From 1bf33ef5819a5197052b02d3eae11a3be898e138 Mon Sep 17 00:00:00 2001 From: Thierry Moreau <tmoreau@octoml.ai> Date: Thu, 16 May 2024 11:08:25 -0400 Subject: [PATCH] adding missing file --- .../android_inference/mlc-package-config.json | 14 ++++++++++++++ 1 file changed, 14 insertions(+) create mode 100644 recipes/inference/mobile_inference/android_inference/mlc-package-config.json diff --git a/recipes/inference/mobile_inference/android_inference/mlc-package-config.json b/recipes/inference/mobile_inference/android_inference/mlc-package-config.json new file mode 100644 index 00000000..37de5e7b --- /dev/null +++ b/recipes/inference/mobile_inference/android_inference/mlc-package-config.json @@ -0,0 +1,14 @@ +{ + "device": "android", + "model_list": [ + { + "model": "HF://mlc-ai/Llama-3-8B-Instruct-q4f16_1-MLC", + "estimated_vram_bytes": 4348727787, + "model_id": "Llama-3-8B-Instruct", + "overrides": { + "context_window_size": 768, + "prefill_chunk_size": 256 + } + } + ] +} \ No newline at end of file -- GitLab