MLC-LLM
web-llm

Lema

Lemnal's strategy compiler: turns how traders describe a strategy into Lemnal's strategy spec. Qwen3-1.7B fine-tuned with LoRA, merged, and quantized with GPTQ into MLC's q4f16_1 format, so it runs in the browser with WebLLM using WebLLM's prebuilt Qwen3-1.7B q4f16_1 WebGPU library.

Built on Qwen3-1.7B by the Qwen team, Apache 2.0.

Downloads last month
24
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for ysnxf/lema

Finetuned
Qwen/Qwen3-1.7B
Quantized
(451)
this model