Plus Light's picture

19 18

Plus Light

Light4Bear

·

sgsdxzy

AI & ML interests

None yet

Recent Activity

new activity 2 days ago

cognitivecomputations/DeepSeek-R1-AWQ:Can't get 48 TPS on 8x H800

new activity 18 days ago

cognitivecomputations/DeepSeek-V3-AWQ:GPTQ Support

new activity 8 months ago

deepseek-ai/DeepSeek-V2-Chat:Join LMSYS Chatbot Arena?

View all activity

Organizations

Light4Bear's activity

New activity in cognitivecomputations/DeepSeek-R1-AWQ 2 days ago

Can't get 48 TPS on 8x H800

#21 opened 2 days ago by

New activity in cognitivecomputations/DeepSeek-V3-AWQ 18 days ago

GPTQ Support

#1 opened about 2 months ago by

New activity in deepseek-ai/DeepSeek-V2-Chat 8 months ago

Join LMSYS Chatbot Arena?

#11 opened 9 months ago by

New activity in alpindale/c4ai-command-r-plus-GPTQ 11 months ago

Can VLLM be used for loading?

#4 opened 11 months ago by

How many bits and what is the groupsize?

#3 opened 11 months ago by

How to load command r+ in text-generation-webui?

#1 opened 11 months ago by

MLDataScientist

New activity in abacusai/Liberated-Qwen1.5-72B 12 months ago

GPTQ/AWQ quant that is runable in vllm?

#4 opened 12 months ago by

New activity in jondurbin/bagel-34b-v0.4 12 months ago

Difference between v0.2 and v0.4?

#2 opened about 1 year ago by

Tokenizer is incorrectly tokenizing '<|im_start|>' and '<|im_end|>' as strings

#5 opened 12 months ago by

New activity in dreamgen/opus-v1-34b about 1 year ago

Instruct sequences?

#2 opened about 1 year ago by deleted

What is the context size of this model?

#1 opened about 1 year ago by

MarinaraSpaghetti

New activity in brucethemoose/Yi-34B-200K-RPMerge about 1 year ago

Suggestion: increase the weights of instruction-following models.

#6 opened about 1 year ago by

New activity in LoneStriker/MiquMaid-v2-2x70B-DPO-GPTQ about 1 year ago

Safetensor naming convention

#1 opened about 1 year ago by

New activity in LoneStriker/Smaug-72B-v0.1-AWQ about 1 year ago

vLLM output gibberish but text-generation-webui is fine

#2 opened about 1 year ago by

New activity in ShinojiResearch/Senku-70B-Full about 1 year ago

GPTQ and AWQ quants

#1 opened about 1 year ago by

New activity in abacusai/Smaug-72B-v0.1 about 1 year ago

Congratulations!

#1 opened about 1 year ago by

New activity in bartowski/internlm2-chat-20b-llama-exl2 about 1 year ago

Difference between this and the non-"test" version?

#2 opened about 1 year ago by

New activity in LoneStriker/Mixtral_34Bx2_MoE_60B-6.0bpw-h6-exl2 about 1 year ago

8.0bpw-h8-exl2 quant of this model

#1 opened about 1 year ago by

New activity in chavinlo/gpt4-x-alpaca almost 2 years ago

fp16 version of the model

#6 opened almost 2 years ago by