J's picture

9 21

J

jth01

·

t

AI & ML interests

None yet

Recent Activity

updated a model 3 days ago

jth01/DeepCoder-14B-Preview-6.5bpw-h8-exl2

published a model 3 days ago

jth01/DeepCoder-14B-Preview-6.5bpw-h8-exl2

liked a dataset 3 days ago

allenai/RLVR-IFeval

View all activity

Organizations

None yet

jth01's activity

New activity in unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit 8 days ago

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

#1 opened 9 days ago by

New activity in unsloth/Llama-4-Scout-17B-16E-Instruct 8 days ago

DOA

#1 opened 9 days ago by

New activity in unsloth/Llama-4-Scout-17B-16E-Instruct-unsloth-bnb-4bit 8 days ago

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

#2 opened 8 days ago by

New activity in turboderp/gemma-3-27b-it-exl2 about 1 month ago

U da man

#1 opened about 1 month ago by

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

New activity in billingsmoore/84000-bo-en about 1 month ago

At a quick glance it looks like these pairs are misaligned?

#2 opened about 2 months ago by

New activity in qihoo360/TinyR1-32B-Preview about 2 months ago

Repeated Thinking Tags in Output Generation

#2 opened about 2 months ago by

New activity in arcee-ai/Virtuoso-Medium-v2 2 months ago

Where are the benchmark scores?

#4 opened 2 months ago by

New activity in mistralai/Mistral-Small-24B-Instruct-2501 2 months ago

This Mistral Small has FAR less knowledge than the last.

#5 opened 2 months ago by

This Mistral Small has FAR less knowledge than the last.

#5 opened 2 months ago by