Sthenno's picture

Sthenno

sthenno

·

https://github.com/neoheartbeats

neoheartbeats

AI & ML interests

To contact me: [email protected]

Recent Activity

reacted to sometimesanotion's post with 👍 about 6 hours ago

The capabilities of the new Qwen 3 models are fascinating, and I am watching that space! My experience, however, is that context management is vastly more important with them. If you use a client with a typical session log with rolling compression, a Qwen 3 model will start to generate the same messages over and over. I don't think that detracts from them. They're optimized for a more advanced MCP environment. I honestly think the 8B is optimal for home use, given proper RAG/CAG. In typical session chats, Lamarck and Chocolatine are still my daily drives. I worked hard to give Lamarck v0.7 a sprinkling of CoT from both DRT and Deepseek R1. While those models got surpassed on the leaderboards, in practice, I still really enjoy their output. My projects are focusing on application and context management, because that's where the payoff in improved quality is right now. But should there be a mix of finetunes to make just the right mix of - my recipes are standing by.

new activity about 6 hours ago

sthenno-com/miscii-14b-0218:使用时需要购买api吗

liked a model 5 days ago

shuttleai/shuttle-3.5

View all activity

Organizations

sthenno's activity

New activity in sthenno-com/miscii-14b-0218 about 6 hours ago

使用时需要购买api吗

#3 opened 3 days ago by

New activity in sthenno-com/miscii-14b-1028 8 days ago

Improve language tag

#5 opened 11 days ago by

New activity in wanlige/li-14b-v0.4-slerp0.1 2 months ago

Fusion vs. SLERP?

#2 opened 2 months ago by

sometimesanotion

New activity in sthenno-com/miscii-14b-0218 2 months ago

Adding Evaluation Results

#2 opened 2 months ago by

倾向于拒绝生成xx内容

#1 opened 2 months ago by

New activity in sthenno/tempesthenno-ppo-ckpt40 3 months ago

Adding Evaluation Results

#2 opened 3 months ago by

New activity in sthenno-com/miscii-14b-1225 3 months ago

Adding Evaluation Results

#4 opened 3 months ago by

New activity in sthenno-com/miscii-14b-1028 3 months ago

Adding Evaluation Results

#4 opened 3 months ago by

New activity in suayptalha/Lamarckvergence-14B 3 months ago

This merge makes sense

#1 opened 3 months ago by

sometimesanotion

New activity in sthenno/tempesthenno-kto-0205-ckpt80 3 months ago

Adding Evaluation Results

#1 opened 3 months ago by

New activity in sthenno/tempesthenno-nuslerp-0124 3 months ago

Adding Evaluation Results

#1 opened 3 months ago by

New activity in sthenno/tempesthenno-nuslerp-001 3 months ago

Adding Evaluation Results

#2 opened 3 months ago by

New activity in sthenno/tempesthenno-ppo-ckpt40 3 months ago

Adding Evaluation Results

#1 opened 3 months ago by

New activity in bamec66557/Qwen-2.5-14B-MINUS 3 months ago

Extra SLERP parameters

#1 opened 4 months ago by

sometimesanotion

New activity in sthenno/tempesthenno-nuslerp-001 3 months ago

Nuslerp parameters?

#1 opened 3 months ago by

sometimesanotion

New activity in sthenno/miscii-1218-ckpt350 4 months ago

Quant Request

#1 opened 5 months ago by

New activity in sthenno-com/miscii-14b-1225 4 months ago

We sincerely invite your participation, model fine-tuners.

#3 opened 4 months ago by

Adding Evaluation Results

#1 opened 4 months ago by

New activity in sthenno-com/miscii-14b-1028 5 months ago

Quant Request

#2 opened 5 months ago by

New activity in sthenno-com/miscii-14b-1028 6 months ago

Adding Evaluation Results

#1 opened 6 months ago by

leaderboard-pr-bot