Instructions to use Vikhrmodels/Vikhr-7B-instruct_0.4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vikhrmodels/Vikhr-7B-instruct_0.4 with Transformers:

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

pipe = pipeline("text-generation", model="Vikhrmodels/Vikhr-7B-instruct_0.4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Vikhrmodels/Vikhr-7B-instruct_0.4")
model = AutoModelForCausalLM.from_pretrained("Vikhrmodels/Vikhr-7B-instruct_0.4", device_map="auto")
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 Settings

vLLM

How to use Vikhrmodels/Vikhr-7B-instruct_0.4 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_0.4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vikhrmodels/Vikhr-7B-instruct_0.4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Vikhrmodels/Vikhr-7B-instruct_0.4

SGLang

How to use Vikhrmodels/Vikhr-7B-instruct_0.4 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_0.4" \
    --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": "Vikhrmodels/Vikhr-7B-instruct_0.4",
		"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 "Vikhrmodels/Vikhr-7B-instruct_0.4" \
        --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": "Vikhrmodels/Vikhr-7B-instruct_0.4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Vikhrmodels/Vikhr-7B-instruct_0.4 with Docker Model Runner:
```
docker model run hf.co/Vikhrmodels/Vikhr-7B-instruct_0.4
```

Vikhr-7B-instruct_0.4 / README.md

AlexWortega

Update README.md

dd96032 verified about 2 years ago

preview code

Raw

History Blame Contribute Delete

2.15 kB

metadata

library_name: transformers
language:
  - ru
  - en

Релиз вихря 0.3-0.4

Долили сильно больше данных в sft, теперь стабильнее работает json и multiturn, слегка подточили параметры претрена модели

Added a lot more data to sft, now json and multiturn work more stable on long context and hard prompts



from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model = AutoModelForCausalLM.from_pretrained("Vikhrmodels/Vikhr-7B-instruct_0.4",
                                             device_map="auto",
                                             attn_implementation="flash_attention_2",
                                             torch_dtype=torch.bfloat16)

tokenizer = AutoTokenizer.from_pretrained("Vikhrmodels/Vikhr-7B-instruct_0.4")
from transformers import  AutoTokenizer, pipeline
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
prompts = [
    "В чем разница между фруктом и овощем?",
    "Годы жизни колмагорова?"]

def test_inference(prompt):
    prompt = pipe.tokenizer.apply_chat_template([{"role": "user", "content": prompt}], tokenize=False, add_generation_prompt=True)
    print(prompt)
    outputs = pipe(prompt, max_new_tokens=512, do_sample=True, num_beams=1, temperature=0.25, top_k=50, top_p=0.98, eos_token_id=79097)
    return outputs[0]['generated_text'][len(prompt):].strip()


for prompt in prompts:
    print(f"    prompt:\n{prompt}")
    print(f"    response:\n{test_inference(prompt)}")
    print("-"*50)

@article{nikolich2024vikhr,
  title={Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian},
  author={Aleksandr Nikolich and Konstantin Korolev and Artem Shelmanov},
  journal={arXiv preprint arXiv:2405.13929},
  year={2024},
  url={https://arxiv.org/pdf/2405.13929}
}