Instructions to use Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r with Transformers:

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

pipe = pipeline("text-generation", model="Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r")
model = AutoModelForCausalLM.from_pretrained("Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r"
# 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/QVikhr-2.5-1.5B-Instruct-r",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r

SGLang

How to use Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r 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/QVikhr-2.5-1.5B-Instruct-r" \
    --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/QVikhr-2.5-1.5B-Instruct-r",
		"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/QVikhr-2.5-1.5B-Instruct-r" \
        --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/QVikhr-2.5-1.5B-Instruct-r",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r with Docker Model Runner:
```
docker model run hf.co/Vikhrmodels/QVikhr-2.5-1.5B-Instruct-r
```

Query about base model

by Tangchiu - opened Mar 14

Discussion

Tangchiu

Mar 14

Hi Vikhrmodels,

I found your model QVikhr-2.5-1.5B-Instruct-r wonderful in math & RU! I’m looking into the training recipe of this model to better understand its behavioral alignment.

Would you mind sharing some insights here(Base model or training hyperparameters due to the difference between model tree & model card in HF about base model), or perhaps providing an email address for a more detailed technical discussion?

Thanks for your contribution to the community!

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