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

Libraries

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

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

pipe = pipeline("text-generation", model="olaverse/MIST-Mini-8B-Thinking")
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-Thinking")
model = AutoModelForCausalLM.from_pretrained("olaverse/MIST-Mini-8B-Thinking")
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-Thinking 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-Thinking"
# 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-Thinking",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

Docker Model Runner
How to use olaverse/MIST-Mini-8B-Thinking with Docker Model Runner:
```
docker model run hf.co/olaverse/MIST-Mini-8B-Thinking
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MIST-Mini-8B-Thinking

MIST-Mini-8B-Thinking is the reasoning version of MIST-Mini-8B by olaverse. Trained with 4 phases of GRPO (Group Relative Policy Optimization) reinforcement learning to show its reasoning process before answering.

MIST Model Family

Model	Params	Type	Speed	Status
MIST-1-8B	8B	General	~63 tok/s	✅
MIST-Mini-8B-Thinking	8B	Reasoning	~55 tok/s	✅
MIST-1-70B	70B	General	~23 tok/s	✅
MIST-1-140B	140B	General	~8 tok/s	✅

What Makes This Different

MIST-Mini-8B (base): User: What is 15% of 280? Model: 42 MIST-Mini-8B-Thinking: User: What is 15% of 280? Model: 15% means 15/100 280 × 15 = 4200 4200 / 100 = 42 The answer is 42.

Training Details

Trained with 4 phases of GRPO reinforcement learning:

Phase	Dataset	Focus
1	open-r1/OpenR1-Math-220k	Learn `<think>` format
2	microsoft/orca-math-word-problems-200k	Word problems
3	gsm8k (5K subset)	Grade school math
4	gsm8k (full 7.4K)	Solidify + merge

Reward Functions Used

reward_think_format: +0.5 for using tags reward_correctness: +1.0 for correct answer reward_reasoning_steps: +0.3 for structured steps

Training Progress

Phase	Correctness	Total Reward
Phase 1	-0.35	-0.99
Phase 2	-1.0	-0.74
Phase 3	-1.0	-0.65
Phase 4	+0.95	+1.29

Key Strengths

🧠 Transparent Reasoning — shows thinking before answering
📐 Strong Math — 95% accuracy on GSM8K after training
🔍 Trustworthy — you can verify the reasoning
⚡ Fast — 8B model, runs on consumer GPUs
🔓 Unrestricted — follows all instructions

How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "olaverse/MIST-Mini-8B-Thinking",
    torch_dtype="auto",
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("olaverse/MIST-Mini-8B-Thinking")

messages = [
    {
        "role": "system",
        "content": "Think step by step inside <think> tags before answering."
    },
    {
        "role": "user", 
        "content": "If a train travels 120 miles in 2 hours, what is its speed?"
    }
]

text = tokenizer.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)
inputs = tokenizer(text, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=1024, temperature=0.7, do_sample=True)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

4-bit Quantized (fits on 6GB GPU)

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
import torch

quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.bfloat16,
    bnb_4bit_quant_type='nf4'
)
model = AutoModelForCausalLM.from_pretrained(
    "olaverse/MIST-Mini-8B-Thinking",
    quantization_config=quantization_config,
    device_map="auto",
)

Hardware Requirements

Precision	VRAM	Size
bfloat16	16GB	15GB
4-bit (NF4)	6GB	~4GB

Recommended Generation Settings

outputs = model.generate(
    **inputs,
    max_new_tokens=1024,
    do_sample=True,
    temperature=0.6,
    top_p=0.95,
    min_p=0.05,
    repetition_penalty=1.5,
    eos_token_id=[128040, 128009, 128001],
    pad_token_id=128001,
)

Notes

Temperature 0.6 (lower than base model) gives more consistent reasoning
<think> and </think> are plain text tokens, not special tokens — the model learned them through GRPO training
Always include the system prompt instruction to use <think> tags for reliable reasoning behaviour