TheBloke
/

Falcon-180B-Chat-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

Resources

View closed (1)

ModuleNotFoundError: No module named 'optimum'

#9 opened 9 months ago by

Model card parameters

#8 opened about 1 year ago by

Model outputs 1 word or letter ("I", "Hey")

#7 opened about 1 year ago by

very slow inference speed on 2x A100 80GB with 4-bit (main branch)

#6 opened about 1 year ago by

AttributeError: 'FalconForCausalLM' object has no attribute 'device_to_buffers

#5 opened about 1 year ago by

Can run on SageMaker g5 instance?

#4 opened about 1 year ago by

3bit on single A100 good quality, poor speed

#3 opened about 1 year ago by

Brilliant!

#1 opened about 1 year ago by