Patrick Shechet's picture

16

Patrick Shechet

kajuberdut

·

http://github.com/kajuberdut

kajuberdut

AI & ML interests

None yet

Organizations

None yet

kajuberdut's activity

New activity in TheBloke/U-Amethyst-20B-GGUF about 1 year ago

Do you have a sample dataset?

#1 opened about 1 year ago by

New activity in TheBloke/CodeLlama-70B-hf-GPTQ about 1 year ago

models files missing!

#1 opened about 1 year ago by

New activity in TheBloke/Qwen-14B-Chat-GPTQ over 1 year ago

Will it come?

#2 opened over 1 year ago by

New activity in TheBloke/Phind-CodeLlama-34B-v2-GPTQ over 1 year ago

Not able to load in oobabooga webui

#1 opened over 1 year ago by

New activity in TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF over 1 year ago

Something is causing seg fault

#1 opened over 1 year ago by

New activity in TheBloke/mpt-30B-GGML over 1 year ago

GPTQ version for italians

#3 opened over 1 year ago by

New activity in TheBloke/Mythical-Destroyer-L2-13B-GGUF over 1 year ago

This model is insanely good.

#1 opened over 1 year ago by

New activity in TheBloke/Phind-CodeLlama-34B-Python-v1-GGUF over 1 year ago

This might be the best coding model (Better than wizardcoder_python_34b)

#1 opened over 1 year ago by

New activity in TheBloke/WizardCoder-Python-34B-V1.0-GPTQ over 1 year ago

Does the result right?

#1 opened over 1 year ago by

New activity in TheBloke/Phind-CodeLlama-34B-Python-v1-GPTQ over 1 year ago

Needs "pad_token_id": 0,

#1 opened over 1 year ago by

New activity in TheBloke/WizardCoder-Python-34B-V1.0-GGUF over 1 year ago

This model looks insanely good for coding ( 73.2 for humanEval )!

#1 opened over 1 year ago by

New activity in TheBloke/CodeLlama-34B-Instruct-GPTQ over 1 year ago

Is the 34B llama2 actually GPTQ working?

#3 opened over 1 year ago by

New activity in TheBloke/CodeLlama-13B-Instruct-GPTQ over 1 year ago

What's the prompt template for this?

#3 opened over 1 year ago by

New activity in TheBloke/CodeLlama-34B-GPTQ over 1 year ago

Strange output in oobabooga

#2 opened over 1 year ago by

New activity in timdettmers/guanaco-33b-merged almost 2 years ago

Is it very slow , correct?

#8 opened almost 2 years ago by

New activity in TheBloke/guanaco-33B-GPTQ almost 2 years ago

Could this model be loaded in 3090 GPU?

#6 opened almost 2 years ago by

New activity in timdettmers/guanaco-33b-merged almost 2 years ago

Is it very slow , correct?

#8 opened almost 2 years ago by