Instructions to use silveroxides/Anima-Quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use silveroxides/Anima-Quantized with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Upload anima-preview-fp8mixedlearned.safetensors
#1
by MoonliteRainbow - opened
No description provided.
(510/516) Skipping tensor: net.llm_adapter.blocks.5.self_attn.q_proj.weight (Reason: regex exclusion (--exclude-layers))
(511/516) Skipping tensor: net.llm_adapter.blocks.5.self_attn.v_proj.weight (Reason: regex exclusion (--exclude-layers))
(512/516) Skipping tensor: net.llm_adapter.embed.weight (Reason: regex exclusion (--exclude-layers))
(513/516) Skipping tensor: net.llm_adapter.out_proj.weight (Reason: regex exclusion (--exclude-layers))
(514/516) Skipping tensor: net.t_embedder.1.linear_1.weight (Reason: regex exclusion (--exclude-layers))
(515/516) Skipping tensor: net.t_embedder.1.linear_2.weight (Reason: regex exclusion (--exclude-layers))
(516/516) Skipping tensor: net.x_embedder.proj.1.weight (Reason: regex exclusion (--exclude-layers))
Saving 1225 tensors to ./anima-preview-fp8mixedlearned.safetensors
Adding quantization metadata for 270 layers
Conversion complete!
Summary:
- Original tensor count : 685
- Weights processed : 270
- Weights skipped : 246
- Final tensor count : 1225
silveroxides changed pull request status to merged