Instructions to use Vikhrmodels/Vikhr-7B-instruct_0.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vikhrmodels/Vikhr-7B-instruct_0.2 with Transformers:

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

pipe = pipeline("text-generation", model="Vikhrmodels/Vikhr-7B-instruct_0.2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Vikhrmodels/Vikhr-7B-instruct_0.2")
model = AutoModelForCausalLM.from_pretrained("Vikhrmodels/Vikhr-7B-instruct_0.2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Vikhrmodels/Vikhr-7B-instruct_0.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vikhrmodels/Vikhr-7B-instruct_0.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vikhrmodels/Vikhr-7B-instruct_0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Vikhrmodels/Vikhr-7B-instruct_0.2

SGLang

How to use Vikhrmodels/Vikhr-7B-instruct_0.2 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 "Vikhrmodels/Vikhr-7B-instruct_0.2" \
    --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": "Vikhrmodels/Vikhr-7B-instruct_0.2",
		"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 "Vikhrmodels/Vikhr-7B-instruct_0.2" \
        --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": "Vikhrmodels/Vikhr-7B-instruct_0.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Vikhrmodels/Vikhr-7B-instruct_0.2 with Docker Model Runner:
```
docker model run hf.co/Vikhrmodels/Vikhr-7B-instruct_0.2
```

Просто хочу оставить отзыв.

by Izikos - opened Feb 16, 2024

Discussion

Izikos

Feb 16, 2024

Совсем недавно попробовал эту модель и я незнаю как вы это сделали но это по моему мнению лучшее что есть на русском языке. Она умнее и логичнее Сайги (даже мистраль) и ruGPT и даже квантованая до q8 осталась умной и логичной с RAG. Мечтал бы увидеть ваши 13b и 30b

radm

Feb 19, 2024

Поддерживаю, действительно очень удачный выпуск. По сравнению в версией 0.1 небо и земля. Не поделитесь что именно поправили?

AlexWortega

Vikhr models org Mar 1, 2024

сменили датасет, часть модели заморозили

zhanbol

Mar 9, 2024

оставлю комментарий. спасибо большое!

AlexWortega changed discussion status to closed Mar 10, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment