anemll
/

anemll-meta-llama-Llama-3.2-1B-Instruct-ctx1024_0.3.4

Apple Neural Engine

Model card Files Files and versions Community

anemll commited on Jul 3

Commit

394dbf8

·

verified ·

1 Parent(s): 86e1dcb

Update README.md

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -15,12 +15,11 @@ tags:
 meta-llama/Llama-3.2-1B-Instruct
 | Task          | HF-FP16 | ANEMLL-LUT6 | DIFF % |
-|---------------|---------|----------------------|
 | arc_challenge | 35.58%  | 33.87%      | -1.71% |
 | arc_easy      | 68.69%  | 68.14%      | -0.55% |
 | boolq         | 69.45%  | 67.34%      | -2.11% |
 **ANEMLL** (pronounced like "animal") is an open-source project focused on accelerating the porting of Large Language Models (LLMs) to tensor processors, starting with the Apple Neural Engine (ANE).
 The goal is to provide a fully open-source pipeline from model conversion to inference for common LLM architectures running on ANE.

 meta-llama/Llama-3.2-1B-Instruct
 | Task          | HF-FP16 | ANEMLL-LUT6 | DIFF % |
+|---------------|---------|-------------|--------|
 | arc_challenge | 35.58%  | 33.87%      | -1.71% |
 | arc_easy      | 68.69%  | 68.14%      | -0.55% |
 | boolq         | 69.45%  | 67.34%      | -2.11% |
 **ANEMLL** (pronounced like "animal") is an open-source project focused on accelerating the porting of Large Language Models (LLMs) to tensor processors, starting with the Apple Neural Engine (ANE).
 The goal is to provide a fully open-source pipeline from model conversion to inference for common LLM architectures running on ANE.