Instructions to use olaverse/MIST-Mini-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use olaverse/MIST-Mini-8B with Transformers:

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

pipe = pipeline("text-generation", model="olaverse/MIST-Mini-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("olaverse/MIST-Mini-8B")
model = AutoModelForCausalLM.from_pretrained("olaverse/MIST-Mini-8B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use olaverse/MIST-Mini-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "olaverse/MIST-Mini-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "olaverse/MIST-Mini-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/olaverse/MIST-Mini-8B

SGLang

How to use olaverse/MIST-Mini-8B 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 "olaverse/MIST-Mini-8B" \
    --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": "olaverse/MIST-Mini-8B",
		"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 "olaverse/MIST-Mini-8B" \
        --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": "olaverse/MIST-Mini-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use olaverse/MIST-Mini-8B with Docker Model Runner:
```
docker model run hf.co/olaverse/MIST-Mini-8B
```

olumideola commited on 1 day ago

Commit

cb2c02b

verified ·

1 Parent(s): 1a62942

Update README.md

Browse files

Files changed (1) hide show

README.md +29 -0

README.md CHANGED Viewed

@@ -88,6 +88,35 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ---
 ## License
 [Llama 3.1 Community License](https://llama.meta.com/llama3/license/)

 ---
+## Recommended Generation Settings
+These settings were verified through testing. Without `repetition_penalty`
+and `min_p` the model will ramble and not stop cleanly.
+```python
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=1024,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.95,
+    min_p=0.05,
+    repetition_penalty=1.5,
+    eos_token_id=[128040, 128009, 128001],
+    pad_token_id=128001,
+)
+```
+### Stop Tokens
+This model's ChatML parents (`<|im_end|>`) survived the DARE+TIES merge
+alongside Llama 3.1 native tokens. Use all three:
+| Token | ID | Source |
+|---|---|---|
+| `<\|im_end\|>` | 128040 | Hermes/Nemotron parents |
+| `<\|eot_id\|>` | 128009 | Llama 3.1 native |
+| `<\|end_of_text\|>` | 128001 | Llama 3.1 native |
 ## License
 [Llama 3.1 Community License](https://llama.meta.com/llama3/license/)