Fine-tuned models of all-miniLM model on the CoSQA dataset
Alessandro
Devy1
AI & ML interests
AI for Software Engineering
Recent Activity
authored a paper about 10 hours ago
No Resource, No Benchmarks, No Problem? Evaluating and Improving LLMs for Code Generation in No-Resource Languages updated a model 3 months ago
Devy1/Qwen2.5-Coder-CONTROL-checkpoints_python_only_2k-1.5B-Base-10 published a model 3 months ago
Devy1/Qwen2.5-Coder-CONTROL-checkpoints_python_only_2k-1.5B-Base-10Organizations
Collection of AQLM quantized models from the paper "Quantizing Large Language Models for Code Generation: A Differentiated Replication"
-
Quantizing Large Language Models for Code Generation: A Differentiated Replication
Paper • 2503.07103 • Published • 8 -
Devy1/CodeLlama-7b-hf-AQLM-8bit-rnd-4x15
Text Generation • 4B • Updated • 3 -
Devy1/CodeLlama-7b-hf-AQLM-4bit-rnd-2x15
Text Generation • 2B • Updated • 4 -
Devy1/CodeLlama-7b-hf-AQLM-3bit-rnd-2x12
Text Generation • 2B • Updated • 2
Fine-tuned models of all-miniLM model on the CoSQA dataset
Collection of AQLM quantized models from the paper "Quantizing Large Language Models for Code Generation: A Differentiated Replication"
-
Quantizing Large Language Models for Code Generation: A Differentiated Replication
Paper • 2503.07103 • Published • 8 -
Devy1/CodeLlama-7b-hf-AQLM-8bit-rnd-4x15
Text Generation • 4B • Updated • 3 -
Devy1/CodeLlama-7b-hf-AQLM-4bit-rnd-2x15
Text Generation • 2B • Updated • 4 -
Devy1/CodeLlama-7b-hf-AQLM-3bit-rnd-2x12
Text Generation • 2B • Updated • 2