Instructions to use subho123/gemma-7b-finetune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use subho123/gemma-7b-finetune with Transformers:

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

pipe = pipeline("text-generation", model="subho123/gemma-7b-finetune")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("subho123/gemma-7b-finetune")
model = AutoModelForCausalLM.from_pretrained("subho123/gemma-7b-finetune")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use subho123/gemma-7b-finetune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "subho123/gemma-7b-finetune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "subho123/gemma-7b-finetune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/subho123/gemma-7b-finetune

SGLang

How to use subho123/gemma-7b-finetune 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 "subho123/gemma-7b-finetune" \
    --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": "subho123/gemma-7b-finetune",
		"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 "subho123/gemma-7b-finetune" \
        --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": "subho123/gemma-7b-finetune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use subho123/gemma-7b-finetune with Docker Model Runner:
```
docker model run hf.co/subho123/gemma-7b-finetune
```

This is a demo project for learning purpose,This is gemma 7b model fintuned on 'Abirate/english_quotes' dataset.

Downloads last month: 2

Safetensors

Model size

9B params

Tensor type

F32

Model tree for subho123/gemma-7b-finetune

Base model

google/gemma-7b

Quantized

(21)

this model

subho123
/

gemma-7b-finetune

Model tree for subho123/gemma-7b-finetune

Dataset used to train subho123/gemma-7b-finetune