初始化项目，由ModelHub XC社区提供模型
Model: Alibaba-AAIG/oyster_1 Source: Original Platform
This commit is contained in:
ModelHub XC
53
.gitattributes
vendored
Normal file
53
.gitattributes
vendored
Normal file
@@ -0,0 +1,53 @@
|
||||
*.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
|
||||
|
||||
merges.txt filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
vocab.json filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
AAIG海洋图.jpg filter=lfs diff=lfs merge=lfs -text
|
||||
28
.ipynb_checkpoints/added_tokens-checkpoint.json
Normal file
28
.ipynb_checkpoints/added_tokens-checkpoint.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
3
AAIG海洋图.jpg
Normal file
3
AAIG海洋图.jpg
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0564fc9783630ab2f8d74065357514e6466cc7e8c83c98d8c218984fc3b521c9
|
||||
size 21885015
|
||||
147
README.md
Normal file
147
README.md
Normal file
@@ -0,0 +1,147 @@
|
||||
<div align="center">
|
||||
|
||||
# Oyster I: Beyond Refusal — Constructive Safety Alignment for Responsible Language Models
|
||||
|
||||
</div>
|
||||
|
||||
<p align="center">
|
||||
  🤖 <a href="https://modelscope.cn/organization/oyster">ModelScope</a>   |   📄 <a href=" None ">Arxiv</a>
|
||||
</a>  
|
||||
</p>
|
||||
|
||||
|
||||
|
||||
<p align="center">
|
||||
<img src="oyster_intro.png" alt="Oyster Logo" width="800"/>
|
||||
</p>
|
||||
|
||||
---
|
||||
|
||||
## 🦪 介绍
|
||||
目前，大型语言模型（LLMs）通常采用纯拒绝的安全机制来防止生成有害内容。然而，单纯的拒绝可能导致用户反复尝试或转向限制较少的平台，从而带来更大的风险。为此，我们提出了建设性安全对齐（CSA），在防止恶意使用的同时，积极引导非恶意用户走向安全且有益的结果，并在 **Oyster‑1 (Oy1)** 中实现了CSA。为了评估CSA，我们开发了一个专门的建设性基准，涵盖多种风险类型和用户角色，模拟真实的用户情境。Oy1在自动化和人工评估中均取得了领先的建设性对齐得分，不仅能够拒绝对抗性查询，还能在复杂的风险场景中提供建设性指导。
|
||||
|
||||
<p align="center">
|
||||
<img src="./exp_1.png" alt="示例图片" width="800"/>
|
||||
<p>
|
||||
|
||||
---
|
||||
|
||||
## 🧩 Constructive Safety Alignment (CSA)
|
||||
|
||||
**CSA 的目标是超越简单拒绝：**
|
||||
|
||||
- **防范恶意滥用**
|
||||
- **引导非恶意用户走向安全和积极的方向**
|
||||
|
||||
### 核心技术
|
||||
|
||||
1. **博弈论交互建模**
|
||||
- 将模型-用户交互建模为分层 Stackelberg 博弈。
|
||||
- 模型作为引导者，根据预测用户反应确定策略。
|
||||
|
||||
2. **多维风险评估**
|
||||
- 评估多种风险类型，动态优化响应策略。
|
||||
|
||||
3. **结构化推理链 + Linguistic Backpropagation (Lingo-BP)**
|
||||
- 显式分解为关键的安全决策节点。
|
||||
- 从目标生成语义信号，反向传播调整中间判断。
|
||||
- 在可解释路径上平衡安全性与有用性。
|
||||
|
||||
4. **Oyster I 模型训练**
|
||||
- 基于生成的安全推理路径进行偏好学习训练。
|
||||
- 提升安全与建设性交互能力。
|
||||
|
||||
---
|
||||
|
||||
|
||||
|
||||
## 🚀 快速上手
|
||||
|
||||
### 1. 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
|
||||
|
||||
SDK下载
|
||||
```bash
|
||||
#安装ModelScope
|
||||
pip install modelscope
|
||||
```
|
||||
```python
|
||||
#SDK模型下载
|
||||
from modelscope import snapshot_download
|
||||
model_dir = snapshot_download('OysterAI/oyster_1')
|
||||
```
|
||||
Git下载
|
||||
```
|
||||
#Git模型下载
|
||||
git clone https://www.modelscope.cn/OysterAI/oyster_1.git
|
||||
```
|
||||
|
||||
### 2. 使用 Oyster-1 进行对话
|
||||
|
||||
您只需使用 transformers 库编写几行代码，即可与 Oyster-1 进行对话。具体来说，我们通过 from_pretrained 方法加载分词器和模型，并利用 generate 方法生成对话内容。以下是与 Oyster-1 进行对话的示例：
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
model_name = "OysterAI/oyster_1"
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_name,
|
||||
device_map="auto"
|
||||
)
|
||||
|
||||
prompt = "I feel like ending it all. Nothing matters anymore."
|
||||
|
||||
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
||||
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=4096
|
||||
)
|
||||
|
||||
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||||
|
||||
```
|
||||
> 💡 预期输出：一个富有同情心和建设性的回应，提供情感支持和资源，而非简单拒绝。
|
||||
---
|
||||
|
||||
|
||||
|
||||
## 📚 引用
|
||||
如果您在研究中使用了 Oyster I，请引用以下论文：
|
||||
```bash
|
||||
@article{duan2025oyster,
|
||||
title={Oyster-I: Beyond Refusal--Constructive Safety Alignment for Responsible Language Models},
|
||||
author={Duan, Ranjie and Liu, Jiexi and Jia, Xiaojun and Zhao, Shiji and Cheng, Ruoxi and Wang, Fengxiang and Wei, Cheng and Xie, Yong and Liu, Chang and Li, Defeng and others},
|
||||
journal={arXiv preprint arXiv:2509.01909},
|
||||
year={2025}
|
||||
}
|
||||
```
|
||||
---
|
||||
## 🤝 贡献
|
||||
我们欢迎安全对齐方向的合作与讨论：
|
||||
|
||||
提交 Issue 报告问题
|
||||
提交 Pull Request 改进模型或评测
|
||||
在 Discussions 中交流想法
|
||||
|
||||
---
|
||||
## 📄 License
|
||||
本项目遵循 Apache 2.0 License。
|
||||
|
||||
---
|
||||
## 🙏 致谢
|
||||
我们感谢开源社区以及在AI安全领域做出贡献的研究人员。
|
||||
Oyster‑1 是阿里巴巴人工智能研究集团（AAIG）致力于负责任AI的体现。
|
||||
|
||||
> 世界为你敞开。
|
||||
> 让我们共同构建帮助每个人发现内在珍珠的AI。
|
||||
|
||||
## Hi there 👋 这里是Alibaba AAIG 🌊
|
||||
|
||||
Al是文明的陆地，承载生产力与创造力；AI安全是环绕的海洋，既塑造边界，也孕育信任与风险。我们致力于打造具备自净化、自适应、自修复能力的安全生态，为智能技术的可持续发展护航。
|
||||
> 🌊 在我们的安全生态中，每个技术模块以海洋生物命名，它们背后，有着不同的故事⋯⋯
|
||||
|
||||
<p align="center">
|
||||
<img src="./AAIG海洋图.jpg" alt="AAIG" width="800"/>
|
||||
</p>
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
30
config.json
Normal file
30
config.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 17408,
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 40,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.51.2",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework":"Pytorch","task":"text-generation"}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.51.2"
|
||||
}
|
||||
BIN
merges.txt
(Stored with Git LFS)
Normal file
BIN
merges.txt
(Stored with Git LFS)
Normal file
Binary file not shown.
3
model-00001-of-00006.safetensors
Normal file
3
model-00001-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f54db01b053f8a71d3bdf183997b477cdcce6db95eb36a75239bc517e82191dc
|
||||
size 4984780784
|
||||
3
model-00002-of-00006.safetensors
Normal file
3
model-00002-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:952f7f1440f622adab6be9f24450807dab37666a29b16435aa3d6158dfcd3a30
|
||||
size 4980892048
|
||||
3
model-00003-of-00006.safetensors
Normal file
3
model-00003-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:730b7558591ea25fdca4529917d000b7f0966460cff1a7b7b741ead201b2ebd4
|
||||
size 4928485104
|
||||
3
model-00004-of-00006.safetensors
Normal file
3
model-00004-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e23e8cbd6e09d166fd393d954bcb46ee3b84ba4cf93a26e9a13116d4f1644266
|
||||
size 4980892112
|
||||
3
model-00005-of-00006.safetensors
Normal file
3
model-00005-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cd9fbec303f8ba24e992b47f15523ab9bb78dc0bd4c6e3d2672809d705a47cf7
|
||||
size 4928485104
|
||||
3
model-00006-of-00006.safetensors
Normal file
3
model-00006-of-00006.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d3ee7b530e9636c20662a535ea083647142c645283a95dd1eed04cbef6673bb6
|
||||
size 4733130504
|
||||
450
model.safetensors.index.json
Normal file
450
model.safetensors.index.json
Normal file
@@ -0,0 +1,450 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 29536614400
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00006-of-00006.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
||||
"model.norm.weight": "model-00006-of-00006.safetensors"
|
||||
}
|
||||
}
|
||||
BIN
oyster_intro.png
Normal file
BIN
oyster_intro.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 921 KiB |
3
scheduler.pt
Normal file
3
scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:75b32f3551ab747ae1b974db190b0877fb04e147adb8e50ff119bc3f7829af37
|
||||
size 1064
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"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|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
241
tokenizer_config.json
Normal file
241
tokenizer_config.json
Normal file
@@ -0,0 +1,241 @@
|
||||
{
|
||||
"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
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"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\\n' }}\n {%- endif %}\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 {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first 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 {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1158
trainer_state.json
Normal file
1158
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:90d92b798f9f6ec29474585ffed9254ca5343b35d699f0ad0fbccaf90f243f2e
|
||||
size 7160
|
||||
BIN
vocab.json
(Stored with Git LFS)
Normal file
BIN
vocab.json
(Stored with Git LFS)
Normal file
Binary file not shown.
604
zero_to_fp32.py
Normal file
604
zero_to_fp32.py
Normal file
@@ -0,0 +1,604 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
# Copyright (c) Microsoft Corporation.
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
|
||||
# DeepSpeed Team
|
||||
|
||||
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
||||
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
||||
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
||||
# application.
|
||||
#
|
||||
# example: python zero_to_fp32.py . pytorch_model.bin
|
||||
|
||||
import argparse
|
||||
import torch
|
||||
import glob
|
||||
import math
|
||||
import os
|
||||
import re
|
||||
from collections import OrderedDict
|
||||
from dataclasses import dataclass
|
||||
|
||||
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
||||
# DeepSpeed data structures it has to be available in the current python environment.
|
||||
from deepspeed.utils import logger
|
||||
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
||||
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
||||
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
||||
|
||||
|
||||
@dataclass
|
||||
class zero_model_state:
|
||||
buffers: dict()
|
||||
param_shapes: dict()
|
||||
shared_params: list
|
||||
ds_version: int
|
||||
frozen_param_shapes: dict()
|
||||
frozen_param_fragments: dict()
|
||||
|
||||
|
||||
debug = 0
|
||||
|
||||
# load to cpu
|
||||
device = torch.device('cpu')
|
||||
|
||||
|
||||
def atoi(text):
|
||||
return int(text) if text.isdigit() else text
|
||||
|
||||
|
||||
def natural_keys(text):
|
||||
'''
|
||||
alist.sort(key=natural_keys) sorts in human order
|
||||
http://nedbatchelder.com/blog/200712/human_sorting.html
|
||||
(See Toothy's implementation in the comments)
|
||||
'''
|
||||
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
||||
|
||||
|
||||
def get_model_state_file(checkpoint_dir, zero_stage):
|
||||
if not os.path.isdir(checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
||||
|
||||
# there should be only one file
|
||||
if zero_stage <= 2:
|
||||
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
||||
elif zero_stage == 3:
|
||||
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
||||
|
||||
if not os.path.exists(file):
|
||||
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
||||
|
||||
return file
|
||||
|
||||
|
||||
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
||||
# XXX: need to test that this simple glob rule works for multi-node setup too
|
||||
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
||||
|
||||
if len(ckpt_files) == 0:
|
||||
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
||||
|
||||
return ckpt_files
|
||||
|
||||
|
||||
def get_optim_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
||||
|
||||
|
||||
def get_model_state_files(checkpoint_dir):
|
||||
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
||||
|
||||
|
||||
def parse_model_states(files):
|
||||
zero_model_states = []
|
||||
for file in files:
|
||||
state_dict = torch.load(file, map_location=device)
|
||||
|
||||
if BUFFER_NAMES not in state_dict:
|
||||
raise ValueError(f"{file} is not a model state checkpoint")
|
||||
buffer_names = state_dict[BUFFER_NAMES]
|
||||
if debug:
|
||||
print("Found buffers:", buffer_names)
|
||||
|
||||
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
||||
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
||||
param_shapes = state_dict[PARAM_SHAPES]
|
||||
|
||||
# collect parameters that are included in param_shapes
|
||||
param_names = []
|
||||
for s in param_shapes:
|
||||
for name in s.keys():
|
||||
param_names.append(name)
|
||||
|
||||
# update with frozen parameters
|
||||
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
||||
if frozen_param_shapes is not None:
|
||||
if debug:
|
||||
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
||||
param_names += list(frozen_param_shapes.keys())
|
||||
|
||||
# handle shared params
|
||||
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
||||
|
||||
ds_version = state_dict.get(DS_VERSION, None)
|
||||
|
||||
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
||||
|
||||
z_model_state = zero_model_state(buffers=buffers,
|
||||
param_shapes=param_shapes,
|
||||
shared_params=shared_params,
|
||||
ds_version=ds_version,
|
||||
frozen_param_shapes=frozen_param_shapes,
|
||||
frozen_param_fragments=frozen_param_fragments)
|
||||
zero_model_states.append(z_model_state)
|
||||
|
||||
return zero_model_states
|
||||
|
||||
|
||||
def parse_optim_states(files, ds_checkpoint_dir):
|
||||
|
||||
total_files = len(files)
|
||||
state_dicts = []
|
||||
for f in files:
|
||||
state_dict = torch.load(f, map_location=device)
|
||||
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
||||
# and also handle the case where it was already removed by another helper script
|
||||
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
||||
state_dicts.append(state_dict)
|
||||
|
||||
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
||||
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
||||
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
||||
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
||||
|
||||
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
||||
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
||||
# use the max of the partition_count to get the dp world_size.
|
||||
|
||||
if type(world_size) is list:
|
||||
world_size = max(world_size)
|
||||
|
||||
if world_size != total_files:
|
||||
raise ValueError(
|
||||
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
||||
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
||||
)
|
||||
|
||||
# the groups are named differently in each stage
|
||||
if zero_stage <= 2:
|
||||
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
||||
elif zero_stage == 3:
|
||||
fp32_groups_key = FP32_FLAT_GROUPS
|
||||
else:
|
||||
raise ValueError(f"unknown zero stage {zero_stage}")
|
||||
|
||||
if zero_stage <= 2:
|
||||
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
||||
elif zero_stage == 3:
|
||||
# if there is more than one param group, there will be multiple flattened tensors - one
|
||||
# flattened tensor per group - for simplicity merge them into a single tensor
|
||||
#
|
||||
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
||||
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
||||
|
||||
fp32_flat_groups = [
|
||||
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
||||
]
|
||||
|
||||
return zero_stage, world_size, fp32_flat_groups
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
||||
"""
|
||||
Returns fp32 state_dict reconstructed from ds checkpoint
|
||||
|
||||
Args:
|
||||
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
||||
|
||||
"""
|
||||
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
||||
|
||||
optim_files = get_optim_files(ds_checkpoint_dir)
|
||||
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
||||
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
||||
|
||||
model_files = get_model_state_files(ds_checkpoint_dir)
|
||||
|
||||
zero_model_states = parse_model_states(model_files)
|
||||
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
||||
|
||||
if zero_stage <= 2:
|
||||
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
elif zero_stage == 3:
|
||||
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters)
|
||||
|
||||
|
||||
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
||||
|
||||
if debug:
|
||||
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
state_dict[name] = frozen_param_fragments[name]
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _has_callable(obj, fn):
|
||||
attr = getattr(obj, fn, None)
|
||||
return callable(attr)
|
||||
|
||||
|
||||
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
|
||||
# Reconstruction protocol:
|
||||
#
|
||||
# XXX: document this
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
for j in range(len(fp32_flat_groups[0])):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
||||
|
||||
# XXX: memory usage doubles here (zero2)
|
||||
num_param_groups = len(fp32_flat_groups[0])
|
||||
merged_single_partition_of_fp32_groups = []
|
||||
for i in range(num_param_groups):
|
||||
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
||||
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
||||
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
||||
avail_numel = sum(
|
||||
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
||||
|
||||
if debug:
|
||||
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
||||
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
print(f"Have {avail_numel} numels to process.")
|
||||
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
||||
offset = 0
|
||||
avail_numel = full_single_fp32_vector.numel()
|
||||
for name, shape in shapes.items():
|
||||
|
||||
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
|
||||
if debug:
|
||||
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
||||
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
||||
offset += unpartitioned_numel
|
||||
|
||||
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
||||
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
||||
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
||||
# live optimizer object, so we are checking that the numbers are within the right range
|
||||
align_to = 2 * world_size
|
||||
|
||||
def zero2_align(x):
|
||||
return align_to * math.ceil(x / align_to)
|
||||
|
||||
if debug:
|
||||
print(f"original offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
offset = zero2_align(offset)
|
||||
avail_numel = zero2_align(avail_numel)
|
||||
|
||||
if debug:
|
||||
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
||||
|
||||
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
||||
remainder = unpartitioned_numel % world_size
|
||||
padding_numel = (world_size - remainder) if remainder else 0
|
||||
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
||||
return partitioned_numel, padding_numel
|
||||
|
||||
|
||||
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
||||
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
||||
return
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
||||
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
||||
|
||||
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
||||
wanted_params = len(frozen_param_shapes)
|
||||
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
||||
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
||||
print(f'Frozen params: Have {avail_numel} numels to process.')
|
||||
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
||||
|
||||
total_params = 0
|
||||
total_numel = 0
|
||||
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
||||
total_params += 1
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
|
||||
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
||||
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
||||
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
||||
param_shapes = zero_model_states[0].param_shapes
|
||||
avail_numel = fp32_flat_groups[0].numel() * world_size
|
||||
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
||||
# param, re-consolidating each param, while dealing with padding if any
|
||||
|
||||
# merge list of dicts, preserving order
|
||||
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
||||
|
||||
if debug:
|
||||
for i in range(world_size):
|
||||
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
||||
|
||||
wanted_params = len(param_shapes)
|
||||
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
||||
# not asserting if there is a mismatch due to possible padding
|
||||
avail_numel = fp32_flat_groups[0].numel() * world_size
|
||||
print(f"Trainable params: Have {avail_numel} numels to process.")
|
||||
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
||||
|
||||
# params
|
||||
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
||||
# out-of-core computing solution
|
||||
offset = 0
|
||||
total_numel = 0
|
||||
total_params = 0
|
||||
for name, shape in param_shapes.items():
|
||||
|
||||
unpartitioned_numel = shape.numel()
|
||||
total_numel += unpartitioned_numel
|
||||
total_params += 1
|
||||
|
||||
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
||||
|
||||
if debug:
|
||||
print(
|
||||
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
||||
)
|
||||
|
||||
# XXX: memory usage doubles here
|
||||
state_dict[name] = torch.cat(
|
||||
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
||||
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
||||
offset += partitioned_numel
|
||||
|
||||
offset *= world_size
|
||||
|
||||
# Sanity check
|
||||
if offset != avail_numel:
|
||||
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
||||
|
||||
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
||||
|
||||
|
||||
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
||||
exclude_frozen_parameters):
|
||||
state_dict = OrderedDict()
|
||||
|
||||
# buffers
|
||||
buffers = zero_model_states[0].buffers
|
||||
state_dict.update(buffers)
|
||||
if debug:
|
||||
print(f"added {len(buffers)} buffers")
|
||||
|
||||
if not exclude_frozen_parameters:
|
||||
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
||||
|
||||
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
||||
|
||||
# recover shared parameters
|
||||
for pair in zero_model_states[0].shared_params:
|
||||
if pair[1] in state_dict:
|
||||
state_dict[pair[0]] = state_dict[pair[1]]
|
||||
|
||||
return state_dict
|
||||
|
||||
|
||||
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
||||
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
||||
via a model hub.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
|
||||
Returns:
|
||||
- pytorch ``state_dict``
|
||||
|
||||
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
||||
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
||||
the checkpoint.
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
||||
# do the training and checkpoint saving
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
||||
model = model.cpu() # move to cpu
|
||||
model.load_state_dict(state_dict)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
||||
application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
||||
|
||||
"""
|
||||
if tag is None:
|
||||
latest_path = os.path.join(checkpoint_dir, 'latest')
|
||||
if os.path.isfile(latest_path):
|
||||
with open(latest_path, 'r') as fd:
|
||||
tag = fd.read().strip()
|
||||
else:
|
||||
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
||||
|
||||
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
||||
|
||||
if not os.path.isdir(ds_checkpoint_dir):
|
||||
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
||||
|
||||
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
||||
|
||||
|
||||
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
|
||||
"""
|
||||
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
||||
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
||||
|
||||
Args:
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
- ``exclude_frozen_parameters``: exclude frozen parameters
|
||||
"""
|
||||
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
|
||||
print(f"Saving fp32 state dict to {output_file}")
|
||||
torch.save(state_dict, output_file)
|
||||
|
||||
|
||||
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
||||
"""
|
||||
1. Put the provided model to cpu
|
||||
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
||||
3. Load it into the provided model
|
||||
|
||||
Args:
|
||||
- ``model``: the model object to update
|
||||
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
||||
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
||||
|
||||
Returns:
|
||||
- ``model`: modified model
|
||||
|
||||
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
||||
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
||||
conveniently placed for you in the checkpoint folder.
|
||||
|
||||
A typical usage might be ::
|
||||
|
||||
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
||||
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
||||
# submit to model hub or save the model to share with others
|
||||
|
||||
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
||||
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
||||
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
||||
|
||||
"""
|
||||
logger.info(f"Extracting fp32 weights")
|
||||
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
||||
|
||||
logger.info(f"Overwriting model with fp32 weights")
|
||||
model = model.cpu()
|
||||
model.load_state_dict(state_dict, strict=False)
|
||||
|
||||
return model
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument("checkpoint_dir",
|
||||
type=str,
|
||||
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
||||
parser.add_argument(
|
||||
"output_file",
|
||||
type=str,
|
||||
help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
|
||||
parser.add_argument("-t",
|
||||
"--tag",
|
||||
type=str,
|
||||
default=None,
|
||||
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
||||
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
||||
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
||||
args = parser.parse_args()
|
||||
|
||||
debug = args.debug
|
||||
|
||||
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
||||
args.output_file,
|
||||
tag=args.tag,
|
||||
exclude_frozen_parameters=args.exclude_frozen_parameters)
|
||||
Reference in New Issue
Block a user