From 2f38cc54ccaef0c17199634776c9cd977ef4ae3c Mon Sep 17 00:00:00 2001
From: ModelHub XC <noreply@modelhub.org.cn>
Date: Sun, 5 Jul 2026 22:42:13 +0800
Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?=
 =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?=
 =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Model: QuantFactory/HuatuoGPT-o1-8B-GGUF
Source: Original Platform
---
 .gitattributes              | 49 +++++++++++++++++++
 HuatuoGPT-o1-8B.Q2_K.gguf   |  3 ++
 HuatuoGPT-o1-8B.Q3_K_L.gguf |  3 ++
 HuatuoGPT-o1-8B.Q3_K_M.gguf |  3 ++
 HuatuoGPT-o1-8B.Q3_K_S.gguf |  3 ++
 HuatuoGPT-o1-8B.Q4_0.gguf   |  3 ++
 HuatuoGPT-o1-8B.Q4_1.gguf   |  3 ++
 HuatuoGPT-o1-8B.Q4_K_M.gguf |  3 ++
 HuatuoGPT-o1-8B.Q4_K_S.gguf |  3 ++
 HuatuoGPT-o1-8B.Q5_0.gguf   |  3 ++
 HuatuoGPT-o1-8B.Q5_1.gguf   |  3 ++
 HuatuoGPT-o1-8B.Q5_K_M.gguf |  3 ++
 HuatuoGPT-o1-8B.Q5_K_S.gguf |  3 ++
 HuatuoGPT-o1-8B.Q6_K.gguf   |  3 ++
 HuatuoGPT-o1-8B.Q8_0.gguf   |  3 ++
 README.md                   | 95 +++++++++++++++++++++++++++++++++++++
 configuration.json          |  1 +
 17 files changed, 187 insertions(+)
 create mode 100644 .gitattributes
 create mode 100644 HuatuoGPT-o1-8B.Q2_K.gguf
 create mode 100644 HuatuoGPT-o1-8B.Q3_K_L.gguf
 create mode 100644 HuatuoGPT-o1-8B.Q3_K_M.gguf
 create mode 100644 HuatuoGPT-o1-8B.Q3_K_S.gguf
 create mode 100644 HuatuoGPT-o1-8B.Q4_0.gguf
 create mode 100644 HuatuoGPT-o1-8B.Q4_1.gguf
 create mode 100644 HuatuoGPT-o1-8B.Q4_K_M.gguf
 create mode 100644 HuatuoGPT-o1-8B.Q4_K_S.gguf
 create mode 100644 HuatuoGPT-o1-8B.Q5_0.gguf
 create mode 100644 HuatuoGPT-o1-8B.Q5_1.gguf
 create mode 100644 HuatuoGPT-o1-8B.Q5_K_M.gguf
 create mode 100644 HuatuoGPT-o1-8B.Q5_K_S.gguf
 create mode 100644 HuatuoGPT-o1-8B.Q6_K.gguf
 create mode 100644 HuatuoGPT-o1-8B.Q8_0.gguf
 create mode 100644 README.md
 create mode 100644 configuration.json

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..ae5d415
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,49 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+HuatuoGPT-o1-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+HuatuoGPT-o1-8B.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+HuatuoGPT-o1-8B.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+HuatuoGPT-o1-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+HuatuoGPT-o1-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+HuatuoGPT-o1-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+HuatuoGPT-o1-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+HuatuoGPT-o1-8B.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+HuatuoGPT-o1-8B.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+HuatuoGPT-o1-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+HuatuoGPT-o1-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+HuatuoGPT-o1-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+HuatuoGPT-o1-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+HuatuoGPT-o1-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
diff --git a/HuatuoGPT-o1-8B.Q2_K.gguf b/HuatuoGPT-o1-8B.Q2_K.gguf
new file mode 100644
index 0000000..42ba395
--- /dev/null
+++ b/HuatuoGPT-o1-8B.Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:705712ed0e05c08be836ca2e0c5fffeac6c0ac80460ba42dc8278ca9cd191639
+size 3179136832
diff --git a/HuatuoGPT-o1-8B.Q3_K_L.gguf b/HuatuoGPT-o1-8B.Q3_K_L.gguf
new file mode 100644
index 0000000..d41b4d2
--- /dev/null
+++ b/HuatuoGPT-o1-8B.Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e579bdf6a2bda5889c2cf12dc1eb28e49459a9f2fc917565f0a2de373d49666f
+size 4321961792
diff --git a/HuatuoGPT-o1-8B.Q3_K_M.gguf b/HuatuoGPT-o1-8B.Q3_K_M.gguf
new file mode 100644
index 0000000..334e017
--- /dev/null
+++ b/HuatuoGPT-o1-8B.Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6adc4f26562c93905c8354010ea528e4daa872520e221176bbf365bee0dcf1d7
+size 4018923328
diff --git a/HuatuoGPT-o1-8B.Q3_K_S.gguf b/HuatuoGPT-o1-8B.Q3_K_S.gguf
new file mode 100644
index 0000000..faf9ad0
--- /dev/null
+++ b/HuatuoGPT-o1-8B.Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e0266820a2a14c09e5aab296a95c52ff148d4443ccd317ff21b93a56d0bb3a
+size 3664504640
diff --git a/HuatuoGPT-o1-8B.Q4_0.gguf b/HuatuoGPT-o1-8B.Q4_0.gguf
new file mode 100644
index 0000000..aaca9b5
--- /dev/null
+++ b/HuatuoGPT-o1-8B.Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddc9bcf0edd489204c726691fa7c6c3110ce9d7a4148b2eb5a0a9fa6d54de75a
+size 4661217088
diff --git a/HuatuoGPT-o1-8B.Q4_1.gguf b/HuatuoGPT-o1-8B.Q4_1.gguf
new file mode 100644
index 0000000..88e67e8
--- /dev/null
+++ b/HuatuoGPT-o1-8B.Q4_1.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25b942fb66df1a433e872afdbe1e1e8e00e8436280ea91ee70592d22707d808c
+size 5130258240
diff --git a/HuatuoGPT-o1-8B.Q4_K_M.gguf b/HuatuoGPT-o1-8B.Q4_K_M.gguf
new file mode 100644
index 0000000..1e38c57
--- /dev/null
+++ b/HuatuoGPT-o1-8B.Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71f69a0eecd656db48b494a7bdcdbca4aa14109f40de729055ab5c8b0a6d5f81
+size 4920739648
diff --git a/HuatuoGPT-o1-8B.Q4_K_S.gguf b/HuatuoGPT-o1-8B.Q4_K_S.gguf
new file mode 100644
index 0000000..64e377a
--- /dev/null
+++ b/HuatuoGPT-o1-8B.Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1cc5128be314bbe7cc26eb654c691ae13c7c65169ef6339bb1337e4c76ab99
+size 4692674368
diff --git a/HuatuoGPT-o1-8B.Q5_0.gguf b/HuatuoGPT-o1-8B.Q5_0.gguf
new file mode 100644
index 0000000..9cca269
--- /dev/null
+++ b/HuatuoGPT-o1-8B.Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b10ae074160b867309bccd9934614361ac5258380545004e5ec6902c736df0bc
+size 5599299392
diff --git a/HuatuoGPT-o1-8B.Q5_1.gguf b/HuatuoGPT-o1-8B.Q5_1.gguf
new file mode 100644
index 0000000..8160a8a
--- /dev/null
+++ b/HuatuoGPT-o1-8B.Q5_1.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b44f5e840863bf844c21acc2e57dfda2f9d650f712535845e993dc66ac553dea
+size 6068340544
diff --git a/HuatuoGPT-o1-8B.Q5_K_M.gguf b/HuatuoGPT-o1-8B.Q5_K_M.gguf
new file mode 100644
index 0000000..f0f4bfc
--- /dev/null
+++ b/HuatuoGPT-o1-8B.Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ddfb9f73dbc7a69cf999acb9943c0a12edb49b4ba7a460053db8095d3f16c0
+size 5732992832
diff --git a/HuatuoGPT-o1-8B.Q5_K_S.gguf b/HuatuoGPT-o1-8B.Q5_K_S.gguf
new file mode 100644
index 0000000..236688b
--- /dev/null
+++ b/HuatuoGPT-o1-8B.Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6187ef4cf7da6ce0e03a5b8058f6c3c0dc1f51ae965f7567205fb868ebbbd9
+size 5599299392
diff --git a/HuatuoGPT-o1-8B.Q6_K.gguf b/HuatuoGPT-o1-8B.Q6_K.gguf
new file mode 100644
index 0000000..856a19b
--- /dev/null
+++ b/HuatuoGPT-o1-8B.Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27c546bbc1329df3a7b84068871586e600ce5f3f7e35d9f9aa050276b99c6523
+size 6596011840
diff --git a/HuatuoGPT-o1-8B.Q8_0.gguf b/HuatuoGPT-o1-8B.Q8_0.gguf
new file mode 100644
index 0000000..8981f7a
--- /dev/null
+++ b/HuatuoGPT-o1-8B.Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ca330c5508e9da3c54392f7776a92c8a652a4c5eba477c5fea51bf156a762
+size 8540776256
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..85238df
--- /dev/null
+++ b/README.md
@@ -0,0 +1,95 @@
+
+---
+
+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
+
+---
+
+[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)
+
+
+# QuantFactory/HuatuoGPT-o1-8B-GGUF
+This is quantized version of [FreedomIntelligence/HuatuoGPT-o1-8B](https://huggingface.co/FreedomIntelligence/HuatuoGPT-o1-8B) created using llama.cpp
+
+# Original Model Card
+
+
+<div align="center">
+<h1>
+  HuatuoGPT-o1-8B
+</h1>
+</div>
+
+<div align="center">
+<a href="https://github.com/FreedomIntelligence/HuatuoGPT-o1" target="_blank">GitHub</a> | <a href="https://arxiv.org/pdf/2412.18925" target="_blank">Paper</a>
+</div>
+
+# <span>Introduction</span>
+**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).
+
+# <span>Model Info</span>
+|                      | 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) |
+
+
+
+# <span>Usage</span>
+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]
+```
+
+# <span>📖 Citation</span>
+```
+@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}, 
+}
+```
+
+
+
+
diff --git a/configuration.json b/configuration.json
new file mode 100644
index 0000000..bbeeda1
--- /dev/null
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
\ No newline at end of file