None's picture

None

Thireus

·

AI & ML interests

None yet

Recent Activity

liked a model 3 days ago

DavidAU/Qwen3-4B-Q8_0-64k-128k-256k-context-GGUF

new activity 4 days ago

unsloth/Qwen3-32B-GGUF:Potentially still broken?

liked a model 4 days ago

unsloth/Qwen3-32B-128K-GGUF

View all activity

Organizations

None yet

Thireus's activity

New activity in unsloth/Qwen3-32B-GGUF 4 days ago

Potentially still broken?

#8 opened 12 days ago by

New activity in kalomaze/Qwen3-16B-A3B 5 days ago

Brainstorming

#6 opened 11 days ago by

New activity in unsloth/Qwen3-32B-128K-GGUF 5 days ago

UD version not doing great with YaRN compared to non-UD of the same size

#4 opened 13 days ago by

New activity in unsloth/Qwen3-32B-GGUF 5 days ago

PPL vs model size - safe to assume larger size == better accuracy regardless of UD vs non-UD?

#6 opened 15 days ago by

New activity in Qwen/Qwen3-32B 9 days ago

Potential issue with large context sizes - can someone confirm?

#18 opened 14 days ago by

New activity in Qwen/Qwen3-235B-A22B 10 days ago

Qwen is loosing broad knowledge since Qwen2.

#16 opened 15 days ago by

New activity in unsloth/Qwen3-235B-A22B-128K-GGUF 10 days ago

YaRN not enabled correctly

#3 opened 15 days ago by

New activity in unsloth/Qwen3-0.6B-GGUF 10 days ago

Any chance of a 128k version so we can use it as a draft model for the larger 128k models?

#3 opened 14 days ago by

New activity in unsloth/Qwen3-16B-A3B-GGUF 11 days ago

Could we have the 128K variants as well please?

#1 opened 11 days ago by

New activity in kalomaze/Qwen3-16B-A3B 11 days ago

Context size? YaRN still supported?

#3 opened 11 days ago by

New activity in mattshumer/Reflection-Llama-3.1-70B 8 months ago

CORRECTION: THIS SYSTEM MESSAGE IS PURE GOLD!!!

#33 opened 8 months ago by

New activity in Kijai/flux-fp8 9 months ago

FP8 Checkpoint version size mismatch?

#15 opened 9 months ago by

New activity in meta-llama/Meta-Llama-3-70B-Instruct about 1 year ago

What is the "system" prompt?

#13 opened about 1 year ago by

New activity in mistralai/Mixtral-8x22B-Instruct-v0.1 about 1 year ago

First Word Ignored Issue / Single Word Instruction

#11 opened about 1 year ago by

Prompt format

#12 opened about 1 year ago by

New activity in mistralai/Mixtral-8x7B-Instruct-v0.1 about 1 year ago

Incomplete Answers

#59 opened over 1 year ago by

samparksoftwares

New activity in cognitivecomputations/dolphin-2.5-mixtral-8x7b over 1 year ago

Higher PPL than Mixtral?

#11 opened over 1 year ago by

New activity in LoneStriker/dolphin-2.2-70b-6.0bpw-h6-exl2 over 1 year ago

exl2-2 please?

#1 opened over 1 year ago by

New activity in cognitivecomputations/dolphin-2.2-70b over 1 year ago

Safetensors version?

#2 opened over 1 year ago by

New activity in LoneStriker/dolphin-2.2-yi-34b-4.0bpw-h6-exl2 over 1 year ago

tokenization_yi.py

#1 opened over 1 year ago by