Downloads · 30 days
12
3% of all-time downloads
falcon-40b-instruct-gptq-128g-act
jiyuanq/falcon-40b-instruct-gptq-128g-act
falcon-40b-instruct-gptq-128g-act is a text generation model from jiyuanq. Use it when you need the model to write or continue text. It is set up for transformers.
falcon-40b-instruct quantized with GPTQ using the script in https://github.com/huggingface/text-generation-inference/pull/438
All-time downloads
345
Public
Parameters
6.5B
23.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors23.3 GB · 100%
Parameter types
How the weights are stored.
I325.1B · 79%
Try a prompt
Model card
From the Hugging Face model README
falcon-40b-instruct quantized with GPTQ using the script in https://github.com/huggingface/text-generation-inference/pull/438
- group size: 128
- act order: true
- nsamples: 128
- dataset: wikitext2
- Task
- Text Generation
- Library
- transformers
- Type
- RefinedWeb
- Created
- Jun 25, 2023
- Updated
- Jun 25, 2023