File size: 4,212 Bytes
d7307fd
 
 
 
 
55b39e4
d7307fd
 
 
 
 
a6ca063
 
 
d7307fd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11c92aa
d7307fd
 
 
 
 
11c92aa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a6ca063
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
---
license: apache-2.0
datasets:
- FreedomIntelligence/medical-o1-reasoning-SFT
language:
- zh
base_model:
- unsloth/DeepSeek-R1-Distill-Llama-8B
pipeline_tag: text-generation
tags:
- unsloth
- deepseek
- rola
- sft
---

# DeepSeek-R1 Medical Reasoning Model

This repository contains a **fine-tuned medical reasoning model** based on  
[DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/unsloth/DeepSeek-R1-Distill-Llama-8B)  
and trained on the [medical-o1-reasoning-SFT](https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT) dataset.

⚠️ **The uploaded file (`unsloth.Q8_0.gguf`) contains quantized weights** for efficient inference.

---

## 🔍 Model Overview

- **Base Model**: unsloth/DeepSeek-R1-Distill-Llama-8B  
- **Training Method**: SFT (Supervised Fine-Tuning)  
- **Domain**: Medical reasoning and clinical knowledge  
- **Language**: English  
- **Quantization**: Q8_0 (gguf format for efficient inference)  

---

## 📚 Training Data

The model was fine-tuned on:

- **Dataset**: `FreedomIntelligence/medical-o1-reasoning-SFT`  
- **Language**: English  
- **Task**: Medical reasoning, clinical question-answering  

---

## 🚀 Usage Example

> **Note:** The model is stored in `.gguf` format (quantized). You can load it using `unsloth` library.

```python
from unsloth import FastLanguageModel
import torch

# Load the quantized GGUF model
model, tokenizer = FastLanguageModel.from_pretrained(
    "./unsloth.Q8_0.gguf",
    max_seq_length=2048,
    load_in_8bit=True,  # optional depending on quantization
)

FastLanguageModel.for_inference(model)

def generate(model, prompt, max_new_tokens=200):
    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_new_tokens=max_new_tokens,
            do_sample=True,
            temperature=0.7,
            top_p=0.9,
        )

    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Example prompt
prompt = """### Instruction:
"一个患有急性阑尾炎的病人已经发病5天,腹痛稍有减轻但仍然发热,在体检时发现右下腹有压痛的包块,此时应如何处理?"
### Response:
"""

print(generate(model, prompt))


<think>
这个病人已经有五天的急性阑尾炎了,腹痛虽然有所缓解,但他还是发烧,这让我有点担心。再看看他的体检结果,右下腹有压痛的包块,这就让我更有理由担心。嗯,既然有包块,而且病人还是发烧,应该是急性阑尾炎的急性症状。

想到这些,我觉得应该马上处理一下。最好的办法就是立即做腹部超声检查,看看包块的具体情况。超声检查可以帮助我们了解包块的位置、大小、形态以及周围组织的状态,这些信息对治疗非常重要。

哦,对了,包块如果是液体的,可能就不需要手术了。我们可以通过超声检查来确定这一点。这样就能避免不必要的手术创伤。

但是如果包块是固体的,特别是当它对周围组织有压迫作用时,手术就变得必要了。我们需要根据包块的具体情况来决定是否手术。

另外,包块的形态和位置也会影响手术的选择。我们需要根据这些因素来制定具体的手术方案。

嗯,总结一下,首先必须做一个腹部超声检查,确定包块的类型和具体情况。只有在确认包块是固体并且对周围组织有压迫作用的时候,才需要考虑手术。

好的,这个思路看起来很合理。现在就要把这些想法转化为具体的处理步骤。
</think>
在这种情况下,建议首先进行腹部超声检查,以确定包块的类型和具体情况。根据检查结果:

1. **如果包块是液体性包块**:通常不需要手术。可以通过药物治疗缓解症状,随后观察病情缓解情况。

2. **如果包块是固体性包块并且对周围组织有压迫作用**:这时手术就变得必要了。通常需要进行包块切除术,以解除压迫,缓解症状。

请尽快安排进行腹部超声检查,并根据检查结果制定最合适的手术方案。<|end▁of▁sentence|>