eaddario/Qwen3-30B-A3B-pruned-GGUF
Text Generation
•
Updated
•
225
•
1
Ed Addario PRO
eaddario
AI & ML interests
None yet
Recent Activity
updated
a model
3 days ago
eaddario/Qwen3-30B-A3B-pruned-GGUF
published
a model
5 days ago
eaddario/Qwen3-30B-A3B-pruned-GGUF
updated
a model
5 days ago
eaddario/Qwen3-30B-A3B-GGUF
Organizations
eaddario's activity
updated
a
model
3 days ago
published
a
model
5 days ago
updated
a
model
5 days ago
Interesting comparisons!
11
#1 opened 25 days ago
by
ubergarm
replied to
their
post
6 days ago
Thanks @ubergarm . As usual, very insightful!
reacted to
AdinaY's
post with 👍
7 days ago
Post
991
AReaL-boba² 🔥 A fully async RL system by Ant Research & Tsinghua.
Paper: AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning (2505.24298)
Model:
inclusionAI/areal-boba-2-683f0e819ccb7bb2e1b2f2d5
✨ 8B/14B/32B models, datasets & paper – all on the hub
✨ 2.77× faster training
✨ Native Agentic RL support
Paper: AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning (2505.24298)
Model:
inclusionAI/areal-boba-2-683f0e819ccb7bb2e1b2f2d5
✨ 8B/14B/32B models, datasets & paper – all on the hub
✨ 2.77× faster training
✨ Native Agentic RL support
reacted to
danieldk's
post with 🤗
7 days ago
Post
1540
We have been working on a project called
We plan to give kernels a more proper introduction soon. But for those who have been following along, we are happy to announce a new release:
- New layer API with
- Experimental support for loading Apple Silicon Metal 🤘 Kernels.
- Generate wheels from Hub kernels for legacy deployments.
Full release notes here: https://github.com/huggingface/kernels/releases/tag/v0.6.0
kernels. kernels makes it possible to load compute kernels directly from the Hub! 🚀We plan to give kernels a more proper introduction soon. But for those who have been following along, we are happy to announce a new release:
- New layer API with
torch.compile support.- Experimental support for loading Apple Silicon Metal 🤘 Kernels.
- Generate wheels from Hub kernels for legacy deployments.
Full release notes here: https://github.com/huggingface/kernels/releases/tag/v0.6.0
reacted to
MJannik's
post with 🤝
7 days ago
Post
1592
Hi everyone, we’ve got big news! Starting today, all Langfuse product features are available as free OSS (MIT license).
You can now upgrade your self-hosted Langfuse to access features like:
- Managed LLM-as-a-Judge evaluations
- Annotation queues
- Prompt experiments
- LLM playground
We’re incredibly grateful for the support of this amazing community and can’t wait to hear your feedback on the new features!
More on this change here: https://langfuse.com/blog/2025-06-04-open-sourcing-langfuse-product
You can now upgrade your self-hosted Langfuse to access features like:
- Managed LLM-as-a-Judge evaluations
- Annotation queues
- Prompt experiments
- LLM playground
We’re incredibly grateful for the support of this amazing community and can’t wait to hear your feedback on the new features!
More on this change here: https://langfuse.com/blog/2025-06-04-open-sourcing-langfuse-product
posted
an
update
8 days ago
Post
1254
Layer-wise and Pruned versions of google/gemma-3-12b-it
After enhancing llama.cpp to handle user-defined quantization levels for arbitrary tensors (https://github.com/ggml-org/llama.cpp/pull/12511), I have added an option to prune whole layers (https://github.com/ggml-org/llama.cpp/pull/13037), and have published two versions of google/gemma-3-12b-it for demo and testing purposes:
* Tesor-wise: eaddario/gemma-3-12b-it-GGUF
* Pruned: eaddario/gemma-3-12b-it-pruned-GGUF
Even though the Perplexity scores of the pruned version are 3 times higher, the ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores are holding remarkably well, considering two layers were removed (26 and 29). This seems to support Xin Men et al conclusions in ShortGPT: Layers in Large Language Models are More Redundant Than You Expect (2403.03853)
Results summary in the model's card and test results in the ./scores directory. Questions/feedback is always welcomed.
After enhancing llama.cpp to handle user-defined quantization levels for arbitrary tensors (https://github.com/ggml-org/llama.cpp/pull/12511), I have added an option to prune whole layers (https://github.com/ggml-org/llama.cpp/pull/13037), and have published two versions of google/gemma-3-12b-it for demo and testing purposes:
* Tesor-wise: eaddario/gemma-3-12b-it-GGUF
* Pruned: eaddario/gemma-3-12b-it-pruned-GGUF
Even though the Perplexity scores of the pruned version are 3 times higher, the ARC, HellaSwag, MMLU, Truthful QA and WinoGrande scores are holding remarkably well, considering two layers were removed (26 and 29). This seems to support Xin Men et al conclusions in ShortGPT: Layers in Large Language Models are More Redundant Than You Expect (2403.03853)
Results summary in the model's card and test results in the ./scores directory. Questions/feedback is always welcomed.
updated
2
models
8 days ago
published
a
model
9 days ago
updated
2
models
10 days ago