Roman Ivanov's picture

13 1 5

Roman Ivanov

perelmanych

AI & ML interests

None yet

Organizations

None yet

New activity in ubergarm/Kimi-K2-Thinking-GGUF 3 months ago

Definitely interested in this one!

#1 opened 3 months ago by

New activity in xai-org/grok-2 5 months ago

Incorrect Model Uploaded

#8 opened 5 months ago by

New activity in zai-org/CC-Bench-trajectories 6 months ago

Qwen3 coder version

#1 opened 6 months ago by

New activity in sleepdeprived3/Llama-3.3-T3 7 months ago

Difference from other presets

#1 opened 7 months ago by

New activity in bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF about 1 year ago

R1 32b is much worse than QwQ ...

#6 opened about 1 year ago by

New activity in deepseek-ai/DeepSeek-R1-Distill-Llama-70B about 1 year ago

SFT (Non-RL) distillation is this good on a sub-100B model?

#2 opened about 1 year ago by

New activity in mradermacher/Llama3-ChatQA-1.5-70B-GGUF over 1 year ago

IQ2_XS variant

#2 opened over 1 year ago by

New activity in lmsys/vicuna-33b-v1.3 over 2 years ago

When we can expect vicuna variant of CodeLlama-2 34b model?

#10 opened over 2 years ago by

New activity in TheBloke/WizardCoder-Guanaco-15B-V1.1-GGML over 2 years ago

Can't load q5_1 model

#1 opened over 2 years ago by

New activity in anon8231489123/vicuna-13b-GPTQ-4bit-128g almost 3 years ago

Error when using with web-ui "KeyError: 'model.layers.39.self_attn.q_proj.wf1'"

#7 opened almost 3 years ago by

New activity in anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g almost 3 years ago

Error using ooba-gooba

#6 opened almost 3 years ago by

Error using ooba-gooba

#6 opened almost 3 years ago by

Error using ooba-gooba

#6 opened almost 3 years ago by