ermiaazarkhalili/wordle-grpo-qwen3-0-6b-bucket
570 kB
🔄 In a Training Loop
Behrooz Azarkhalili
ermiaazarkhalili
AI & ML interests
LLMs, VLMs, PEFT, RL for LLMs and VLMs.
Recent Activity
liked a Space 1 day ago
townbox/deepseek-profile-guide liked a dataset 3 days ago
songlab/gpn-star-scores updated a model 6 days ago
ermiaazarkhalili/Qwen3.8-9B-SFT-Fable5-GGUFOrganizations
buckets 10
ermiaazarkhalili/reasoning-gym-chain-sum-qwen3-0-6b-grpo-bucket
1.35 MB
ermiaazarkhalili/huggingface-static-ea28bf-bucket
224 kB
ermiaazarkhalili/huggingface-static-811ae1-bucket
590 kB
ermiaazarkhalili/reasoning-gym-chain-sum-qwen3-1-7b-grpo-bucket
4.49 MB
ermiaazarkhalili/huggingface-static-c0c0a8-bucket
446 kB
-
yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF
Text Generation • 12B • Updated • 511k • 2.89k -
yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF
Text Generation • 12B • Updated • 664k • 1.56k -
empero-ai/Qwythos-9B-Claude-Mythos-5-1M
Text Generation • 9B • Updated • 20.7k • • 936
-
yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF
Text Generation • 12B • Updated • 511k • 2.89k -
yuxinlu1/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF
Text Generation • 12B • Updated • 664k • 1.56k -
empero-ai/Qwythos-9B-Claude-Mythos-5-1M
Text Generation • 9B • Updated • 20.7k • • 936
Curated SFT datasets for instruction-following and conversational fine-tuning
spaces 9
Paused
Agents
Wordle Grpo Qwen3 0 6b
🎯
Sleeping
RL
TextArena Environment Server
🎮
Play Wordle by entering guesses and see results live
Running
Huggingface Static Ea28bf
🎯
Explore your data with an interactive Trackio dashboard
Sleeping
Agents
Reasoning Gym Chain Sum Qwen3 0 6b Grpo
🎯
Display experiment tracking results
Running
Huggingface Static 811ae1
🎯
View and monitor your tracked data in a dashboard
Running
Huggingface Static C0c0a8
🎯
View and monitor your tracking data in an interactive dashboard
models 223
ermiaazarkhalili/Qwen3.8-9B-SFT-Fable5-GGUF
9B • Updated • 475
ermiaazarkhalili/Qwen3.8-9B-SFT-Fable5
Image-Text-to-Text • 10B • Updated • 29
ermiaazarkhalili/Qwen3.8-2B-SFT-Fable5-GGUF
Text Generation • 2B • Updated • 342
ermiaazarkhalili/Qwen3.8-2B-SFT-Fable5
Text Generation • 2B • Updated • 385
ermiaazarkhalili/FastContext-4B-RL_base-SFT-Claude-Opus-Reasoning-Unsloth-GGUF
Text Generation • 4B • Updated • 350
ermiaazarkhalili/FastContext-4B-SFT_base-SFT-Claude-Opus-Reasoning-Unsloth-GGUF
Text Generation • 4B • Updated • 325
ermiaazarkhalili/FastContext-4B-SFT_base-Function-Calling-xLAM-Unsloth-GGUF
Text Generation • 4B • Updated • 364
ermiaazarkhalili/FastContext-4B-RL_base-Function-Calling-xLAM-Unsloth-GGUF
Text Generation • 4B • Updated • 209
ermiaazarkhalili/VibeThinker-3B-Function-Calling-xLAM-Unsloth-GGUF
Text Generation • 3B • Updated • 309 • 1
ermiaazarkhalili/VibeThinker-3B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF
Text Generation • 3B • Updated • 529 • 3
datasets 8
ermiaazarkhalili/wordle-grpo-runs
Updated • 6
ermiaazarkhalili/datasets-genbank-test
Updated • 9
ermiaazarkhalili/alpaca-gpt4-short-100tok
Viewer • Updated • 5k • 29
ermiaazarkhalili/orca-mini-short-100tok
Viewer • Updated • 5k • 25
ermiaazarkhalili/orca-mini-v1-high-prob-qwen-0.5b-10k
Viewer • Updated • 10k • 5
ermiaazarkhalili/alpaca-gpt4-en-high-prob-qwen-0.5b-10k
Viewer • Updated • 10k • 7
ermiaazarkhalili/alpaca-cleaned-high-prob-qwen-0.5b-10k
Viewer • Updated • 10k • 6
ermiaazarkhalili/alpaca-high-prob-qwen-0.5b-10k
Viewer • Updated • 10k • 20