Instructions to use ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic")
model = AutoModelForCausalLM.from_pretrained("ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic

SGLang

How to use ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic with Docker Model Runner:
```
docker model run hf.co/ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

A decensored version of Joker-sxj/Qwen2.5-3B-instruct-medical-finetuned, made using Heretic v1.2.0

	Qwen2.5-3B-instruct-medical-finetuned-Heretic	Original model (Joker-sxj/Qwen2.5-3B-instruct-medical-finetuned)
Refusals	4/100	79/100
KL divergence	0.0126	0 (by definition)

Heretic Abliteration parameters

Parameter	Value
direction_index	24.64
attn.o_proj.max_weight	1.32
attn.o_proj.max_weight_position	24.56
attn.o_proj.min_weight	0.58
attn.o_proj.min_weight_distance	19.88
mlp.down_proj.max_weight	0.96
mlp.down_proj.max_weight_position	23.74
mlp.down_proj.min_weight	0.22
mlp.down_proj.min_weight_distance	17.35

Heretic config used

dtypes: "bfloat16"

max_response_length: 384

kl_divergence_scale: 1.0
kl_divergence_target: 0.015

orthogonalize_direction: true

row_normalization: "full"
full_normalization_lora_rank: 3

winsorization_quantile: 0.975

n_trials: 200
n_startup_trials: 40

refusal_markers:
  # defaults plus the following:
   "unsafe",
   "unethical",
   "ethical boundaries",
   "cannot assist",
   "can't assist",
   "not able to",
   "not appropriate",
   "against policies",

system_prompt: "You are a helpful assistant."

模型经过医疗数据集微调后，已初步具备推理能力，可以进行基础的问诊，且文本的质量BLEU比原模型更优。

After fine-tuning on a medical dataset, the model has initially acquired reasoning capabilities and can conduct basic consultations, with the textual quality achieving a better BLEU score than the original model.

Downloads last month: 10

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Finetuned

Joker-sxj/Qwen2.5-3B-instruct-medical-finetuned

Finetuned

(2)

this model

Quantizations

2 models

ChiKoi7
/

Qwen2.5-3B-instruct-medical-finetuned-Heretic

A decensored version of Joker-sxj/Qwen2.5-3B-instruct-medical-finetuned, made using Heretic v1.2.0

Heretic Abliteration parameters

Heretic config used

Model tree for ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic

Dataset used to train ChiKoi7/Qwen2.5-3B-instruct-medical-finetuned-Heretic