Pablo-Flores-Mollinedo
/

verilog-qwen2.5-coder-7b-v16-pilot-5k-from-v9-lora

Model card Files Files and versions

Verilog Qwen2.5-Coder 7B v16 Pilot 5K from v9 LoRA

Continuation from v9 with retention mix plus 5K verified synthetic_v2 pilot examples.

VerilogEval v2 direct result:

Compile: 138/156 = 88.46%
Functional pass: 60/156 = 38.46%

Caveat: benchmark-targeted research adapter. Not a clean zero-shot leaderboard claim.

Downloads last month: 5

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Pablo-Flores-Mollinedo/verilog-qwen2.5-coder-7b-v16-pilot-5k-from-v9-lora

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-Coder-7B

Finetuned

Qwen/Qwen2.5-Coder-7B-Instruct

Adapter

(734)

this model