Siddhesh Parulekar's picture

Siddhesh Parulekar

siddhesh22

·

AI & ML interests

None yet

Recent Activity

liked a model 19 days ago

deepseek-ai/DeepSeek-R1

liked a model 2 months ago

Qwen/Qwen2.5-Coder-32B-Instruct

liked a model 2 months ago

coqui/XTTS-v2

View all activity

Organizations

None yet

siddhesh22's activity

New activity in city96/FLUX.1-dev-gguf 6 months ago

Q6_K is slower than Q8_0!

#17 opened 6 months ago by

New activity in mlabonne/Beyonder-4x7B-v3-GGUF 11 months ago

Excellent work on this, sir!

#2 opened 11 months ago by

New activity in AetherResearch/Cerebrum-1.0-8x7b 11 months ago

How do I use the chat template in oobabooga/sillytavern/koboldcpp?

#2 opened 11 months ago by

New activity in bartowski/starchat2-15b-v0.1-GGUF 11 months ago

What is the prompt format?

#1 opened 11 months ago by

New activity in BK-Lee/MoAI-7B 11 months ago

Quantized GGUF / EXL2 please?

#1 opened 11 months ago by

New activity in FreedomIntelligence/Apollo-7B 11 months ago

Quantized versions please?

#1 opened 11 months ago by

New activity in mlabonne/AlphaMonarch-7B 11 months ago

Randomly switches to Russian and even inserts gibberish english on Q6_K on KoboldCPP + Silly Tavern. Mistral Instruct prompt format.

#5 opened 12 months ago by

New activity in TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF 12 months ago

Q6_K version is broken

#19 opened about 1 year ago by

New activity in AlekseyKorshuk/vicuna-7b almost 2 years ago

Only 13b has been released, how can this be 7b?

#1 opened almost 2 years ago by