Hugging Face's logo
mobicham's picture
43 5 37

mobicham

mobicham
appoose's profile picture victor's profile picture Jilt's profile picture
·
https://www.mobiuslabs.com/

AI & ML interests

Model pruning, quantization, computer vision, LLMs

Recent Activity

updated a model 1 day ago
mobiuslabsgmbh/gemma-3-12b-it_4bitgs64_bfp16_hqq_hf
liked a model 7 days ago
mobiuslabsgmbh/gemma-3-12b-it_4bitgs64_bfp16_hqq_hf
published a model 7 days ago
mobiuslabsgmbh/gemma-3-12b-it_4bitgs64_bfp16_hqq_hf
View all activity

Organizations

Mobius Labs GmbH's profile picture Distillation Hugs's profile picture

mobicham's activity

New activity in mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.1 about 2 months ago

Open source eval metrics and library?

1
#1 opened about 2 months ago by
er1k0
New activity in mobiuslabsgmbh/DeepSeek-R1-ReDistill-Llama3-8B-v1.1 about 2 months ago

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

5
#1 opened about 2 months ago by
SalomonMejia01
New activity in mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1 about 2 months ago

It's bad, sorry.

1
#2 opened about 2 months ago by
MrDevolver

Will there be a 32b and 70b too?

1
#1 opened about 2 months ago by
AlgorithmicKing
New activity in mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-1.5B-v1.0 about 2 months ago

Open Source Distillation Approach?

1
#1 opened 2 months ago by
nbroad
New activity in mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bitgs8-metaoffload-HQQ about 2 months ago

not run

2
#2 opened about 2 months ago by
rakmik
New activity in mobiuslabsgmbh/Llama-3-8b-instruct_2bitgs64_hqq about 2 months ago

erorr

4
#2 opened about 2 months ago by
rakmik

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

6
#1 opened 8 months ago by
vasilee
New activity in mobiuslabsgmbh/Llama-3.1-8b-instruct_4bitgs64_hqq about 2 months ago

not run

2
#1 opened about 2 months ago by
rakmik
New activity in mobiuslabsgmbh/Llama-2-7b-chat-hf-4bit_g64-HQQ about 2 months ago

not run

5
#1 opened 3 months ago by
sdyy
New activity in open-llm-leaderboard/deepseek-ai__DeepSeek-R1-Distill-Qwen-1.5B-details 2 months ago

Benchmark numbers are too low and don't match the numbers run locally
#1 opened 2 months ago by
mobicham
New activity in mobiuslabsgmbh/Llama-3.1-70b-instruct_4bitgs64_hqq 7 months ago

CPU support

1
#2 opened 7 months ago by
Essa20001

Decensored version?

5
#1 opened 8 months ago by
KnutJaegersberg
New activity in mobiuslabsgmbh/Llama-3.1-8b-instruct_4bitgs64_hqq_calib 8 months ago

Oobabooga?

1
#1 opened 8 months ago by
AIGUYCONTENT
New activity in mobiuslabsgmbh/Llama-2-7b-chat-hf_1bitgs8_hqq 8 months ago

QUANTIZED VERSION GGUF

1
#5 opened 8 months ago by
ar08
New activity in open-llm-leaderboard/open_llm_leaderboard 10 months ago

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

5
#755 opened 10 months ago by
mobicham
New activity in mobiuslabsgmbh/Llama-2-7b-chat-hf_1bitgs8_hqq 11 months ago

Details about this model

1
#4 opened 11 months ago by
at676

Make it usageable for cpu

2
#3 opened 11 months ago by
ar08

Error with adapter ?

3
#2 opened 12 months ago by
nelkh
New activity in mobiuslabsgmbh/Llama-2-7b-chat-hf_1bitgs8_hqq 12 months ago

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

1
#1 opened 12 months ago by
raincandy-u