Instructions to use olaverse/MIST-1-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use olaverse/MIST-1-70B with Transformers:

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

pipe = pipeline("text-generation", model="olaverse/MIST-1-70B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("olaverse/MIST-1-70B")
model = AutoModelForCausalLM.from_pretrained("olaverse/MIST-1-70B")
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 olaverse/MIST-1-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "olaverse/MIST-1-70B"
# 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-1-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/olaverse/MIST-1-70B

SGLang

How to use olaverse/MIST-1-70B 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-1-70B" \
    --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-1-70B",
		"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-1-70B" \
        --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-1-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use olaverse/MIST-1-70B with Docker Model Runner:
```
docker model run hf.co/olaverse/MIST-1-70B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MIST-1-70B

MIST-1-70B is the mid-size model in the MIST model family by olaverse. Built by blending 4 of the best Llama 3.1 70B models using DARE+TIES. structured, detailed, production ready

MIST Model Family

Model	Params	Speed	Status
MIST-1-8B	8B	~63 tok/s	✅ Available
MIST-1-70B	70B	~23 tok/s	✅ Available
MIST-1-140B	140B	~8 tok/s	✅ Available

Key Strengths

🧠 Strong Reasoning — DeepSeek R1 distillation at 70B scale
🤝 Highly Helpful — built on Nemotron #1 on helpfulness benchmarks
💻 Coding — clean documented production-ready code
📐 Math — step-by-step structured problem solving
🌍 Multilingual — supports 8+ languages
📚 Long Context — 128K token context window
🔓 Unrestricted — follows instructions without excessive refusals

Merge Method

MIST-1-70B uses DARE+TIES:

DARE prunes redundant weights from each model
TIES resolves weight conflicts using sign consensus
Result: best capabilities of all 4 models combined

Benchmark Results

Task	Speed	Quality
Reasoning	10.5s	✅ Correct step-by-step
Coding	11.3s	✅ Clean with type hints
Math	11.3s	✅ Structured with verification
General	11.3s	✅ Accurate and detailed
Instruction	8.1s	✅ Precise and formatted

Average: 23 tok/s

How to Use

bfloat16 — Full Precision (140GB VRAM)

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "olaverse/MIST-1-70B",
    torch_dtype="auto",
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("olaverse/MIST-1-70B")

messages = [{"role": "user", "content": "Your question here"}]
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=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

4-bit Quantized (40GB VRAM)

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-1-70B",
    quantization_config=quantization_config,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("olaverse/MIST-1-70B")

Hardware Requirements

Precision	VRAM	Size
bfloat16	140GB (1x H200 or 2x H100)	132GB
4-bit (NF4)	40GB (1x A100/H100)	~35GB

Important Notes on Chat Template

This model was merged from both Llama 3.1 and ChatML-trained parents (Hermes-3, Nemotron, DeepSeek-R1-Distill). The merged tokenizer uses Llama 3.1 format, but the model can occasionally output <|im_end|> as plain text due to its mixed training heritage.

✅ Correct Usage

Always use the built-in chat template — never hardcode prompts manually:

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

tokenizer = AutoTokenizer.from_pretrained("olaverse/MIST-1-70B")
model = AutoModelForCausalLM.from_pretrained(
    "olaverse/MIST-1-70B",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

messages = [
    {"role": "system", "content": "You are MIST, a helpful AI assistant."},
    {"role": "user", "content": "Your question here"}
]

inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt",
    return_dict=True
).to(model.device)

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=[128009, 128001, 128008],
    pad_token_id=128001,
)

response = tokenizer.decode(
    outputs[0][inputs["input_ids"].shape[-1]:],
    skip_special_tokens=True
)
print(response)

⚠️ Common Mistake

Do NOT hardcode ChatML format like this:

# WRONG — this model is Llama 3.1, not ChatML
prompt = f"user\n{question}\nassistant\n"

Forcing ChatML format on a Llama 3.1 tokenizer confuses the model and causes <|im_end|> to leak as plain text in responses.

Stop Tokens

Token	ID	Purpose
`<\|eot_id\|>`	128009	Primary stop (Llama 3.1 native)
`<\|end_of_text\|>`	128001	Secondary stop
`<\|eom_id\|>`	128008	End of message

Note: <|im_end|> is NOT in this model's vocabulary. If you see it in output, your prompt formatting is wrong — use apply_chat_template as shown above.