Behrooz Azarkhalili
ermiaazarkhalili
AI & ML interests
LLMs, VLMs, PEFT, RL for LLMs and VLMs.
Recent Activity
upvoted
an
article
3 days ago
Building Deep Research: How we Achieved State of the Art
upvoted
an
article
3 days ago
Smol2Operator: Post-Training GUI Agents for Computer Use
commented on
an
article
3 days ago
We Got Claude to Fine-Tune an Open Source LLM
Organizations
Qwen-Function-Calling-xLAM
-
ermiaazarkhalili/Qwen2.5-0.5B-Instruct_Function_Calling_xLAM
Text Generation • 0.5B • Updated • 17 -
ermiaazarkhalili/Qwen2.5-1.5B-Instruct_Function_Calling_xLAM
Text Generation • 2B • Updated • 14 -
ermiaazarkhalili/Qwen2.5-3B-Instruct_Function_Calling_xLAM
Text Generation • 3B • Updated • 8 -
ermiaazarkhalili/Qwen2.5-7B-Instruct_Function_Calling_xLAM
Text Generation • 8B • Updated • 8
VLMs
Llama-GRPO-GSM8K
Reasoning Datasets
Llama-Function_Calling-xLAM
-
ermiaazarkhalili/Llama-3.2-3B-Instruct_Function_Calling_xLAM
Text Generation • 3B • Updated • 5 -
ermiaazarkhalili/Llama-3-8B-Instruct_Function_Calling_xLAM
Text Generation • 8B • Updated • 3 -
ermiaazarkhalili/Llama-3.2-1B-Instruct_Function_Calling_xLAM
Text Generation • 1B • Updated • 8 -
ermiaazarkhalili/Llama-3.1-8B-Instruct_Function_Calling_xLAM
Text Generation • 8B • Updated • 6
Mistral-GRPO-GSM8K
Qwen2.5-GRPO-GSM8K
-
ermiaazarkhalili/qwen-2.5-14b-instruct_grpo-GSM8K
Text Generation • 15B • Updated • 7 -
ermiaazarkhalili/qwen-2.5-7b-instruct_grpo-GSM8K
Text Generation • 8B • Updated • 6 -
ermiaazarkhalili/qwen-2.5-3b-instruct_grpo-GSM8K
Text Generation • 3B • Updated • 7 -
ermiaazarkhalili/qwen-2.5-1.5b-instruct_grpo-GSM8K
Text Generation • 2B • Updated • 3
Multimodal Datasets
Reasoning Datasets
Qwen-Function-Calling-xLAM
-
ermiaazarkhalili/Qwen2.5-0.5B-Instruct_Function_Calling_xLAM
Text Generation • 0.5B • Updated • 17 -
ermiaazarkhalili/Qwen2.5-1.5B-Instruct_Function_Calling_xLAM
Text Generation • 2B • Updated • 14 -
ermiaazarkhalili/Qwen2.5-3B-Instruct_Function_Calling_xLAM
Text Generation • 3B • Updated • 8 -
ermiaazarkhalili/Qwen2.5-7B-Instruct_Function_Calling_xLAM
Text Generation • 8B • Updated • 8
Llama-Function_Calling-xLAM
-
ermiaazarkhalili/Llama-3.2-3B-Instruct_Function_Calling_xLAM
Text Generation • 3B • Updated • 5 -
ermiaazarkhalili/Llama-3-8B-Instruct_Function_Calling_xLAM
Text Generation • 8B • Updated • 3 -
ermiaazarkhalili/Llama-3.2-1B-Instruct_Function_Calling_xLAM
Text Generation • 1B • Updated • 8 -
ermiaazarkhalili/Llama-3.1-8B-Instruct_Function_Calling_xLAM
Text Generation • 8B • Updated • 6
VLMs
Mistral-GRPO-GSM8K
Llama-GRPO-GSM8K
Qwen2.5-GRPO-GSM8K
-
ermiaazarkhalili/qwen-2.5-14b-instruct_grpo-GSM8K
Text Generation • 15B • Updated • 7 -
ermiaazarkhalili/qwen-2.5-7b-instruct_grpo-GSM8K
Text Generation • 8B • Updated • 6 -
ermiaazarkhalili/qwen-2.5-3b-instruct_grpo-GSM8K
Text Generation • 3B • Updated • 7 -
ermiaazarkhalili/qwen-2.5-1.5b-instruct_grpo-GSM8K
Text Generation • 2B • Updated • 3