Instructions to use Vikhrmodels/Vikhr-tiny-0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vikhrmodels/Vikhr-tiny-0.1 with Transformers:

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

pipe = pipeline("text-generation", model="Vikhrmodels/Vikhr-tiny-0.1", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Vikhrmodels/Vikhr-tiny-0.1", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Vikhrmodels/Vikhr-tiny-0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vikhrmodels/Vikhr-tiny-0.1"
# 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-tiny-0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Vikhrmodels/Vikhr-tiny-0.1

SGLang

How to use Vikhrmodels/Vikhr-tiny-0.1 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-tiny-0.1" \
    --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-tiny-0.1",
		"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-tiny-0.1" \
        --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-tiny-0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Vikhrmodels/Vikhr-tiny-0.1 with Docker Model Runner:
```
docker model run hf.co/Vikhrmodels/Vikhr-tiny-0.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

DONT TOUCH, under dev

Task	Version	Metric	Value		Stderr
parus	0	acc	0.4950	±	0.0250
rcb	0	acc	0.3333	±	0.0226
		f1_macro	0.1667
rwsd	0	acc	0.4901	±	0.0203
mmlu	0	0.31	0.225

Based on https://huggingface.co/openbmb/MiniCPM-2B-sft-bf16

https://wandb.ai/alexwortega/cpm_rus/runs/32w8pv7x?workspace=user-alexwortega

lol

Downloads last month: 19

Safetensors

Model size

3B params

Tensor type

F16

Model tree for Vikhrmodels/Vikhr-tiny-0.1

Quantizations

2 models

Vikhrmodels
/

Vikhr-tiny-0.1

Model tree for Vikhrmodels/Vikhr-tiny-0.1

Space using Vikhrmodels/Vikhr-tiny-0.1 1