Victor Nogueira's picture

Victor Nogueira

Felladrin

·

https://felladrin.com

felladrin

AI & ML interests

Models to run in the web browser

Recent Activity

reacted to ngxson's post with 🚀 about 9 hours ago

A comprehensive matrix for which format should you use. Read more on my blog post: https://huggingface.co./blog/ngxson/common-ai-model-formats ``` | Hardware | GGUF | PyTorch | Safetensors | ONNX | |-----------------|-----------|------------------------|--------------------------|-------| | CPU | ✅ (best) | 🟡 | 🟡 | ✅ | | GPU | ✅ | ✅ | ✅ | ✅ | | Mobile | ✅ | 🟡 (via executorch) | ❌ | ✅ | | Apple silicon | ✅ | 🟡 | ✅ (via MLX framework) | ✅ | ```

new activity about 22 hours ago

Felladrin/gguf-sharded-LaMini-Flan-T5-248M:how to run encoder-decoder models with llama.cpp

updated a model about 22 hours ago

Felladrin/gguf-Q8_0-LaMini-Flan-T5-248M

View all activity

Organizations

Felladrin's activity

New activity in Felladrin/gguf-sharded-LaMini-Flan-T5-248M about 22 hours ago

how to run encoder-decoder models with llama.cpp

#1 opened 7 months ago by

New activity in mlx-community/Phi-4-mini-instruct-8bit 1 day ago

ValueError: [broadcast_shapes] Shapes (48) and (64) cannot be broadcast.

#1 opened 1 day ago by

New activity in mlx-community/mlx-my-repo 1 day ago

Error when converting huihui-ai/Llama-3.2-3B-Instruct-abliterated: Received parameters not in model: lm_head.weight.

#36 opened 1 day ago by

New activity in onnx-community/convert-to-onnx 1 day ago

update-transformer.js

#9 opened 1 day ago by

New activity in mlx-community/mlx-my-repo 1 day ago

Error converting microsoft/Phi-4-mini-instruct: Shapes (48) and (64) cannot be broadcast.

#35 opened 2 days ago by

New activity in UUFO-Aigis/Pico-OpenLAiNN-250M 5 days ago

What's its license?

#1 opened 7 days ago by

New activity in Felladrin/llama2_xs_460M_experimental_platypus 21 days ago

Adding `safetensors` variant of this model

#1 opened 21 days ago by

New activity in onnx-community/mms-tts-kan-ONNX 28 days ago

Create README.md

#1 opened 28 days ago by

New activity in onnx-community/dictabert-ner-ONNX about 2 months ago

Create README.md

#1 opened about 2 months ago by

New activity in onnx-community/Qwen2.5-0.5B-ONNX about 2 months ago

How is this different to onnx-community/Qwen2.5-0.5B?

#1 opened about 2 months ago by

New activity in onnx-community/TinyMistral-248M-v2-ONNX about 2 months ago

Create README.md

#1 opened about 2 months ago by

New activity in onnx-community/TinyLlama-1.1B-Chat-v1.0-ONNX about 2 months ago

Create README.md

#1 opened about 2 months ago by

New activity in mlx-community/mlx-my-repo 2 months ago

Error: [quantize] The requested number of bits 3 is not supported. The supported bits are 2, 4 and 8.

#34 opened 2 months ago by

New activity in vectara/leaderboard 3 months ago

Broken link for deepseek/deepseek-chat model

#8 opened 3 months ago by

New activity in onnx-community/convert-to-onnx 3 months ago

Error: "Conversoin failed: Framework not specified. Using pt to export the model."

#5 opened 3 months ago by

We moved! 🚚

#1 opened 8 months ago by

Remove env variables subprocess call

#4 opened 5 months ago by

Update to v3

#3 opened 5 months ago by

New activity in Felladrin/onnx-Llama-160M-Chat-v1 3 months ago

Quantize llama 3.2 1B into onnx INT8

#1 opened 5 months ago by

New activity in Felladrin/Minueza-32M-Base 4 months ago

Transfer learning?

#3 opened 8 months ago by