Downloads · 30 days
8
7% of all-time downloads
fbaldassarri/tiiuae_Falcon3-1B-Base-autoawq-int4-gs128-sym
tiiuae_Falcon3-1B-Base-autoawq-int4-gs128-sym is a text generation model from fbaldassarri. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
Quantized version of tiiuae/Falcon3-1B-Base using torch.float32 for quantization tuning. - 4 bits (INT4) - group size = 128 - Symmetrical Quantization - Method AutoAWQ
Downloads · 30 days
8
7% of all-time downloads
All-time downloads
115
Public
Parameters
1.7B
2.7 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors2.7 GB · 100%
How the weights are stored.
I321.1B · 68%
From the Hugging Face model README
Quantized version of tiiuae/Falcon3-1B-Base using torch.float32 for quantization tuning.
Quantization framework: Intel AutoRound v0.4.4
Note: this INT4 version of Falcon3-1B-Base has been quantized to run inference through CPU.
I suggest to install requirements into a dedicated python-virtualenv or a conda enviroment.
wget https://github.com/intel/auto-round/archive/refs/tags/v0.4.4.tar.gz
tar -xvzf v0.4.4.tar.gz
cd auto-round-0.4.4
pip install -r requirements-cpu.txt --upgrade
pip install -vvv --no-build-isolation -e .[cpu]
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "tiiuae/Falcon3-1B-Base"
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, True, '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/tiiuae_Falcon3-1B-Base-autoawq-int4-gs128-sym"
autoround.save_quantized(output_dir, format='auto_awq', inplace=True)
This quantized model comes with no warranty. It has been developed only for research purposes.