Hugging Face's logo
Siddhesh Parulekar's picture
9 13 163

Siddhesh Parulekar

siddhesh22
dvilasuero's profile picture madhavdutta's profile picture 21world's profile picture
·

AI & ML interests

None yet

Organizations

None yet

siddhesh22's activity

New activity in city96/FLUX.1-dev-gguf 3 months ago

Q6_K is slower than Q8_0!

1
#17 opened 3 months ago by siddhesh22
New activity in mlabonne/Beyonder-4x7B-v3-GGUF 8 months ago

Excellent work on this, sir!

3
#2 opened 8 months ago by dillfrescott
New activity in AetherResearch/Cerebrum-1.0-8x7b 8 months ago

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

2
#2 opened 8 months ago by siddhesh22
New activity in bartowski/starchat2-15b-v0.1-GGUF 8 months ago

What is the prompt format?

13
#1 opened 8 months ago by siddhesh22
New activity in BK-Lee/MoAI-7B 8 months ago

Quantized GGUF / EXL2 please?

2
#1 opened 8 months ago by siddhesh22
New activity in FreedomIntelligence/Apollo-7B 8 months ago

Quantized versions please?

4
#1 opened 8 months ago by siddhesh22
New activity in mlabonne/AlphaMonarch-7B 8 months ago

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

8
#5 opened 9 months ago by siddhesh22
New activity in TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF 9 months ago

Q6_K version is broken

7
#19 opened 10 months ago by tankstarwar
New activity in AlekseyKorshuk/vicuna-7b over 1 year ago

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

4
#1 opened over 1 year ago by underlines