Instructions to use iproskurina/bloom-3b-GPTQ-4bit-g128 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use iproskurina/bloom-3b-GPTQ-4bit-g128 with Transformers:

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

pipe = pipeline("text-generation", model="iproskurina/bloom-3b-GPTQ-4bit-g128")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("iproskurina/bloom-3b-GPTQ-4bit-g128")
model = AutoModelForCausalLM.from_pretrained("iproskurina/bloom-3b-GPTQ-4bit-g128", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use iproskurina/bloom-3b-GPTQ-4bit-g128 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "iproskurina/bloom-3b-GPTQ-4bit-g128"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "iproskurina/bloom-3b-GPTQ-4bit-g128",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/iproskurina/bloom-3b-GPTQ-4bit-g128

SGLang

How to use iproskurina/bloom-3b-GPTQ-4bit-g128 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 "iproskurina/bloom-3b-GPTQ-4bit-g128" \
    --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": "iproskurina/bloom-3b-GPTQ-4bit-g128",
		"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 "iproskurina/bloom-3b-GPTQ-4bit-g128" \
        --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": "iproskurina/bloom-3b-GPTQ-4bit-g128",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use iproskurina/bloom-3b-GPTQ-4bit-g128 with Docker Model Runner:
```
docker model run hf.co/iproskurina/bloom-3b-GPTQ-4bit-g128
```

iproskurina commited on Mar 29, 2025

Commit

7ba4174

verified ·

1 Parent(s): 96513a7

Update README.md to include GPTQModel usage.

Browse files

Files changed (1) hide show

README.md +0 -14

README.md CHANGED Viewed

@@ -127,17 +127,3 @@ model = GPTQModel.load(model_id)
 result = model.generate("Uncovering deep insights")[0] # tokens
 print(model.tokenizer.decode(result)) # string output
 ```
-### Run the model with GPTQModel
-GPTQModel package: https://github.com/ModelCloud/GPTQModel
-```
-pip install -v gptqmodel=="1.8.0" --no-build-isolation
-from gptqmodel import GPTQModel
-model_id = 'iproskurina/bloom-3b-GPTQ-4bit-g128'
-model = GPTQModel.load(model_id)
-result = model.generate("Uncovering deep insights")[0] # tokens
-print(model.tokenizer.decode(result)) # string output
-```

 result = model.generate("Uncovering deep insights")[0] # tokens
 print(model.tokenizer.decode(result)) # string output
 ```