Orimo W's picture

Orimo W

imoc

·

Originalimoc

AI & ML interests

None yet

Recent Activity

liked a model 3 days ago

Qwen/QwQ-32B

new activity 3 days ago

Qwen/QwQ-32B:Nice work... Cant-believe-its-just-32B-performance even with various different tones system prompt.

liked a model 19 days ago

perplexity-ai/r1-1776

View all activity

Organizations

None yet

imoc's activity

New activity in Qwen/QwQ-32B 3 days ago

Nice work... Cant-believe-its-just-32B-performance even with various different tones system prompt.

#37 opened 3 days ago by

New activity in Qwen/QVQ-72B-Preview about 2 months ago

Hmmmmm still weird refusal, as QwQ

#5 opened about 2 months ago by

New activity in abacusai/Dracarys2-72B-Instruct 3 months ago

Minimal GPU requirements

#3 opened 5 months ago by

New activity in diabolic6045/open-llama-3.2-1B-Instruct 3 months ago

Which one?

#1 opened 3 months ago by

New activity in black-forest-labs/FLUX.1-dev 3 months ago

too big to run

#320 opened 3 months ago by

New activity in MaziyarPanahi/calme-3.2-instruct-78b 3 months ago

Why FP32?

#10 opened 3 months ago by

New activity in crestf411/Q2.5-32B-Slush 3 months ago

The training data is not in ChatML format and it won't stop correctly.

#3 opened 3 months ago by

New activity in AALF/gemma-2-27b-it-SimPO-37K 3 months ago

Difference between this and the other (100 steps) model?

#1 opened 7 months ago by

New activity in AiCloser/Qwen2.5-32B-AGI 3 months ago

Nice work!

#1 opened 6 months ago by

New activity in Nexusflow/Athene-V2-Chat 3 months ago

32 B coding model please

#4 opened 4 months ago by

New activity in Qwen/QwQ-32B-Preview 3 months ago

vllm reply garbled

#29 opened 3 months ago by

This is way too much... USB? Yes. U SB.

#21 opened 3 months ago by

New activity in thirdeyeai/qwen2.5-7b-uncensored 3 months ago

Very good 7B, good job

#1 opened 3 months ago by

New activity in Qwen/QwQ-32B-Preview 3 months ago

Adds Chinese characters to responses

#16 opened 3 months ago by

Nice name QAQ. I'll later upload a 4.7bpw quantized model if it works.

#12 opened 3 months ago by

New activity in AXCXEPT/EZO-Qwen2.5-32B-Instruct 4 months ago

Nice work. Best 32B model(quantized to 4.7bpw) so far, more people should try.

#1 opened 4 months ago by

New activity in Volko76/Qwen2.5-Coder-1.5B-Instruct-5.5bpw-exl2 4 months ago

Does not work. The model size is wrong too. 1.5B x 5.5BPW should be ~1.6GB

#1 opened 4 months ago by

New activity in Orenguteng/Llama-3-8B-Lexi-Uncensored 11 months ago

What's the prompt template though? It doesn't like to stop😂

#4 opened 11 months ago by

New activity in WizardLMTeam/WizardCoder-33B-V1.1 about 1 year ago

WC models are heavily biased towards old standards/code samples

#8 opened about 1 year ago by