Gordon's picture

13

Gordon

Satya93

AI & ML interests

None yet

Recent Activity

new activity about 23 hours ago

google/gemma-3-27b-it:Simple questions too hard?

new activity 3 days ago

google/gemma-3-27b-it:Tool usage?

new activity 11 months ago

mlabonne/OrpoLlama-3-8B:Repetition from tuning via https://huggingface.co/blog/mlabonne/orpo-llama-3

View all activity

Organizations

None yet

Satya93's activity

New activity in google/gemma-3-27b-it about 23 hours ago

Simple questions too hard?

#22 opened 3 days ago by

New activity in google/gemma-3-27b-it 3 days ago

Tool usage?

#8 opened 4 days ago by

New activity in mlabonne/OrpoLlama-3-8B 11 months ago

Repetition from tuning via https://huggingface.co/blog/mlabonne/orpo-llama-3

#2 opened 11 months ago by

New activity in sentence-transformers/all-mpnet-base-v2 about 1 year ago

How to compare sentences?

#9 opened over 1 year ago by

New activity in jondurbin/airoboros-l2-70b-3.1.2 over 1 year ago

Space after [/INST]

#2 opened over 1 year ago by

New activity in NousResearch/Llama-2-13b-hf over 1 year ago

Chat version

#4 opened over 1 year ago by

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

Weird responses in Oobabooga

#2 opened over 1 year ago by

New activity in WizardLMTeam/WizardLM-13B-V1.2 over 1 year ago

RuntimeError: probability tensor contains either `inf`, `nan` or element < 0

#7 opened over 1 year ago by

New activity in TheBloke/StableBeluga2-70B-GPTQ over 1 year ago

comparison with bitsandbytes nf4, hope to increase GPTQ accuracy

#11 opened over 1 year ago by

Mininum VRAM?

#9 opened over 1 year ago by

New activity in TheBloke/Wizard-Vicuna-30B-Uncensored-GPTQ over 1 year ago

NotImplementedError: Cannot copy out of meta tensor; no data!

#15 opened over 1 year ago by

New activity in TheBloke/stable-vicuna-13B-GPTQ almost 2 years ago

stable-vicuna-13B-GPTQ-4bit.compat.no-act-order.safetensors not compatible with "standard" settings

#1 opened almost 2 years ago by

New activity in TheBloke/stable-vicuna-13B-GGML almost 2 years ago

Run with langchain

#4 opened almost 2 years ago by