Downloads · 30 days
7
13% of all-time downloads
fbaldassarri/openlm-research_open_llama_7b_v2-autoround-int8-gs64-sym
openlm-research_open_llama_7b_v2-autoround-int8-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 apache-2.0.
Quantized version of openlm-research/openllama7bv2 using torch.float32 for quantization tuning. - 8 bits (INT4) - group size = 64 - Symmetrical Quantization - Method WoQ (AutoRound format)
Downloads · 30 days
7
13% of all-time downloads
All-time downloads
53
Public
Parameters
2B
7.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors7.8 GB · 100%
How the weights are stored.
I321.6B · 82%
From the Hugging Face model README
Quantized version of openlm-research/open_llama_7b_v2 using torch.float32 for quantization tuning.
Fast and low memory, 2-3X speedup (slight accuracy drop at W8G64)
Quantization framework: Intel AutoRound v0.4.6
Note: this INT8 version of open_llama_7b_v2 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
model_name = "openlm-research/open_llama_7b_v2"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
from auto_round import AutoRound
bits, group_size, sym, device, amp = 8, 64, 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/openlm-research_open_llama_7b_v2-autoround-int8-gs64-sym"
autoround.save_quantized(output_dir, format='auto_round', inplace=True)
This quantized model comes with no warranty. It has been developed only for research purposes.