From 3a3d662e32a11db7dbe7e7b623ccf497a12317d5 Mon Sep 17 00:00:00 2001 From: Charlie Ruan <53290280+CharlieFRuan@users.noreply.github.com> Date: Wed, 25 Sep 2024 17:17:19 -0400 Subject: [PATCH] [Llama] Add Llama3.2 Instruct 1B 3B to preset --- src/config.ts | 80 ++++++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 79 insertions(+), 1 deletion(-) diff --git a/src/config.ts b/src/config.ts index 3d11b5e0..77aa56f0 100644 --- a/src/config.ts +++ b/src/config.ts @@ -308,7 +308,85 @@ export const functionCallingModelIds = [ export const prebuiltAppConfig: AppConfig = { useIndexedDBCache: false, model_list: [ - // Llama-3 + { + model: "https://huggingface.co/mlc-ai/Llama-3.2-1B-Instruct-q4f32_1-MLC", + model_id: "Llama-3.2-1B-Instruct-q4f32_1-MLC", + model_lib: + modelLibURLPrefix + + modelVersion + + "/Llama-3.2-1B-Instruct-q4f32_1-ctx4k_cs1k-webgpu.wasm", + vram_required_MB: 1128.82, + low_resource_required: true, + overrides: { + context_window_size: 4096, + }, + }, + { + model: "https://huggingface.co/mlc-ai/Llama-3.2-1B-Instruct-q4f16_1-MLC", + model_id: "Llama-3.2-1B-Instruct-q4f16_1-MLC", + model_lib: + modelLibURLPrefix + + modelVersion + + "/Llama-3.2-1B-Instruct-q4f16_1-ctx4k_cs1k-webgpu.wasm", + vram_required_MB: 879.04, + low_resource_required: true, + overrides: { + context_window_size: 4096, + }, + }, + { + model: "https://huggingface.co/mlc-ai/Llama-3.2-1B-Instruct-q0f32-MLC", + model_id: "Llama-3.2-1B-Instruct-q0f32-MLC", + model_lib: + modelLibURLPrefix + + modelVersion + + "/Llama-3.2-1B-Instruct-q0f32-ctx4k_cs1k-webgpu.wasm", + vram_required_MB: 5106.26, + low_resource_required: true, + overrides: { + context_window_size: 4096, + }, + }, + { + model: "https://huggingface.co/mlc-ai/Llama-3.2-1B-Instruct-q0f16-MLC", + model_id: "Llama-3.2-1B-Instruct-q0f16-MLC", + model_lib: + modelLibURLPrefix + + modelVersion + + "/Llama-3.2-1B-Instruct-q0f16-ctx4k_cs1k-webgpu.wasm", + vram_required_MB: 2573.13, + low_resource_required: true, + overrides: { + context_window_size: 4096, + }, + }, + { + model: "https://huggingface.co/mlc-ai/Llama-3.2-3B-Instruct-q4f32_1-MLC", + model_id: "Llama-3.2-3B-Instruct-q4f32_1-MLC", + model_lib: + modelLibURLPrefix + + modelVersion + + "/Llama-3.2-3B-Instruct-q4f32_1-ctx4k_cs1k-webgpu.wasm", + vram_required_MB: 2951.51, + low_resource_required: true, + overrides: { + context_window_size: 4096, + }, + }, + { + model: "https://huggingface.co/mlc-ai/Llama-3.2-3B-Instruct-q4f16_1-MLC", + model_id: "Llama-3.2-3B-Instruct-q4f16_1-MLC", + model_lib: + modelLibURLPrefix + + modelVersion + + "/Llama-3.2-3B-Instruct-q4f16_1-ctx4k_cs1k-webgpu.wasm", + vram_required_MB: 2263.69, + low_resource_required: true, + overrides: { + context_window_size: 4096, + }, + }, + // Llama-3.1 { model: "https://huggingface.co/mlc-ai/Llama-3.1-8B-Instruct-q4f32_1-MLC", model_id: "Llama-3.1-8B-Instruct-q4f32_1-MLC-1k",