Instructions to use nitwof/saiga2_7b_lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nitwof/saiga2_7b_lora with Transformers:

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

pipe = pipeline("text-generation", model="nitwof/saiga2_7b_lora")

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

tokenizer = AutoTokenizer.from_pretrained("nitwof/saiga2_7b_lora")
model = AutoModelForCausalLM.from_pretrained("nitwof/saiga2_7b_lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nitwof/saiga2_7b_lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nitwof/saiga2_7b_lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nitwof/saiga2_7b_lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nitwof/saiga2_7b_lora

SGLang

How to use nitwof/saiga2_7b_lora 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 "nitwof/saiga2_7b_lora" \
    --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": "nitwof/saiga2_7b_lora",
		"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 "nitwof/saiga2_7b_lora" \
        --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": "nitwof/saiga2_7b_lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nitwof/saiga2_7b_lora with Docker Model Runner:
```
docker model run hf.co/nitwof/saiga2_7b_lora
```

saiga2_7b_lora

Commit History

Apr 10, 2025

15:53
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
f7d1b1f

Sep 26, 2023

16:57
Upload pytorch_model-00001-of-00003.bin

nitwof

2497588
16:44
Upload 3 files

nitwof

9939e87
14:14
Upload special_tokens_map.json

nitwof

21c0361
14:13
Upload 2 files

nitwof

44c6f28
14:12
Upload 3 files

nitwof

c7d6521
14:11
Update generation_config.json

nitwof

d5b2664
13:09
Update config.json

nitwof

a8478c4

Sep 25, 2023

21:21
Upload 6 files

nitwof

493758d
19:56
initial commit

nitwof

d359206

Commit History

Apr 10, 2025

Adding `safetensors` variant of this model⁠

Sep 26, 2023

Upload pytorch_model-00001-of-00003.bin

Upload 3 files

Upload special_tokens_map.json

Upload 2 files

Upload 3 files

Update generation_config.json

Update config.json

Sep 25, 2023

Upload 6 files

initial commit