43 5 36

mobicham

https://www.mobiuslabs.com/

AI & ML interests

Model pruning, quantization, computer vision, LLMs

Recent Activity

updated a model 13 days ago

mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1_4bitgs64_hqq_hf

liked a model 13 days ago

mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1_4bitgs64_hqq_hf

published a model 13 days ago

mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1_4bitgs64_hqq_hf

View all activity

Organizations

mobicham's activity

New activity in mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1 15 days ago

Open source eval metrics and library?

#1 opened 15 days ago by

er1k0

New activity in mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1 15 days ago

No model file found in repo 'mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1'

#1 opened 19 days ago by

SalomonMejia01

New activity in mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1 15 days ago

It's bad, sorry.

#2 opened 17 days ago by

MrDevolver

Will there be a 32b and 70b too?

#1 opened 23 days ago by

AlgorithmicKing

New activity in mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0 15 days ago

Open Source Distillation Approach?

#1 opened 30 days ago by

nbroad

New activity in mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bitgs8-metaoffload-HQQ 18 days ago

not run

#2 opened 20 days ago by

rakmik

New activity in mobiuslabsgmbh/Llama-3-8b-instruct_2bitgs64_hqq 19 days ago

erorr

#2 opened 20 days ago by

rakmik

the coder from the model card has errors when executing on google colab

#1 opened 7 months ago by

vasilee

New activity in mobiuslabsgmbh/Llama-3.1-8b-instruct_4bitgs64_hqq 19 days ago

not run

#1 opened 20 days ago by

rakmik

New activity in mobiuslabsgmbh/Llama-2-7b-chat-hf-4bit_g64-HQQ 19 days ago

not run

#1 opened 2 months ago by

sdyy

New activity in open-llm-leaderboard/deepseek-ai__DeepSeek-R1-Distill-Qwen-1.5B-details about 1 month ago

Benchmark numbers are too low and don't match the numbers run locally

#1 opened about 1 month ago by

mobicham

New activity in mobiuslabsgmbh/Llama-3.1-70b-instruct_4bitgs64_hqq 6 months ago

CPU support

#2 opened 6 months ago by

Essa20001

Decensored version?

#1 opened 7 months ago by

KnutJaegersberg

New activity in mobiuslabsgmbh/Llama-3.1-8b-instruct_4bitgs64_hqq_calib 7 months ago

Oobabooga?

#1 opened 7 months ago by

AIGUYCONTENT

New activity in mobiuslabsgmbh/Llama-2-7b-chat-hf_1bitgs8_hqq 7 months ago

QUANTIZED VERSION GGUF

#5 opened 7 months ago by

ar08

New activity in open-llm-leaderboard/open_llm_leaderboard 9 months ago

GSM8K (5-shot) performance is quite different compared to running lm_eval locally

#755 opened 9 months ago by

mobicham

New activity in mobiuslabsgmbh/Llama-2-7b-chat-hf_1bitgs8_hqq 10 months ago

Details about this model

#4 opened 10 months ago by

at676

Make it usageable for cpu

#3 opened 10 months ago by

ar08

Error with adapter ?

#2 opened 11 months ago by

nelkh

New activity in mobiuslabsgmbh/Llama-2-7b-chat-hf_1bitgs8_hqq 11 months ago

Any plan for making HQQ+ 2bit quant for Mixtral or larger models?

#1 opened 11 months ago by

raincandy-u