Qwen/Qwen3-Embedding-8B
Feature Extraction
β’
Updated
β’
14.2k
β’
116
Sthenno
sthenno
AI & ML interests
To contact me: [email protected]
Recent Activity
liked
a model
1 day ago
Qwen/Qwen3-Embedding-8B
liked
a dataset
2 days ago
sentence-transformers/stsb
liked
a model
3 days ago
intfloat/multilingual-e5-large-instruct
Organizations
sthenno's activity
liked
a
model
1 day ago
liked
a
dataset
2 days ago
liked
3
models
3 days ago
liked
3
models
16 days ago
liked
a
model
20 days ago
liked
a
dataset
22 days ago
liked
3
models
22 days ago
reacted to
sometimesanotion's
post with π
about 1 month ago
Post
1772
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.
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.
δ½Ώη¨ζΆιθ¦θ΄δΉ°apiε
1
#3 opened about 1 month ago
by
Andy2390
liked
a
model
about 1 month ago
reacted to
sometimesanotion's
post with πβ€οΈ
about 1 month ago
Post
1772
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.
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.
liked
a
model
about 1 month ago
Improve language tag
π€
1
#5 opened about 2 months ago
by
lbourdois