>
|
||||||
|
<tr><td>LiveCodeBench v5<br/>(Pass@1)</td><td>57.8</td><td>60.9</td></tr>
|
||||||
|
<tr><td>LiveCodeBench v6<br/>(Pass@1)</td><td>49.3</td><td>52.2</td></tr>
|
||||||
|
<tr><td colspan="3"><strong>STEM</strong></td></tr>
|
||||||
|
<tr><td>GPQA-Diamond<br/>(Pass@1)</td><td>54.4</td><td>60.6</td></tr>
|
||||||
|
<tr><td colspan="3"><strong>General</strong></td></tr>
|
||||||
|
<tr><td>Alignbench1.1<br/>(Evaluated by GPT4.1)</td><td>6.9</td><td>7.4</td></tr>
|
||||||
|
</tbody>
|
||||||
|
</table>
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
## I. Introduction
|
||||||
|
|
||||||
|
Currently, most successful RL works, including open-source research, rely on relatively large base models, e.g., 32B models, particularly for enhancing code reasoning capabilities. Moreover, it was widely considered that achieving uniform and simultaneous improvements in both mathematical and code capabilities within a small model is challenging. Nonetheless, we believe that the effectiveness of the RL trained reasoning model relies on the inherent reasoning potential of the base model. To fully unlock the reasoning potential of language models, efforts must focus not only on post-training but also on pre-training strategies tailored to reasoning.
|
||||||
|
|
||||||
|
In this work, we present MiMo-7B, a series of models trained from scratch and born for reasoning tasks. Our RL experiments from MiMo-7B-Base show that our model possesses extraordinary reasoning potential, even surpassing much larger 32B models. Additionally, we perform RL training on a cold-started SFT model, resulting in MiMo-7B-RL, which demonstrates superior performance on both mathematics and code reasoning tasks, matching the performance of OpenAI o1-mini.
|
||||||
|
|
||||||
|
<p align="center">
|
||||||
|
<img width="80%" src="https://github.com/XiaomiMiMo/MiMo/raw/main/figures/curve.png?raw=true">
|
||||||
|
</p>
|
||||||
|
|
||||||
|
We open-source MiMo-7B series, including checkpoints of the base model, SFT model, RL model trained from base model, and RL model trained from the SFT model.
|
||||||
|
We believe this report along with the models will provide valuable insights to develop powerful reasoning LLMs that benefit the larger community.
|
||||||
|
|
||||||
|
### 🌟 Highlights
|
||||||
|
|
||||||
|
- **Pre-Training: Base Model Born for Reasoning**
|
||||||
|
- We optimize the data preprocessing pipeline, enhancing text extraction toolkits and applying multi-dimensional data filtering to increase reasoning pattern density in pre-training data. We also employ multiple strategies to generate massive diverse synthetic reasoning data.
|
||||||
|
- We adopt a three-stage data mixture strategy for pre-training. Overall, MiMo-7B-Base is pre-trained on approximately 25 trillion tokens.
|
||||||
|
- We incorporate Multiple-Token Prediction as an additional training objective, which enhances model performance and accelerates inference.
|
||||||
|
|
||||||
|
- **Post-Training Recipe: Pioneering Reasoning Model**
|
||||||
|
- We curate 130K mathematics and code problems as RL training data, which can be verified by rule-based verifiers. Each problem undergoes careful cleaning and difficulty assessment to ensure quality. We employ only rule-based accuracy rewards to avoid potential reward hacking.
|
||||||
|
- To mitigate the sparse reward issue for challenging code problems, we introduce a test difficulty driven code reward. By assigning fine-grained scores for test cases with varying difficulty levels, the policy can be more effectively optimized via dense reward signal.
|
||||||
|
- We implement a data re-sampling strategy for easy problems to enhance rollout sampling efficiency and stabilize policy updates, particularly in the later phases of RL training.
|
||||||
|
|
||||||
|
- **RL Infrastructure**
|
||||||
|
- We develop a Seamless Rollout Engine to accelerate RL training and validation. Our design integrates continuous rollout, asynchronous reward computation, and early termination to minimize GPU idle time, achieving $2.29\times$ faster training and $1.96\times$ faster validation.
|
||||||
|
- We support MTP in vLLM and enhance the robustness of the inference engine in the RL system.
|
||||||
|
|
||||||
|
## II. Model Details
|
||||||
|
|
||||||
|
The MTP layers of MiMo-7B is tuned during pretraining and SFT and freezed during RL. With one MTP layer for speculative decoding, the acceptance rate is about 90%.
|
||||||
|
|
||||||
|
<p align="center">
|
||||||
|
<img width="80%" src="https://github.com/XiaomiMiMo/MiMo/raw/main/figures/architecture.png?raw=true">
|
||||||
|
</p>
|
||||||
|
|
||||||
|
> Models are available at [https://huggingface.co/XiaomiMiMo](https://huggingface.co/XiaomiMiMo) and [https://www.modelscope.cn/organization/XiaomiMiMo](https://www.modelscope.cn/organization/XiaomiMiMo)
|
||||||
|
|
||||||
|
| **Model** | **Description** | **Download (HuggingFace)** | **Download (ModelScope)** |
|
||||||
|
| :-------------: | :---------------------------------------------------------------------------: | :-------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------: |
|
||||||
|
| MiMo-7B-Base | Base model with extraordinary reasoning potential | [🤗 XiaomiMiMo/MiMo-7B-Base](https://huggingface.co/XiaomiMiMo/MiMo-7B-Base) | [🤖️ XiaomiMiMo/MiMo-7B-Base](https://www.modelscope.cn/models/XiaomiMiMo/MiMo-7B-Base) |
|
||||||
|
| MiMo-7B-RL-Zero | RL model trained from base model | [🤗 XiaomiMiMo/MiMo-7B-RL-Zero](https://huggingface.co/XiaomiMiMo/MiMo-7B-RL-Zero) | [🤖️ XiaomiMiMo/MiMo-7B-RL-Zero](https://www.modelscope.cn/models/XiaomiMiMo/MiMo-7B-RL-Zero) |
|
||||||
|
| MiMo-7B-SFT | SFT model trained from base model | [🤗 XiaomiMiMo/MiMo-7B-SFT](https://huggingface.co/XiaomiMiMo/MiMo-7B-SFT) | [🤖️ XiaomiMiMo/MiMo-7B-SFT](https://www.modelscope.cn/models/XiaomiMiMo/MiMo-7B-SFT) |
|
||||||
|
| MiMo-7B-RL | RL model trained from SFT model, superior performance matching OpenAI o1-mini | [🤗 XiaomiMiMo/MiMo-7B-RL](https://huggingface.co/XiaomiMiMo/MiMo-7B-RL) | [🤖️ XiaomiMiMo/MiMo-7B-RL](https://www.modelscope.cn/models/XiaomiMiMo/MiMo-7B-RL) |
|
||||||
|
|
||||||
|
## III. Evaluation Results
|
||||||
|
|
||||||
|
| Benchmark | GPT-4o-0513 | Claude-3.5-Sonnet-1022 | OpenAI o1-mini | QwQ-32B-Preview | R1-Distill-Qwen-14B | R1-Distill-Qwen-7B | MiMo-7B-RL |
|
||||||
|
| ----------------------------- | :---------: | :--------------------: | :------------: | :-------------: | :-----------------: | :----------------: | :--------: |
|
||||||
|
| **General** | | | | | | | |
|
||||||
|
| GPQA Diamond<br/>(Pass@1) | 49.9 | 65.0 | 60.0 | 54.5 | 59.1 | 49.1 | 54.4 |
|
||||||
|
| SuperGPQA<br/>(Pass@1) | 42.4 | 48.2 | 45.2 | 43.6 | 40.6 | 28.9 | 40.5 |
|
||||||
|
| DROP<br/>(3-shot F1) | 83.7 | 88.3 | 83.9 | 71.2 | 85.5 | 77.0 | 78.7 |
|
||||||
|
| MMLU-Pro<br/>(EM) | 72.6 | 78.0 | 80.3 | 52.0 | 68.8 | 53.5 | 58.6 |
|
||||||
|
| IF-Eval<br/>(Prompt Strict) | 84.3 | 86.5 | 84.8 | 40.4 | 78.3 | 60.5 | 61.0 |
|
||||||
|
| **Mathematics** | | | | | | | |
|
||||||
|
| MATH-500<br/>(Pass@1) | 74.6 | 78.3 | 90.0 | 90.6 | 93.9 | 92.8 | 95.8 |
|
||||||
|
| AIME 2024<br/>(Pass@1) | 9.3 | 16.0 | 63.6 | 50.0 | 69.7 | 55.5 | 68.2 |
|
||||||
|
| AIME 2025<br/>(Pass@1) | 11.6 | 7.4 | 50.7 | 32.4 | 48.2 | 38.8 | 55.4 |
|
||||||
|
| **Code** | | | | | | | |
|
||||||
|
| LiveCodeBench v5<br/>(Pass@1) | 32.9 | 38.9 | 53.8 | 41.9 | 53.1 | 37.6 | 57.8 |
|
||||||
|
| LiveCodeBench v6<br/>(Pass@1) | 30.9 | 37.2 | 46.8 | 39.1 | 31.9 | 23.9 | 49.3 |
|
||||||
|
|
||||||
|
MiMo-7B series
|
||||||
|
|
||||||
|
| Benchmark | MiMo-7B-Base | MiMo-7B-RL-Zero | MiMo-7B-SFT | MiMo-7B-RL |
|
||||||
|
| ----------------------------- | :----------: | :-------------: | :---------: | :--------: |
|
||||||
|
| **Mathematics** | | | | |
|
||||||
|
| MATH500<br/>(Pass@1) | 37.4 | 93.6 | 93.0 | 95.8 |
|
||||||
|
| AIME 2024<br/>(Pass@1) | 32.9 | 56.4 | 58.7 | 68.2 |
|
||||||
|
| AIME 2025<br/>(Pass@1) | 24.3 | 46.3 | 44.3 | 55.4 |
|
||||||
|
| **Code** | | | | |
|
||||||
|
| LiveCodeBench v5<br/>(Pass@1) | 32.9 | 49.1 | 52.3 | 57.8 |
|
||||||
|
| LiveCodeBench v6<br/>(Pass@1) | 29.1 | 42.9 | 45.5 | 49.3 |
|
||||||
|
|
||||||
|
> [!IMPORTANT]
|
||||||
|
> The evaluations are conducted with `temperature=0.6`.
|
||||||
|
>
|
||||||
|
> AIME24 and AIME25 are with averaged score of 32 repetitions. LiveCodeBench v5 (20240801-20250201), LiveCodeBench v6 (20250201-20250501), GPQA-Diamond and IF-Eval are with averaged score of 8 repetitions. MATH500 and SuperGPQA are with a single run.
|
||||||
|
|
||||||
|
## IV. Deployment
|
||||||
|
|
||||||
|
### SGLang Inference
|
||||||
|
|
||||||
|
Thanks to the [MiMo model support](https://github.com/sgl-project/sglang/pull/5921) and [MTP](https://github.com/sgl-project/sglang/pull/6059) from the SGLang team, we supported MiMo in SGLang mainstream.
|
||||||
|
|
||||||
|
Example Script
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Install the latest SGlang from main branch
|
||||||
|
python3 -m uv pip install "sglang[all] @ git+https://github.com/sgl-project/sglang.git/@main#egg=sglang&subdirectory=python"
|
||||||
|
|
||||||
|
# Launch SGLang Server
|
||||||
|
python3 -m sglang.launch_server --model-path XiaomiMiMo/MiMo-7B-RL --host 0.0.0.0 --trust-remote-code
|
||||||
|
|
||||||
|
# Launch MTP Server
|
||||||
|
python3 -m sglang.launch_server --model-path XiaomiMiMo/MiMo-7B-RL --trust-remote-code \
|
||||||
|
--speculative-algorithm EAGLE --speculative-num-steps 1 --speculative-eagle-topk 1 \
|
||||||
|
--speculative-num-draft-tokens 2 --mem-fraction 0.5
|
||||||
|
```
|
||||||
|
|
||||||
|
Detailed usage can be found in [SGLang documents](https://docs.sglang.ai/backend/send_request.html).
|
||||||
|
|
||||||
|
### vLLM inference
|
||||||
|
|
||||||
|
1. [Recommended] We officially support inference with MiMo-MTP using [our fork of vLLM](https://github.com/XiaomiMiMo/vllm/tree/feat_mimo_mtp_stable_073).
|
||||||
|
|
||||||
|
Example script
|
||||||
|
|
||||||
|
```py
|
||||||
|
from vllm import LLM, SamplingParams
|
||||||
|
|
||||||
|
model_path = "/path/to/MiMo"
|
||||||
|
llm = LLM(
|
||||||
|
model=model_path,
|
||||||
|
trust_remote_code=True,
|
||||||
|
num_speculative_tokens=1,
|
||||||
|
disable_log_stats=False
|
||||||
|
)
|
||||||
|
sampling_params = SamplingParams(temperature=0.6)
|
||||||
|
|
||||||
|
conversation = [
|
||||||
|
{
|
||||||
|
"role": "system",
|
||||||
|
"content": ""
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"role": "user",
|
||||||
|
"content": "Write an essay about the importance of higher education.",
|
||||||
|
},
|
||||||
|
]
|
||||||
|
|
||||||
|
outputs = llm.chat(conversation,
|
||||||
|
sampling_params=sampling_params,
|
||||||
|
use_tqdm=False)
|
||||||
|
|
||||||
|
for output in outputs:
|
||||||
|
prompt = output.prompt
|
||||||
|
generated_text = output.outputs[0].text
|
||||||
|
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
|
||||||
|
|
||||||
|
print("=" * 80)
|
||||||
|
```
|
||||||
|
|
||||||
|
2. Or, you can register a vLLM loader for MiMo without loading MTP parameters.
|
||||||
|
|
||||||
|
You can copy the [`registry/register_mimo_in_vllm.py`](https://github.com/XiaomiMiMo/MiMo/blob/main/registry/register_mimo_in_vllm.py) to your directory and import it with
|
||||||
|
|
||||||
|
```py
|
||||||
|
import register_mimo_in_vllm
|
||||||
|
|
||||||
|
from vllm import LLM, SamplingParams
|
||||||
|
|
||||||
|
model_path = "/path/to/MiMo"
|
||||||
|
llm = LLM(
|
||||||
|
model=model_path,
|
||||||
|
trust_remote_code=True,
|
||||||
|
# num_speculative_tokens=1,
|
||||||
|
disable_log_stats=False
|
||||||
|
)
|
||||||
|
sampling_params = SamplingParams(temperature=0.6)
|
||||||
|
```
|
||||||
|
|
||||||
|
### HuggingFace inference
|
||||||
|
|
||||||
|
Example script
|
||||||
|
|
||||||
|
```py
|
||||||
|
from transformers import AutoModel, AutoModelForCausalLM, AutoTokenizer
|
||||||
|
|
||||||
|
model_id = "XiaomiMiMo/MiMo-7B-RL"
|
||||||
|
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True)
|
||||||
|
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||||
|
inputs = tokenizer(["Today is"], return_tensors='pt')
|
||||||
|
output = model.generate(**inputs, max_new_tokens = 100)
|
||||||
|
print(tokenizer.decode(output.tolist()[0]))
|
||||||
|
```
|
||||||
|
|
||||||
|
### Recommended environment and prompts
|
||||||
|
|
||||||
|
- We recommend using [our fork of vLLM](https://github.com/XiaomiMiMo/vllm/tree/feat_mimo_mtp_stable_073) which is developed based on vLLM 0.7.3.
|
||||||
|
- We recommend using empty system prompt.
|
||||||
|
|
||||||
|
> We haven't verified MiMo with other inference engines and welcome contributions based on the model definition in the Huggingface repo 💻.
|
||||||
|
|
||||||
|
## V. Citation
|
||||||
|
|
||||||
|
```bibtex
|
||||||
|
@misc{coreteam2025mimounlockingreasoningpotential,
|
||||||
|
title={MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining},
|
||||||
|
author={LLM-Core-Team Xiaomi},
|
||||||
|
year={2025},
|
||||||
|
eprint={2505.07608},
|
||||||
|
archivePrefix={arXiv},
|
||||||
|
primaryClass={cs.CL},
|
||||||
|
url={https://arxiv.org/abs/2505.07608},
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
|
||||||
|
## VI. Contact
|
||||||
|
|
||||||
|
Please contact us at [mimo@xiaomi.com](mailto:mimo@xiaomi.com) or open an issue if you have any questions.
|
||||||
39
config.json
Normal file
39
config.json
Normal file
@@ -0,0 +1,39 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"MiMoForCausalLM"
|
||||||
|
],
|
||||||
|
"tokenizer_class":[
|
||||||
|
"Qwen2Tokenizer"
|
||||||
|
],
|
||||||
|
"auto_map": {
|
||||||
|
"AutoConfig": "configuration_mimo.MiMoConfig",
|
||||||
|
"AutoModel": "modeling_mimo.MiMoModel",
|
||||||
|
"AutoModelForCausalLM": "modeling_mimo.MiMoForCausalLM"
|
||||||
|
},
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 4096,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 11008,
|
||||||
|
"max_position_embeddings": 32768,
|
||||||
|
"max_window_layers": 36,
|
||||||
|
"model_type": "mimo",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"head_dim": 128,
|
||||||
|
"num_hidden_layers": 36,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_theta": 640000,
|
||||||
|
"sliding_window": 32768,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.40.1",
|
||||||
|
"use_cache": true,
|
||||||
|
"use_mrope": false,
|
||||||
|
"use_sliding_window": false,
|
||||||
|
"vocab_size": 151680,
|
||||||
|
"attention_bias": true,
|
||||||
|
"num_nextn_predict_layers": 1
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "others", "allow_remote": true}
|
||||||
16
configuration_mimo.py
Normal file
16
configuration_mimo.py
Normal file
@@ -0,0 +1,16 @@
|
|||||||
|
from transformers.models.qwen2.configuration_qwen2 import Qwen2Config
|
||||||
|
|
||||||
|
class MiMoConfig(Qwen2Config):
|
||||||
|
model_type = "mimo"
|
||||||
|
|
||||||
|
def __init__(
|
||||||
|
self,
|
||||||
|
*args,
|
||||||
|
num_nextn_predict_layers=0,
|
||||||
|
**kwargs
|
||||||
|
):
|
||||||
|
self.num_nextn_predict_layers = num_nextn_predict_layers
|
||||||
|
super().__init__(
|
||||||
|
*args,
|
||||||
|
**kwargs,
|
||||||
|
)
|
||||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
{
|
||||||
|
"bos_token_id": 151643,
|
||||||
|
"do_sample": false,
|
||||||
|
"eos_token_id": 151645,
|
||||||
|
"max_new_tokens": 2048,
|
||||||
|
"transformers_version": "4.37.0"
|
||||||
|
}
|
||||||
151387
merges.txt
Normal file
151387
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:35e42b582755796a0f314bd565355ef9e35a6376e40158fa7fdb1d522ca8933d
|
||||||
|
size 3987958288
|
||||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:ff50b6b2c1a3ec75c428cca736550043983dd85c05d1b422f7a5206a3a39173d
|
||||||
|
size 3989130384
|
||||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:1198f24370251bfcce3e8b3209ad80d4d17ce6743f36d29b469c0c0455bb0f66
|
||||||
|
size 3982835320
|
||||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5a14d2b0b23228b92765eb50ff26d73dc67e54c5f884b8bd58e84bd28c566084
|
||||||
|
size 3706946944
|
||||||
458
model.safetensors.index.json
Normal file
458
model.safetensors.index.json
Normal file
@@ -0,0 +1,458 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 15666819072
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||||
|
"model.mtp_layers.0.final_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.mtp_layers.0.hidden_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.mtp_layers.0.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.mtp_layers.0.input_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.mtp_layers.0.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.mtp_layers.0.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.mtp_layers.0.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.mtp_layers.0.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.mtp_layers.0.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.mtp_layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.mtp_layers.0.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.mtp_layers.0.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.mtp_layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.mtp_layers.0.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
|
||||||
|
"model.mtp_layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.mtp_layers.0.token_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||||
|
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
75
modeling_mimo.py
Normal file
75
modeling_mimo.py
Normal file
@@ -0,0 +1,75 @@
|
|||||||
|
from typing import Optional, Tuple
|
||||||
|
|
||||||
|
import torch
|
||||||
|
from torch import nn
|
||||||
|
from transformers.cache_utils import Cache
|
||||||
|
from transformers.models.qwen2.modeling_qwen2 import (Qwen2Attention,
|
||||||
|
Qwen2ForCausalLM,
|
||||||
|
Qwen2MLP, Qwen2Model,
|
||||||
|
Qwen2RMSNorm)
|
||||||
|
|
||||||
|
from .configuration_mimo import MiMoConfig
|
||||||
|
|
||||||
|
|
||||||
|
class MiMoMTPLayers(nn.Module):
|
||||||
|
def __init__(self, config):
|
||||||
|
super().__init__()
|
||||||
|
self.input_layernorm = Qwen2RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
|
||||||
|
self.post_attention_layernorm = Qwen2RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
|
||||||
|
self.token_layernorm = Qwen2RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
|
||||||
|
self.hidden_layernorm = Qwen2RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
|
||||||
|
self.input_proj = nn.Linear(config.hidden_size * 2, config.hidden_size, bias=False)
|
||||||
|
self.final_layernorm = Qwen2RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
|
||||||
|
self.self_attn = Qwen2Attention(config, layer_idx=0)
|
||||||
|
self.mlp = Qwen2MLP(config)
|
||||||
|
|
||||||
|
def forward(self, input_embeds,
|
||||||
|
hidden_states,
|
||||||
|
attention_mask,
|
||||||
|
position_ids,
|
||||||
|
past_key_values: Optional[Cache]=None,
|
||||||
|
output_attentions: Optional[bool]=False,
|
||||||
|
use_cache: Optional[bool]=False,
|
||||||
|
position_embedding: Optional[Tuple[torch.Tensor, torch.Tensor]] = None,
|
||||||
|
cache_position=None,
|
||||||
|
**kwargs):
|
||||||
|
input_embeds = self.token_layernorm(input_embeds)
|
||||||
|
previous_hidden_states = self.hidden_layernorm(hidden_states)
|
||||||
|
hidden_states = self.input_proj(torch.cat([previous_hidden_states, input_embeds], dim=-1))
|
||||||
|
residual = hidden_states
|
||||||
|
hidden_states = self.input_layernorm(hidden_states)
|
||||||
|
hidden_states, _ = self.self_attn(hidden_states,
|
||||||
|
attention_mask=attention_mask,
|
||||||
|
position_ids=position_ids,
|
||||||
|
past_key_values=past_key_values,
|
||||||
|
output_attentions=output_attentions,
|
||||||
|
use_cache=use_cache,
|
||||||
|
cache_position=cache_position,
|
||||||
|
position_embedding=position_embedding,
|
||||||
|
**kwargs)
|
||||||
|
hidden_states = residual + hidden_states
|
||||||
|
residual = hidden_states
|
||||||
|
hidden_states = self.post_attention_layernorm(hidden_states)
|
||||||
|
hidden_states = self.mlp(hidden_states)
|
||||||
|
hidden_states = residual + hidden_states
|
||||||
|
hidden_states = self.final_layernorm(hidden_states)
|
||||||
|
return hidden_states
|
||||||
|
|
||||||
|
|
||||||
|
class MiMoModel(Qwen2Model):
|
||||||
|
config_class = MiMoConfig
|
||||||
|
|
||||||
|
def __init__(self, config: MiMoConfig):
|
||||||
|
super().__init__(config)
|
||||||
|
self.mtp_layers = nn.ModuleList([MiMoMTPLayers(config) for _ in range(config.num_nextn_predict_layers)])
|
||||||
|
|
||||||
|
|
||||||
|
class MiMoForCausalLM(Qwen2ForCausalLM):
|
||||||
|
config_class = MiMoConfig
|
||||||
|
def __init__(self, config: MiMoConfig):
|
||||||
|
super(Qwen2ForCausalLM, self).__init__(config)
|
||||||
|
self.model = MiMoModel(config)
|
||||||
|
self.vocab_size = config.vocab_size
|
||||||
|
self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
|
||||||
|
|
||||||
|
self.post_init()
|
||||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
207
tokenizer_config.json
Normal file
207
tokenizer_config.json
Normal file
@@ -0,0 +1,207 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": false,
|
||||||
|
"add_prefix_space": false,
|
||||||
|
"added_tokens_decoder": {
|
||||||
|
"151643": {
|
||||||
|
"content": "<|endoftext|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151644": {
|
||||||
|
"content": "<|im_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151645": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151646": {
|
||||||
|
"content": "<|object_ref_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151647": {
|
||||||
|
"content": "<|object_ref_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151648": {
|
||||||
|
"content": "<|box_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151649": {
|
||||||
|
"content": "<|box_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151650": {
|
||||||
|
"content": "<|quad_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151651": {
|
||||||
|
"content": "<|quad_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151652": {
|
||||||
|
"content": "<|vision_start|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151653": {
|
||||||
|
"content": "<|vision_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151654": {
|
||||||
|
"content": "<|vision_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151655": {
|
||||||
|
"content": "<|image_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151656": {
|
||||||
|
"content": "<|video_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": true
|
||||||
|
},
|
||||||
|
"151657": {
|
||||||
|
"content": "<tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151658": {
|
||||||
|
"content": "</tool_call>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151659": {
|
||||||
|
"content": "<|fim_prefix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151660": {
|
||||||
|
"content": "<|fim_middle|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151661": {
|
||||||
|
"content": "<|fim_suffix|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151662": {
|
||||||
|
"content": "<|fim_pad|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151663": {
|
||||||
|
"content": "<|repo_name|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
},
|
||||||
|
"151664": {
|
||||||
|
"content": "<|file_sep|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false,
|
||||||
|
"special": false
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>",
|
||||||
|
"<|im_end|>",
|
||||||
|
"<|object_ref_start|>",
|
||||||
|
"<|object_ref_end|>",
|
||||||
|
"<|box_start|>",
|
||||||
|
"<|box_end|>",
|
||||||
|
"<|quad_start|>",
|
||||||
|
"<|quad_end|>",
|
||||||
|
"<|vision_start|>",
|
||||||
|
"<|vision_end|>",
|
||||||
|
"<|vision_pad|>",
|
||||||
|
"<|image_pad|>",
|
||||||
|
"<|video_pad|>"
|
||||||
|
],
|
||||||
|
"bos_token": null,
|
||||||
|
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": "<|im_end|>",
|
||||||
|
"errors": "replace",
|
||||||
|
"model_max_length": 131072,
|
||||||
|
"pad_token": "<|endoftext|>",
|
||||||
|
"split_special_tokens": false,
|
||||||
|
"tokenizer_class": "Qwen2Tokenizer",
|
||||||
|
"unk_token": null
|
||||||
|
}
|
||||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user