Amgad Hasan's picture

65 4 6

Amgad Hasan

amgadhasan

·

https://amgadhasan.com

AmgadHasan

AI & ML interests

LLM ASR

Recent Activity

new activity 30 days ago

deepseek-ai/DeepSeek-V3.2-Speciale:Super Based!

new activity 2 months ago

ggml-org/gpt-oss-20b-GGUF:Add missing `-fa on` flag

new activity 4 months ago

xai-org/grok-2:What do we know about the architecture so far?

View all activity

Organizations

New activity in deepseek-ai/DeepSeek-V3.2-Speciale 30 days ago

Super Based!

#3 opened 30 days ago by

New activity in ggml-org/gpt-oss-20b-GGUF 2 months ago

Add missing `-fa on` flag

#6 opened 2 months ago by

New activity in xai-org/grok-2 4 months ago

What do we know about the architecture so far?

#6 opened 4 months ago by

New activity in huggingchat/chat-ui 6 months ago

[ANNOUNCEMENT] 📣 HuggingChat is closing for now

❤️ 😔 327

#747 opened 6 months ago by

New activity in inclusionAI/Ming-Lite-Omni 7 months ago

Colab notebook to run the model?

#1 opened 7 months ago by

New activity in nvidia/parakeet-tdt-0.6b-v2 7 months ago

Recipes to Finetune to new Language example Hindi (Finally figured out)

#45 opened 7 months ago by

New activity in openai/whisper-large-v3-turbo about 1 year ago

Which infra to run openai/whisper-large-v3-turbo ?

#7 opened about 1 year ago by

New activity in openai/whisper-large-v3 over 1 year ago

how many GPU memory do I need to finetune largeV3

#150 opened over 1 year ago by

What is the accuracy of the model? Why can't I fine-tune when I set the accuracy to FP16?

#157 opened over 1 year ago by

New activity in openai/whisper over 1 year ago

How to fine tuning with timestamps

#122 opened over 1 year ago by

New activity in fixie-ai/ultravox-v0_4 over 1 year ago

Max sequence length

#2 opened over 1 year ago by

New activity in NousResearch/Meta-Llama-3-8B-Instruct over 1 year ago

What is the difference between this and official meta repo?

#9 opened over 1 year ago by

New activity in mistralai/Mistral-Nemo-Instruct-2407 over 1 year ago

Issues with Fine-Tuning

#21 opened over 1 year ago by

New activity in ZeroWw/Phi-3-mini-4k-instruct-GGUF over 1 year ago

Phi-3.1?

#1 opened over 1 year ago by

New activity in microsoft/Phi-3-mini-4k-instruct over 1 year ago

The model stops after generating one new token

#76 opened over 1 year ago by

rajiv-data-chef

New activity in bartowski/Lite-Mistral-150M-v2-Instruct-GGUF over 1 year ago

Wrong chat template

#1 opened over 1 year ago by

New activity in HuggingFaceTB/SmolLM-360M-Instruct over 1 year ago

Prompting Style?

#3 opened over 1 year ago by

New activity in mlabonne/NeuralDaredevil-7B over 1 year ago

Prompt Template?

#2 opened over 1 year ago by

New activity in omi-health/sum-small over 1 year ago

GGUF

#1 opened over 1 year ago by

New activity in inceptionai/jais-30b-v3 almost 2 years ago

Difference vs v1?

#1 opened almost 2 years ago by