Skip to content

Commit 5315d01

Browse files
CharlieFRuanCharlieFRuan
authored
[WASM] Add qwen2.5 3B q4f16 and q4f32 to webllm (#138)
Compiled at: TVM: apache/tvm@1518008 MLC-LLM: mlc-ai/mlc-llm@2cbf393 Other QWen2.5 models can reuse Qwen2 models' WASMs.
1 parent 055f568 commit 5315d01

File tree

2 files changed

+0
-0
lines changed

2 files changed

+0
-0
lines changed

‎web-llm-models/v0_2_48/Qwen2.5-3B-Instruct-q4f16_1-ctx4k_cs1k-webgpu.wasm‎

4.17 MB
Binary file not shown.

‎web-llm-models/v0_2_48/Qwen2.5-3B-Instruct-q4f32_1-ctx4k_cs1k-webgpu.wasm‎

4.06 MB
Binary file not shown.

0 commit comments

Comments
 (0)