Csaba Kecskemeti PRO

csabakecskemeti's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

updated a model about 4 hours ago

DevQuasar/allenai.Llama-3.1-Tulu-3-8B-GGUF

Text Generation • Updated about 4 hours ago • 26

updated a model about 5 hours ago

DevQuasar/AIDC-AI.Marco-o1-GGUF

Text Generation • Updated about 5 hours ago • 18

updated a model about 16 hours ago

DevQuasar/INSAIT-Institute.BgGPT-Gemma-2-27B-IT-v1.0-GGUF

Text Generation • Updated about 16 hours ago • 123 • 1

updated a model about 19 hours ago

DevQuasar/mistralai.Mistral-Large-Instruct-2411-GGUF

Updated about 19 hours ago • 143

updated 3 models 1 day ago

DevQuasar/Zhengyi.LLaMA-Mesh-GGUF

Text Generation • Updated 1 day ago • 160

DevQuasar/lassoued.legalllama2-GGUF

Text Generation • Updated 1 day ago • 154

DevQuasar/INSAIT-Institute.BgGPT-Gemma-2-2.6B-IT-v1.0-GGUF

Text Generation • Updated 1 day ago • 125

liked a model 2 days ago

sarpba/whisper-base-hungarian_v1

Automatic Speech Recognition • Updated Oct 20 • 106 • 3

liked a dataset 3 days ago

MaziyarPanahi/orca-agentinstruct-1M-v1-cleaned-fixed-sharegpt

Viewer • Updated 3 days ago • 1.05M • 59 • 4

updated a model 4 days ago

DevQuasar/mistralai.Mistral-Large-Instruct-2411-GGUF

Updated about 19 hours ago • 143

Reacted to fdaudens's post with 😎 4 days ago

view post

Post

1544

Reply

🚀 @Qwen just dropped 2.5-Turbo!

1M token context (that's entire "War and Peace"!) + 4.3x faster processing speed. Same price, way more power 🔥

Check out the demo: Qwen/Qwen2.5-Turbo-1M-Demo

#QWEN

• 

🚀

8

8

😎

2

2

+

New activity in DevQuasar/Synthetic-Cyclic-Perception_exp1 4 days ago

[bot] Conversion to Parquet

#1 opened 27 days ago by parquet-converter

updated a model 4 days ago

DevQuasar/hpcgroup.hpc-coder-v2-16b-GGUF

Text Generation • Updated 4 days ago • 138

updated 3 models 5 days ago

DevQuasar/hpcgroup.hpc-coder-v2-6.7b-GGUF

Text Generation • Updated 5 days ago • 107

DevQuasar/hpcgroup.hpc-coder-v2-1.3b-GGUF

Text Generation • Updated 5 days ago • 108

DevQuasar/Qwen.Qwen2.5-Coder-32B-Instruct-GGUF

Text Generation • Updated 5 days ago • 729

posted an update 5 days ago

view post

Post

1196

Reply

Some time ago, I built a predictive LLM router that routes chat requests between small and large LLM models based on prompt classification. It dynamically selects the most suitable model depending on the complexity of the user input, ensuring optimal performance while maintaining conversation context. I also fine-tuned a RoBERTa model to use with the package, but you can plug and play any classifier of your choice.

Project's homepage:
https://devquasar.com/llm-predictive-router/
Pypi:
https://pypi.org/project/llm-predictive-router/
Model:
DevQuasar/roberta-prompt_classifier-v0.1
Training data:
DevQuasar/llm_router_dataset-synth
Git:
https://github.com/csabakecskemeti/llm_predictive_router_package

Feel free to check it out, and/or contribute.

👍

7

7

+

updated 3 models 5 days ago

DevQuasar/numind.NuExtract-1.5-smol-GGUF

Text Generation • Updated 5 days ago • 112

DevQuasar/numind.NuExtract-1.5-smol-GGUF

Text Generation • Updated 5 days ago • 112

DevQuasar/Nexusflow.Athene-V2-Chat-GGUF

Text Generation • Updated 5 days ago • 276 • 1