Downloads · 30 days
5
8% of all-time downloads
fbaldassarri/iGeniusAI_Italia-9B-Instruct-v0.1-autoround-int4-gs64-sym
iGeniusAI_Italia-9B-Instruct-v0.1-autoround-int4-gs64-sym is a text generation model from fbaldassarri. Use it when you need the model to write or continue text. The card lists the license as mit.
Quantized version of iGeniusAI/Italia-9B-Instruct-v0.1 using torch.float32 for quantization tuning. - 4 bits (INT4) - group size = 64 - Asymmetrical Quantization - Method WoQ (AutoRound format)
Downloads · 30 days
5
8% of all-time downloads
All-time downloads
64
Public
Parameters
1.4B
5.4 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors5.4 GB · 100%
How the weights are stored.
I321B · 73%
From the Hugging Face model README
Quantized version of iGeniusAI/Italia-9B-Instruct-v0.1 using torch.float32 for quantization tuning.
Quantization framework: Intel AutoRound v0.4.6
Note: this INT4 version of Italia-9B-Instruct-v0.1 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/v0.4.6.tar.gz
tar -xvzf v0.4.6.tar.gz
cd auto-round-0.4.6
pip install -r requirements-cpu.txt --upgrade
pip install -vvv --no-build-isolation -e .[cpu]
from transformers import AutoModelForCausalLM, AutoTokenizer, GPTNeoXModel
model_name = "iGeniusAI/Italia-9B-Instruct-v0.1"
model = GPTNeoXModel.from_pretrained(model_name, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_name)
from auto_round import AutoRound
bits, group_size, sym, device, amp = 4, 64, 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/iGeniusAI_Italia-9B-Instruct-v0.1-autoround-int4-gs64-asym"
autoround.save_quantized(output_dir, format='auto_round', inplace=True)
Note: the GPTNeoXSdpaAttention class is deprecated in favor of simply modifying the config._attn_implementationattribute of the GPTNeoXAttention class. So this require transformers<4.48.
This quantized model comes with no warranty. It has been developed only for research purposes.