|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
library_name: transformers |
|
tags: |
|
- autoround |
|
- auto-round |
|
- intel |
|
- gptq |
|
- woq |
|
- pytorch |
|
- transformers |
|
- safetensors |
|
- onnx |
|
- transformers.js |
|
model_name: SmolLM2 1.7B |
|
base_model: HuggingFaceTB/SmolLM2-1.7B |
|
inference: false |
|
model_creator: HuggingFaceTB |
|
pipeline_tag: text-generation |
|
prompt_template: '{prompt} |
|
' |
|
quantized_by: fbaldassarri |
|
--- |
|
|
|
## Model Information |
|
|
|
Quantized version of [HuggingFaceTB/SmolLM2-1.7B](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B) using torch.float32 for quantization tuning. |
|
- 4 bits (INT4) |
|
- group size = 128 |
|
- Asymmetrical Quantization |
|
- Method WoQ (AutoRound format) |
|
|
|
Fast and low memory, 2-3X speedup (slight accuracy drop at W4G128) |
|
|
|
Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round) v0.4.2 |
|
|
|
Note: this INT4 version of SmolLM2-1.7B 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==1.2.0 |
|
- autoawq==0.2.7.post3 |
|
- auto_gptq==0.7.1 |
|
- neural_compressor==3.1.1 |
|
- torch==2.4.1+cpu |
|
- torchaudio==2.4.1+cpu |
|
- torchvision==0.19.1+cpu |
|
- transformers==4.47.0 |
|
|
|
### 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 = "HuggingFaceTB/SmolLM2-1.7B" |
|
model = AutoModelForCausalLM.from_pretrained(model_name) |
|
tokenizer = AutoTokenizer.from_pretrained(model_name) |
|
from auto_round import AutoRound |
|
bits, group_size, sym, device, amp = 4, 128, False, 'cpu', False |
|
autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym, device=device, amp=amp) |
|
autoround.quantize() |
|
output_dir = "./AutoRound/HuggingFaceTB_SmolLM2-1.7B-auto_round-int4-gs128-asym" |
|
autoround.save_quantized(output_dir, format='auto_round', inplace=True) |
|
``` |
|
|
|
## License |
|
|
|
[Apache 2.0 License](https://choosealicense.com/licenses/apache-2.0/) |
|
|
|
## Disclaimer |
|
|
|
This quantized model comes with no warrenty. It has been developed only for research purposes. |
|
|
|
|
