23 4

casperhansen PRO

casperhansen

AI & ML interests

Creator of AutoAWQ

Recent Activity

new activity 18 days ago

cognitivecomputations/DeepSeek-R1-AWQ:The inference performance of the DeepSeek-R1-AWQ model is weak compared to the DeepSeek-R1 model

updated a model 18 days ago

casperhansen/deepseek-r1-distill-qwen-1.5b-awq

updated a model 18 days ago

casperhansen/deepseek-r1-distill-qwen-7b-awq

View all activity

Organizations

casperhansen's activity

New activity in cognitivecomputations/DeepSeek-R1-AWQ 18 days ago

The inference performance of the DeepSeek-R1-AWQ model is weak compared to the DeepSeek-R1 model

#3 opened 20 days ago by

qingqingz916

New activity in casperhansen/deepseek-r1-distill-qwen-32b-awq about 1 month ago

Generation configs: Unquantised vs AWQ, model weights format

#1 opened about 1 month ago by

nfunctor

New activity in casperhansen/gsm8k_synthetic_cot 2 months ago

Librarian Bot: Add language metadata for dataset

#2 opened 2 months ago by

librarian-bot

[bot] Conversion to Parquet

#1 opened 2 months ago by

parquet-converter

New activity in casperhansen/mistral-nemo-instruct-2407-awq 5 months ago

Create README.md

#3 opened 6 months ago by

cfahlgren1

New activity in casperhansen/deepseek-coder-v2-instruct-awq 7 months ago

Original model perplexity

#1 opened 8 months ago by

jacobpfau

New activity in casperhansen/llama-3-8b-instruct-awq 9 months ago

update eos token

#6 opened 9 months ago by

Praful932

New activity in casperhansen/llama-3-70b-instruct-awq 10 months ago

encountered error when loading model

#4 opened 10 months ago by

zhouzr

How did you create AWQ-quantized weights?

#5 opened 10 months ago by

nightdude

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

#1 opened 10 months ago by

Komposter43

Update generation_config.json

#3 opened 10 months ago by

alugowski

New activity in casperhansen/llama-3-8b-instruct-awq 10 months ago

Create quant_config.json

#1 opened 10 months ago by

Suparious

New activity in casperhansen/llama-3-70b-instruct-awq 10 months ago

Update generation_config.json

#2 opened 10 months ago by

hmellor

New activity in TheBloke/Mixtral-8x7B-Instruct-v0.1-AWQ about 1 year ago

always getting 0 in output

#3 opened about 1 year ago by

xubuild

Not supporting with TGI

#4 opened about 1 year ago by

abhishek3jangid

OC is not a multiple of cta_N = 64

#5 opened about 1 year ago by

lazyDataScientist

TGI - response is an empty string

#6 opened about 1 year ago by

p-christ

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

#7 opened about 1 year ago by

aaganaie

New activity in Deci/DeciLM-7B-instruct about 1 year ago

Add model_type to config.json

#2 opened about 1 year ago by

casperhansen

New activity in TheBloke/zephyr-7B-beta-AWQ over 1 year ago

Is there a way to finetune these AWQ beasts?

#1 opened over 1 year ago by

yasmolin