J's picture

11 29

J

jth01

·

t

AI & ML interests

None yet

Organizations

None yet

New activity in unsloth/granite-4.0-h-small-bnb-4bit 3 months ago

This isn't a 4 bit model

#1 opened 3 months ago by

New activity in unsloth/Qwen3-32B 8 months ago

Base Model?

#2 opened 8 months ago by

New activity in unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit 9 months ago

What's up with the minimal decrease in file size from fp16?

#1 opened 9 months ago by

New activity in unsloth/Llama-4-Scout-17B-16E-Instruct 9 months ago

DOA

#1 opened 9 months ago by

New activity in unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit 9 months ago

This looks like the base and not bnb-4bit?

#2 opened 9 months ago by

New activity in unsloth/QwQ-32B 10 months ago

I could be wrong, but I think the <think> tag needs to be removed from the last bit of the jinja template in the tokenizer_config.json

#1 opened 10 months ago by

New activity in qihoo360/TinyR1-32B-Preview 10 months ago

Repeated Thinking Tags in Output Generation

#2 opened 10 months ago by

New activity in arcee-ai/Virtuoso-Medium-v2 11 months ago

Where are the benchmark scores?

#4 opened 11 months ago by

New activity in mistralai/Mistral-Small-24B-Instruct-2501 11 months ago

This Mistral Small has FAR less knowledge than the last.

#5 opened 11 months ago by

This Mistral Small has FAR less knowledge than the last.

#5 opened 11 months ago by