manishkumar2101114
/

qwen3.5-9b-tool-prompts-merged

Text Generation

Model card Files Files and versions

Qwen3.5-9B tool-prompts merged

Base: Qwen/Qwen3.5-9B. Adapter: qwen3.5-9b-tool-prompts-adapter (LoRA r=32, alpha=64, 3 epochs, 666 steps, train_loss 0.2591, eval_loss 0.2003, prompts+hindi data). Merged full BF16 via merge_and_unload on CPU.

Downloads last month: -

Safetensors

Model size

10B params

Tensor type

BF16

·

Model tree for manishkumar2101114/qwen3.5-9b-tool-prompts-merged

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Finetuned

(993)

this model