From 18ba0cc6e50a58b72c5dcc7a8cb952d5c6f9f2c1 Mon Sep 17 00:00:00 2001
From: xxl <505279206@qq.com>
Date: Mon, 6 Jan 2025 11:54:08 +0800
Subject: [PATCH] first commit
---
README.md | 83 +++++++++++++++++++++++++++++++-
config.json | 3 ++
generation_config.json | 3 ++
model-00001-of-00004.safetensors | 3 ++
model-00002-of-00004.safetensors | 3 ++
model-00003-of-00004.safetensors | 3 ++
model-00004-of-00004.safetensors | 3 ++
model.safetensors.index.json | 3 ++
special_tokens_map.json | 3 ++
tokenizer.json | 3 ++
tokenizer_config.json | 3 ++
11 files changed, 111 insertions(+), 2 deletions(-)
create mode 100644 config.json
create mode 100644 generation_config.json
create mode 100644 model-00001-of-00004.safetensors
create mode 100644 model-00002-of-00004.safetensors
create mode 100644 model-00003-of-00004.safetensors
create mode 100644 model-00004-of-00004.safetensors
create mode 100644 model.safetensors.index.json
create mode 100644 special_tokens_map.json
create mode 100644 tokenizer.json
create mode 100644 tokenizer_config.json
diff --git a/README.md b/README.md
index b7a3a3a..57eba2e 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,82 @@
-# HuatuoGPT-o1-8B_a14191238398210048235517
+---
+license: apache-2.0
+datasets:
+- FreedomIntelligence/medical-o1-reasoning-SFT
+- FreedomIntelligence/medical-o1-verifiable-problem
+language:
+- en
+base_model:
+- meta-llama/Llama-3.1-8B-Instruct
+pipeline_tag: text-generation
+tags:
+- medical
+---
+
+
+
+ HuatuoGPT-o1-8B
+
+
+
+
+
+# Introduction
+**HuatuoGPT-o1** is a medical LLM designed for advanced medical reasoning. It generates a complex thought process, reflecting and refining its reasoning, before providing a final response.
+
+For more information, visit our GitHub repository:
+[https://github.com/FreedomIntelligence/HuatuoGPT-o1](https://github.com/FreedomIntelligence/HuatuoGPT-o1).
+
+# Model Info
+| | Backbone | Supported Languages | Link |
+| -------------------- | ------------ | ----- | --------------------------------------------------------------------- |
+| **HuatuoGPT-o1-8B** | LLaMA-3.1-8B | English | [HF Link](https://huggingface.co/FreedomIntelligence/HuatuoGPT-o1-8B) |
+| **HuatuoGPT-o1-70B** | LLaMA-3.1-70B | English | [HF Link](https://huggingface.co/FreedomIntelligence/HuatuoGPT-o1-70B) |
+| **HuatuoGPT-o1-7B** | Qwen2.5-7B | English & Chinese | [HF Link](https://huggingface.co/FreedomIntelligence/HuatuoGPT-o1-7B) |
+| **HuatuoGPT-o1-72B** | Qwen2.5-72B | English & Chinese | [HF Link](https://huggingface.co/FreedomIntelligence/HuatuoGPT-o1-72B) |
+
+
+
+# Usage
+You can use HuatuoGPT-o1 in the same way as `Llama-3.1-8B-Instruct`. You can deploy it with tools like [vllm](https://github.com/vllm-project/vllm) or [Sglang](https://github.com/sgl-project/sglang), or perform direct inference:
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("FreedomIntelligence/HuatuoGPT-o1-8B",torch_dtype="auto",device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("FreedomIntelligence/HuatuoGPT-o1-8B")
+
+input_text = "How to stop a cough?"
+messages = [{"role": "user", "content": input_text}]
+
+inputs = tokenizer(tokenizer.apply_chat_template(messages, tokenize=False,add_generation_prompt=True
+), return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=2048)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+HuatuoGPT-o1 adopts a *thinks-before-it-answers* approach, with outputs formatted as:
+
+```
+## Thinking
+[Reasoning process]
+
+## Final Response
+[Output]
+```
+
+# 📖 Citation
+```
+@misc{chen2024huatuogpto1medicalcomplexreasoning,
+ title={HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs},
+ author={Junying Chen and Zhenyang Cai and Ke Ji and Xidong Wang and Wanlong Liu and Rongsheng Wang and Jianye Hou and Benyou Wang},
+ year={2024},
+ eprint={2412.18925},
+ archivePrefix={arXiv},
+ primaryClass={cs.CL},
+ url={https://arxiv.org/abs/2412.18925},
+}
+```
+
+
-HuatuoGPT-o1-8B
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..9fffd33
--- /dev/null
+++ b/config.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c0f840a9431158ee67c9090c6eaca9bd2f4c299946755cb65fb61c311558f75
+size 875
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..378edcd
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e4974aa25a0663629ea355eda8c1e25cba53885e2fff319450d0d5af87bc80
+size 213
diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors
new file mode 100644
index 0000000..d72888e
--- /dev/null
+++ b/model-00001-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aff2113c01a04389ed40261f1f192a561b9d482b7ac4ef765004433635734f2
+size 4976698672
diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors
new file mode 100644
index 0000000..e26218b
--- /dev/null
+++ b/model-00002-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e460e5bcbe969138d0d632cc4f97c2f21c71a17dd5835e8143b0a06ae43f0e7b
+size 4999802720
diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors
new file mode 100644
index 0000000..64eea54
--- /dev/null
+++ b/model-00003-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0af645dfc9a1c9a30abcbf4378946ffc89723f18934b719b07daf8f18718b9c
+size 4915916176
diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors
new file mode 100644
index 0000000..92964ad
--- /dev/null
+++ b/model-00004-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11982e89782a6e3c262d99676e3dd36c47091005a1af24734335cd4d568b1c3c
+size 1168138808
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..a054aad
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:146776fce3f6db1103aa6f249e65ee5544c5923ce6f971b092eee79aa6e5d37b
+size 23950
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..f395329
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a6d7fa83a01e8192333cd7b848541159709c4b206739071980432612f807807
+size 444
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..1c1d8d5
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..2bdb152
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f8f588a3a36a8c0d17995caf083625c92480e747c9cadd3192297c59bea4e5
+size 55385