Bazsi

BazsiBazsi

·

AI & ML interests

None yet

Recent Activity

new activity about 14 hours ago

LiquidAI/LFM2.5-24B-A2B-GGUF:QAD Q4_0 GGUF Accuracy

upvoted an article 14 days ago

Qwen3.8-27B-pi: Effort-Ordered Reasoning for Agentic Coding

liked a model 17 days ago

Asopo/cacifer_char_lstm_storyteller

View all activity

Organizations

None yet

New activity in LiquidAI/LFM2.5-24B-A2B-GGUF about 14 hours ago

QAD Q4_0 GGUF Accuracy

#2 opened about 19 hours ago by

New activity in inclusionAI/Ling-3.0-tiny about 1 month ago

MTP support?

#11 opened about 2 months ago by

New activity in Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B about 2 months ago

This vs ornith 1.5 9b

#1 opened about 2 months ago by

New activity in DontPlanToEnd/UGI-Leaderboard 3 months ago

I will be testing fewer finetunes/merges

#624 opened 7 months ago by

New activity in sphaela/Qwen3.6-27B-AutoRound-GGUF 4 months ago

New high quality quants for smaller schemes(Q2_K_S and so on)

#4 opened 4 months ago by

New activity in sphaela/Qwen3.6-27B-AutoRound-GGUF 5 months ago

Impressive

#1 opened 6 months ago by

New activity in TeichAI/GLM-4.7-Flash-Claude-Opus-4.5-High-Reasoning-Distill 8 months ago

Great Job on this Model. Sharing my Config...

#2 opened 8 months ago by

New activity in MetaphoricalCode/gemma3-27b-abliterated-dpo-exl3-3bpw-hb6 over 1 year ago

Request for smaller quants

#1 opened over 1 year ago by

New activity in isogen/Josiefied-Qwen3-8B-abliterated-v1-exl3-4bpw over 1 year ago

What is the significance of the data in the model card?

#1 opened over 1 year ago by

New activity in microsoft/Phi-4-reasoning-plus over 1 year ago

Running with VLLM is not printing '<think>' tokens.

#8 opened over 1 year ago by

New activity in DontPlanToEnd/UGI-Leaderboard over 1 year ago

possible idea geopolitical aligment?

#253 opened over 1 year ago by

Votable next models que?

#252 opened over 1 year ago by

Link mainstream benchmarks to UGI scores

#166 opened over 1 year ago by

Reasoning Models

#108 opened over 1 year ago by

New activity in open-llm-leaderboard/open_llm_leaderboard over 3 years ago

Allow submitting models with remote code

#58 opened over 3 years ago by

Checking for toxicity too

#53 opened over 3 years ago by

ronald-d-rogers

[feature request] prioritize the queue (by user voting?)

#46 opened over 3 years ago by

New activity in TheBloke/wizardLM-7B-GPTQ over 3 years ago

Very slow speed with oobabooga

#2 opened over 3 years ago by

New activity in open-llm-leaderboard/open_llm_leaderboard over 3 years ago

The system message and prompt format for TruthfulQA results for Vicuna 13B

#28 opened over 3 years ago by

New activity in TheBloke/wizardLM-7B-GPTQ over 3 years ago

Very slow speed with oobabooga

#2 opened over 3 years ago by