update llama-3.1-405b-8bit model id to IntuitIntel/Meta-Llama-3.1-405B-Instruct-8bit

36c1f68cc77fe7f9228ae8ce84716b6c3639a66c · 2024-11-06 12:43:57 +0400 · Alex Cheema

Files touched

M exo/models.py

Diff

commit 36c1f68cc77fe7f9228ae8ce84716b6c3639a66c
Author: Alex Cheema <alexcheema123@gmail.com>
Date:   Wed Nov 6 12:43:57 2024 +0400

    update llama-3.1-405b-8bit model id to IntuitIntel/Meta-Llama-3.1-405B-Instruct-8bit
---
 exo/models.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/exo/models.py b/exo/models.py
index e512f918..e05d79fc 100644
--- a/exo/models.py
+++ b/exo/models.py
@@ -17,7 +17,7 @@ model_base_shards = {
     "TinygradDynamicShardInferenceEngine": Shard(model_id="NousResearch/Meta-Llama-3.1-70B-Instruct", start_layer=0, end_layer=0, n_layers=80),
   },
   "llama-3.1-405b": {"MLXDynamicShardInferenceEngine": Shard(model_id="mlx-community/Meta-Llama-3.1-405B-4bit", start_layer=0, end_layer=0, n_layers=126),},
-  "llama-3.1-405b-8bit": {"MLXDynamicShardInferenceEngine": Shard(model_id="IntuitIntel/Llama-3.1-405B-Instruct", start_layer=0, end_layer=0, n_layers=126),},
+  "llama-3.1-405b-8bit": {"MLXDynamicShardInferenceEngine": Shard(model_id="IntuitIntel/Meta-Llama-3.1-405B-Instruct-8bit", start_layer=0, end_layer=0, n_layers=126),},
   "llama-3-8b": {
     "MLXDynamicShardInferenceEngine": Shard(model_id="mlx-community/Meta-Llama-3-8B-Instruct-4bit", start_layer=0, end_layer=0, n_layers=32),
     "TinygradDynamicShardInferenceEngine": Shard(model_id="TriAiExperiments/SFR-Iterative-DPO-LLaMA-3-8B-R", start_layer=0, end_layer=0, n_layers=32),

← c8438b6d add llama-3.1-405b-8bit · back to Exo · ignore in test-tokenizers e80ed76c →