GPTQ
Collection
quantized LLMs by AutoGPTQ
•
31 items
•
Updated
•
2
Text Generation
Transformers
Safetensors
llama
finetuned
quantized
4-bit precision
gptq
dataset:ai2_arc
dataset:unalignment/spicy-3.1
dataset:codeparrot/apps
dataset:facebook/belebele
dataset:boolq
dataset:jondurbin/cinematika-v0.1
dataset:drop
dataset:lmsys/lmsys-chat-1m
dataset:TIGER-Lab/MathInstruct
dataset:cais/mmlu
dataset:Muennighoff/natural-instructions
dataset:openbookqa
dataset:piqa
dataset:Vezora/Tested-22k-Python-Alpaca
dataset:cakiki/rosetta-code
dataset:Open-Orca/SlimOrca
dataset:spider
dataset:squad_v2
dataset:migtissera/Synthia-v1.3
dataset:datasets/winogrande
dataset:nvidia/HelpSteer
dataset:Intel/orca_dpo_pairs
dataset:unalignment/toxic-dpo-v0.1
dataset:jondurbin/truthy-dpo-v0.1
dataset:allenai/ultrafeedback_binarized_cleaned
dataset:Squish42/bluemoon-fandom-1-1-rp-cleaned
dataset:LDJnr/Capybara
dataset:JULIELab/EmoBank
dataset:kingbri/PIPPA-shareGPT
Inference Endpoints
text-generation-inference
conversational
Eval Results
Description
MaziyarPanahi/UNA-34Beagles-32K-bf16-v1-GPTQ is a quantized (GPTQ) version of one-man-army/UNA-34Beagles-32K-bf16-v1
How to use
Install the necessary packages
pip install --upgrade accelerate auto-gptq transformers
Example Python code
from transformers import AutoTokenizer, pipeline
from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
import torch
model_id = "MaziyarPanahi/UNA-34Beagles-32K-bf16-v1-GPTQ"
quantize_config = BaseQuantizeConfig(
bits=4,
group_size=128,
desc_act=False
)
model = AutoGPTQForCausalLM.from_quantized(
model_id,
use_safetensors=True,
device="cuda:0",
quantize_config=quantize_config)
tokenizer = AutoTokenizer.from_pretrained(model_id)
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.1
)
outputs = pipe("What is a large language model?")
print(outputs[0]["generated_text"])
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 29.15 |
| AI2 Reasoning Challenge (25-Shot) | 26.11 |
| HellaSwag (10-Shot) | 26.29 |
| MMLU (5-Shot) | 24.43 |
| TruthfulQA (0-shot) | 47.27 |
| Winogrande (5-shot) | 50.83 |
| GSM8k (5-shot) | 0.00 |
- Downloads last month
- 2,173
Finetuned from
Collection including MaziyarPanahi/UNA-34Beagles-32K-bf16-v1-GPTQ
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard26.110
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard26.290
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard24.430
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard47.270
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard50.830
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard0.000