J's picture

J

jth01

·

t

AI & ML interests

None yet

Recent Activity

liked a model 3 days ago

chromadb/context-1

liked a model 3 days ago

agentscope-ai/CoPaw-Flash-9B

liked a model 17 days ago

khyentsevision/minilm-bo-en-sim

View all activity

Organizations

None yet

New activity in unsloth/granite-4.0-h-small-bnb-4bit 6 months ago

This isn't a 4 bit model

#1 opened 6 months ago by

New activity in unsloth/Qwen3-32B 11 months ago

Base Model?

#2 opened 11 months ago by

New activity in unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit 12 months ago

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

#1 opened about 1 year ago by

New activity in unsloth/Llama-4-Scout-17B-16E-Instruct 12 months ago

DOA

#1 opened about 1 year ago by

New activity in unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit about 1 year ago

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

#2 opened about 1 year ago by

New activity in unsloth/QwQ-32B about 1 year 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 about 1 year ago by

New activity in qihoo360/TinyR1-32B-Preview about 1 year ago

Repeated Thinking Tags in Output Generation

#2 opened about 1 year ago by

New activity in arcee-ai/Virtuoso-Medium-v2 about 1 year ago

Where are the benchmark scores?

#4 opened about 1 year ago by

New activity in mistralai/Mistral-Small-24B-Instruct-2501 about 1 year ago

This Mistral Small has FAR less knowledge than the last.

#5 opened about 1 year ago by

This Mistral Small has FAR less knowledge than the last.

#5 opened about 1 year ago by