Instructions to use Komposter43/saiga2_70b_lora-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Komposter43/saiga2_70b_lora-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="Komposter43/saiga2_70b_lora-AWQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Komposter43/saiga2_70b_lora-AWQ")
model = AutoModelForCausalLM.from_pretrained("Komposter43/saiga2_70b_lora-AWQ", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Komposter43/saiga2_70b_lora-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Komposter43/saiga2_70b_lora-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Komposter43/saiga2_70b_lora-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Komposter43/saiga2_70b_lora-AWQ

SGLang

How to use Komposter43/saiga2_70b_lora-AWQ 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 "Komposter43/saiga2_70b_lora-AWQ" \
    --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": "Komposter43/saiga2_70b_lora-AWQ",
		"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 "Komposter43/saiga2_70b_lora-AWQ" \
        --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": "Komposter43/saiga2_70b_lora-AWQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Komposter43/saiga2_70b_lora-AWQ with Docker Model Runner:
```
docker model run hf.co/Komposter43/saiga2_70b_lora-AWQ
```

Saiga2 70B - AWQ, Russian LLaMA2-based chatbot

Model creator: IlyaGusev
Original model: Saiga2 70B

Description

This repo contains AWQ model files for Saiga2 70B

About AWQ

AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference.

It is also now supported by continuous batching server vLLM, allowing use of AWQ models for high-throughput concurrent inference in multi-user server scenarios. Note that, at the time of writing, overall throughput is still lower than running vLLM with unquantised models, however using AWQ enables using much smaller GPUs which can lead to easier deployment and overall cost savings. For example, a 70B model can be run on 1 x 48GB GPU instead of 2 x 80GB.

Downloads last month: 7

Safetensors

Model size

10B params

Tensor type

I32

F16

Model tree for Komposter43/saiga2_70b_lora-AWQ

Base model

IlyaGusev/saiga2_70b_lora

Finetuned

(1)

this model