5 3 6

DINMAY KUMAR BRAHMA

spedrox-sac

AI & ML interests

LLM Pytorch NLP MLOps Efficient-net Qwen Nvidia-nim Mistral

Recent Activity

updated a model 9 days ago

spedrox-sac/Qwen2.5-1.5B_quantized_models

updated a model 10 days ago

spedrox-sac/Llama-3.2-1B_quantized

new activity 11 days ago

spedrox-sac/Anime_dataset:[bot] Conversion to Parquet

View all activity

Organizations

spedrox-sac's activity

updated a model 9 days ago

spedrox-sac/Qwen2.5-1.5B_quantized_models

Text Generation • Updated 9 days ago

updated a model 10 days ago

spedrox-sac/Llama-3.2-1B_quantized

Text Generation • Updated 10 days ago

New activity in spedrox-sac/Anime_dataset 11 days ago

[bot] Conversion to Parquet

#1 opened 12 days ago by

parquet-converter

reacted to csabakecskemeti's post with 👍 11 days ago

Post

4465

The AMD Instinct MI50 (~$110) is surprisingly fast for inference Quantized models.

This runs a Llama 3.1 8B Q8 with Llama.cpp
DevQuasar/Mi50

A little blogpost about the HW
http://devquasar.com/uncategorized/amd-radeon-instinct-mi50-cheap-inference/

updated 2 datasets 13 days ago

spedrox-sac/Anime_dataset

Viewer • Updated 13 days ago • 1.39k • 40

spedrox-sac/Anime_dataset

Viewer • Updated 13 days ago • 1.39k • 40

updated a dataset 16 days ago

spedrox-sac/bengali_chat_conv

Viewer • Updated 16 days ago • 1.07k • 40

New activity in spedrox-sac/bengali_chat_conv 17 days ago

[bot] Conversion to Parquet

#1 opened 17 days ago by

parquet-converter

liked a model 18 days ago

openai/whisper-large-v3-turbo

Automatic Speech Recognition • Updated Oct 4 • 2.55M • • 1.65k

liked a Space 18 days ago

Running

💻

OuteTTS DEMO

Demo space for OuteTTS

updated a Space 22 days ago

Sleeping

🐨

AI SQL Query

replied to nroggendorff's post 23 days ago

Yup , think so .. 🙃

reacted to AdinaY's post with 👍 23 days ago

Post

1331

HunyuanVideo 📹 The new open video generation model by Tencent!
👉 tencent/HunyuanVideo
zh-ai-community/video-models-666afd86cfa4e4dd1473b64c
✨ 13B parameters: Probably the largest open video model to date
✨ Unified architecture for image & video generation
✨ Powered by advanced features: MLLM Text Encoder, 3D VAE, and Prompt Rewrite
✨ Delivers stunning visuals, diverse motion, and unparalleled stability
🔓 Fully open with code & weights

reacted to nroggendorff's post with 🤯 23 days ago

Post

1850

uhh..

11 replies

reacted to mikelabs's post with 👍 23 days ago

Post

1121

this paper is like when you tell an art student just draw it in your own style and they actually do it perfectly on the first try 🎨 diffusion models getting too powerful fr

https://www.aimodels.fyi/papers/arxiv/diffusion-self-distillation-zero-shot-customized-image