openbmb/MiniCPM5-1B
Text Generation • 1B • Updated • 350k • 825
Mesh Anthony Unuakhe
SkyNotion
AI & ML interests
None yet
Recent Activity
liked a model 27 days ago
openbmb/MiniCPM5-1B liked a model 27 days ago
stepfun-ai/PaCoRe-8B upvoted a changelog about 1 month ago
Filter Models page by Base Models onlyOrganizations
liked 2
models 27 days ago
upvoted a changelog about 1 month ago
Hugging Face Changelog
Filter Models page by Base Models only
• 173
liked a
model 8 months ago
upvoted 2
articles 8 months ago
Article
Uncensor any LLM with abliteration
mlabonne
• • 870 Article
Building the Open Agent Ecosystem Together: Introducing OpenEnv
- +8
spisakjo, darktex, zkwentz, mortimerp9, Sanyam, Hamid-Nazeri, Pankit01, emre0, lewtun, reach-vb
• • 164 reacted to piercus's post with 🧠8 months ago
Post
1881
🚧 Reproducing LBM-Eraser… in progress! [1]
When repurposing a T2I model into a pure I2I model, there’s always that orphaned text path — what do we do with it? 🤔
You can reuse it as learnable embeddings in multi-task setups [2], freeze an empty text prompt, distillate or prune the corresponding part.
In LBM, they take a clever route — zeroing [3] and reshaping [4] the text-related cross-attentions into self-attentions.
This gives you fresh weights for I2I computation, nicely integrated into your SD architecture.
📎 References
[1] Our LBM Fork: https://github.com/finegrain-ai/LBM
[2] OmniPaint: OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting (2503.08677)
[3] LBM Zeroing: https://github.com/gojasper/LBM/blob/cafebc46a9ac16dcc61691d289cc4676b5c75380/examples/training/train_lbm_surface.py#L147-L148
[4] LBM Reshaping: https://github.com/gojasper/LBM/blob/cafebc46a9ac16dcc61691d289cc4676b5c75380/examples/training/train_lbm_surface.py#L100
When repurposing a T2I model into a pure I2I model, there’s always that orphaned text path — what do we do with it? 🤔
You can reuse it as learnable embeddings in multi-task setups [2], freeze an empty text prompt, distillate or prune the corresponding part.
In LBM, they take a clever route — zeroing [3] and reshaping [4] the text-related cross-attentions into self-attentions.
This gives you fresh weights for I2I computation, nicely integrated into your SD architecture.
📎 References
[1] Our LBM Fork: https://github.com/finegrain-ai/LBM
[2] OmniPaint: OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting (2503.08677)
[3] LBM Zeroing: https://github.com/gojasper/LBM/blob/cafebc46a9ac16dcc61691d289cc4676b5c75380/examples/training/train_lbm_surface.py#L147-L148
[4] LBM Reshaping: https://github.com/gojasper/LBM/blob/cafebc46a9ac16dcc61691d289cc4676b5c75380/examples/training/train_lbm_surface.py#L100
- 2 replies
liked a
model 10 months ago
liked 2
models about 1 year ago
updated 10
models almost 2 years ago
SkyNotion/gemma-2-2b-it-Q4_K_M-GGUF
Text Generation • 3B • Updated • 14
SkyNotion/NeuralDaredevil-8B-abliterated-Q4_K_M-GGUF
8B • Updated • 35
SkyNotion/Mistral-7B-v0.3-Q4_K_M-GGUF
7B • Updated • 2
SkyNotion/deepseek-coder-6.7b-instruct-Q4_K_M-GGUF
7B • Updated • 42
SkyNotion/deepseek-coder-7b-instruct-v1.5-Q4_K_M-GGUF
7B • Updated • 284 • 1
SkyNotion/deepseek-coder-1.3b-instruct-Q4_K_M-GGUF
1B • Updated • 13
SkyNotion/deepseek-math-7b-instruct-Q4_K_M-GGUF
7B • Updated • 15
SkyNotion/codegemma-2b-Q4_K_M-GGUF
3B • Updated • 7
SkyNotion/Meta-Llama-3-8B-Instruct-abliterated-v3-Q4_K_M-GGUF
8B • Updated • 72
SkyNotion/gemma-2-9b-it-abliterated-Q4_K_M-GGUF
9B • Updated • 23