Instructions to use fbaldassarri/EleutherAI_pythia-1.4b-deduped-autoawq-int4-gs128-sym with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Local Apps Settings

How to use fbaldassarri/EleutherAI_pythia-1.4b-deduped-autoawq-int4-gs128-sym with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fbaldassarri/EleutherAI_pythia-1.4b-deduped-autoawq-int4-gs128-sym"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fbaldassarri/EleutherAI_pythia-1.4b-deduped-autoawq-int4-gs128-sym",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/fbaldassarri/EleutherAI_pythia-1.4b-deduped-autoawq-int4-gs128-sym

SGLang

How to use fbaldassarri/EleutherAI_pythia-1.4b-deduped-autoawq-int4-gs128-sym 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 "fbaldassarri/EleutherAI_pythia-1.4b-deduped-autoawq-int4-gs128-sym" \
    --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": "fbaldassarri/EleutherAI_pythia-1.4b-deduped-autoawq-int4-gs128-sym",
		"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 "fbaldassarri/EleutherAI_pythia-1.4b-deduped-autoawq-int4-gs128-sym" \
        --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": "fbaldassarri/EleutherAI_pythia-1.4b-deduped-autoawq-int4-gs128-sym",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use fbaldassarri/EleutherAI_pythia-1.4b-deduped-autoawq-int4-gs128-sym with Docker Model Runner:
```
docker model run hf.co/fbaldassarri/EleutherAI_pythia-1.4b-deduped-autoawq-int4-gs128-sym
```

EleutherAI_pythia-1.4b-deduped-autoawq-int4-gs128-sym / README.md

fbaldassarri

Initial Upload

5c80e8f verified almost 2 years ago

preview code

Raw

History Blame Contribute Delete

2.15 kB

	---
	language:
	- en
	tags:
	- pytorch
	- causal-lm
	- pythia
	- autoround
	- intel-autoround
	- intel
	- autoawq
	- awq
	- woq
	license: apache-2.0
	model_name: Pythia 1.4b deduped
	base_model: EleutherAI/pythia-1.4b-deduped
	inference: false
	model_creator: EleutherAI
	datasets:
	- EleutherAI/pile
	pipeline_tag: text-generation
	prompt_template: '{prompt}
	'
	quantized_by: fbaldassarri
	---

	## Model Information

	Quantized version of [EleutherAI/pythia-1.4b-deduped](https://huggingface.co/EleutherAI/pythia-1.4b-deduped) using torch.float32 for quantization tuning.
	- 4 bits (INT4)
	- group size = 128
	- Symmetrical Quantization
	- Method AutoAWQ

	Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round)

	Note: this INT4 version of pythia-1.4b-deduped has been quantized to run inference through CPU.

	## Replication Recipe

	### Step 1 Install Requirements

	I suggest to install requirements into a dedicated python-virtualenv or a conda enviroment.

	```
	python -m pip install <package> --upgrade
	```

	- accelerate==1.0.1
	- auto_gptq==0.7.1
	- neural_compressor==3.1
	- torch==2.3.0+cpu
	- torchaudio==2.5.0+cpu
	- torchvision==0.18.0+cpu
	- transformers==4.45.2

	### Step 2 Build Intel AutoRound wheel from sources

	```
	python -m pip install git+https://github.com/intel/auto-round.git
	```

	### Step 3 Script for Quantization

	```
	from transformers import AutoModelForCausalLM, AutoTokenizer
	model_name = "EleutherAI/pythia-1.4b-deduped"
	model = AutoModelForCausalLM.from_pretrained(model_name)
	tokenizer = AutoTokenizer.from_pretrained(model_name)
	from auto_round import AutoRound
	bits, group_size, sym = 4, 128, True
	autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym)
	autoround.quantize()
	output_dir = "./AutoRound/EleutherAI_pythia-1.4b-deduped-autoawq-int4-gs128-sym"
	autoround.save_quantized(output_dir, format='auto_awq', inplace=True)
	```

	## License

	[Apache 2.0 License](https://choosealicense.com/licenses/apache-2.0/)

	## Disclaimer

	This quantized model comes with no warranty. It has been developed only for research purposes.