casperhansen's picture

17 1

casperhansen

casperhansen

·

AI & ML interests

None yet

Organizations

casperhansen's activity

New activity in casperhansen/llama-3-8b-instruct-awq 23 days ago

update eos token

#6 opened about 1 month ago by

New activity in casperhansen/llama-3-70b-instruct-awq 2 months ago

encountered error when loading model

#4 opened 2 months ago by

How did you create AWQ-quantized weights?

#5 opened 2 months ago by

Infinity conversation, sould eos be <|eot_id|> ?

#1 opened 2 months ago by

Update generation_config.json

#3 opened 2 months ago by

New activity in casperhansen/llama-3-8b-instruct-awq 2 months ago

Create quant_config.json

#1 opened 2 months ago by

New activity in casperhansen/llama-3-70b-instruct-awq 2 months ago

Update generation_config.json

#2 opened 2 months ago by

New activity in TheBloke/Mixtral-8x7B-Instruct-v0.1-AWQ 5 months ago

always getting 0 in output

#3 opened 6 months ago by

Not supporting with TGI

#4 opened 6 months ago by

abhishek3jangid

OC is not a multiple of cta_N = 64

#5 opened 5 months ago by

lazyDataScientist

TGI - response is an empty string

#6 opened 5 months ago by

RuntimeError: probability tensor contains either `inf`, `nan` or element < 0

#7 opened 5 months ago by

New activity in Deci/DeciLM-7B-instruct 7 months ago

Add model_type to config.json

#2 opened 7 months ago by

New activity in TheBloke/zephyr-7B-beta-AWQ 8 months ago

Is there a way to finetune these AWQ beasts?

#1 opened 8 months ago by

New activity in TheBloke/Mistral-7B-Instruct-v0.1-AWQ 9 months ago

KeyError: 'mistral'

#1 opened 9 months ago by

tripathiarpan20

New activity in mistralai/Mistral-7B-v0.1 9 months ago

Add Apache 2.0 license

#3 opened 9 months ago by

Apache 2.0 License

#2 opened 9 months ago by