Instructions to use gotzmann/Mira-70B-v0.8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gotzmann/Mira-70B-v0.8 with Transformers:

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

pipe = pipeline("text-generation", model="gotzmann/Mira-70B-v0.8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gotzmann/Mira-70B-v0.8")
model = AutoModelForCausalLM.from_pretrained("gotzmann/Mira-70B-v0.8", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use gotzmann/Mira-70B-v0.8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gotzmann/Mira-70B-v0.8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gotzmann/Mira-70B-v0.8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gotzmann/Mira-70B-v0.8

SGLang

How to use gotzmann/Mira-70B-v0.8 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 "gotzmann/Mira-70B-v0.8" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gotzmann/Mira-70B-v0.8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "gotzmann/Mira-70B-v0.8" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gotzmann/Mira-70B-v0.8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gotzmann/Mira-70B-v0.8 with Docker Model Runner:
```
docker model run hf.co/gotzmann/Mira-70B-v0.8
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Mira 70B v0.8

The smartest Russian model based on LLaMA 70B v2 architecture. So maybe it's the last Big Russian Model of that family.

Trained with TRINITY method for 60 hours of Nvidia H100.

Prompt Format

Please use the prompt formatted like this:

You are an AI assistant that follows instruction. Help as much as you can.

### Human:

Your question here.

### Assistant:

Please pay attention for double new lines everywhere - and after "### Assistant:" line too!

GGUF

https://huggingface.co/gotzmann/Mira-70B-v0.8-GGUF/tree/main

Downloads last month: 6

Model tree for gotzmann/Mira-70B-v0.8

Quantizations

1 model