Instructions to use minpeter/Voxtral-Mini-3B-Text-2507-hf-heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use minpeter/Voxtral-Mini-3B-Text-2507-hf-heretic with Transformers:

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

pipe = pipeline("text-generation", model="minpeter/Voxtral-Mini-3B-Text-2507-hf-heretic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("minpeter/Voxtral-Mini-3B-Text-2507-hf-heretic")
model = AutoModelForCausalLM.from_pretrained("minpeter/Voxtral-Mini-3B-Text-2507-hf-heretic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
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

vLLM

How to use minpeter/Voxtral-Mini-3B-Text-2507-hf-heretic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "minpeter/Voxtral-Mini-3B-Text-2507-hf-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": "minpeter/Voxtral-Mini-3B-Text-2507-hf-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/minpeter/Voxtral-Mini-3B-Text-2507-hf-heretic

SGLang

How to use minpeter/Voxtral-Mini-3B-Text-2507-hf-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 "minpeter/Voxtral-Mini-3B-Text-2507-hf-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": "minpeter/Voxtral-Mini-3B-Text-2507-hf-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "minpeter/Voxtral-Mini-3B-Text-2507-hf-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": "minpeter/Voxtral-Mini-3B-Text-2507-hf-heretic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use minpeter/Voxtral-Mini-3B-Text-2507-hf-heretic with Docker Model Runner:
```
docker model run hf.co/minpeter/Voxtral-Mini-3B-Text-2507-hf-heretic
```

This is a decensored version of minpeter/Voxtral-Mini-3B-Text-2507-hf, made using Heretic v1.0.1

Abliteration parameters

Parameter	Value
direction_index	14.47
attn.o_proj.max_weight	1.27
attn.o_proj.max_weight_position	17.46
attn.o_proj.min_weight	0.98
attn.o_proj.min_weight_distance	8.89
mlp.down_proj.max_weight	1.11
mlp.down_proj.max_weight_position	21.50
mlp.down_proj.min_weight	1.02
mlp.down_proj.min_weight_distance	15.14

Performance

Metric	This model	Original model (minpeter/Voxtral-Mini-3B-Text-2507-hf)
KL divergence	0.06	0 (by definition)
Refusals	4/100	99/100

This is a version of Voxtral-Mini-3B-2507 that removes the whisper feature and retains only the language model functionality.
It is similar to the unreleased "Ministral-3B-Instruct" model.

Downloads last month: 7

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for minpeter/Voxtral-Mini-3B-Text-2507-hf-heretic

Base model

mistralai/Voxtral-Mini-3B-2507

Finetuned

(17)

this model