 Alex Cheema
|
6cd78b94d4
run tinygrad test with CLANG=1
|
8 bulan lalu |
|
Alex Cheema
|
49c4394dfa
enable tinygrad test
|
8 bulan lalu |
|
Alex Cheema
|
77d78935b7
remove redundant expected_content
|
8 bulan lalu |
|
Alex Cheema
|
8cc3f51e79
test for tinygrad e2e
|
8 bulan lalu |
 Alex Cheema
|
858421a3a7
Merge pull request #418 from BatSmacker84/llama-3.2-support
|
8 bulan lalu |
|
Alex Cheema
|
832a860b34
Merge pull request #424 from exo-explore/llama405b-8bit
|
8 bulan lalu |
|
Alex Cheema
|
472359147d
ignore 8bit llama 405b from tokenizers test
|
8 bulan lalu |
|
Alex Cheema
|
49833e1fde
Merge pull request #423 from exo-explore/llama405b-8bit
|
8 bulan lalu |
|
Alex Cheema
|
98948441e3
add llama 3.1 405b 8bit at mlx-community/Meta-Llama-3.1-405B-Instruct-8bit
|
8 bulan lalu |
|
Alex Cheema
|
5133885095
Merge pull request #422 from samiamjidkhan/history-button
|
8 bulan lalu |
 Sami Khan
|
0d8a1ee41e
Added clear all history button
|
8 bulan lalu |
|
Alex Cheema
|
f1c74732d5
m4 device capabilities
|
8 bulan lalu |
|
Alex Cheema
|
815529867e
Merge pull request #419 from exo-explore/gemma
|
8 bulan lalu |
|
Alex Cheema
|
fcaebd3b50
add Gemma2 9b and Gemma2 27bg
|
8 bulan lalu |
|
Alex Cheema
|
83d4d2b3d8
update mlx to 0.20.0, mlx-lm to 0.19.3
|
8 bulan lalu |
 Ogden Wells
|
fbec1d2b10
formatted changes
|
8 bulan lalu |
|
Ogden Wells
|
af01b23a07
added rope_scaling and tie_word_embeddings to llama transformer
|
8 bulan lalu |
|
Ogden Wells
|
029dc5f8a7
added new model info for 1B and 3B model sizes
|
8 bulan lalu |
|
Alex Cheema
|
e80ed76c03
ignore in test-tokenizers
|
8 bulan lalu |
|
Alex Cheema
|
36c1f68cc7
update llama-3.1-405b-8bit model id to IntuitIntel/Meta-Llama-3.1-405B-Instruct-8bit
|
8 bulan lalu |
|
Alex Cheema
|
c8438b6d23
add llama-3.1-405b-8bit
|
8 bulan lalu |
|
Alex Cheema
|
6ae6ebeb05
revert back to CORRECTED
|
8 bulan lalu |
|
Alex Cheema
|
e8e05e15a1
remove CORRECTED llama 70b
|
8 bulan lalu |
|
Alex Cheema
|
436709e509
revert back to CORRECTED
|
8 bulan lalu |
|
Alex Cheema
|
8d524bfe71
change mlx-community/Meta-Llama-3.1-70B-Instruct-bf16-CORRECTED to mlx-community/Meta-Llama-3.1-70B-Instruct-bf16 since it works now
|
8 bulan lalu |
|
Alex Cheema
|
ab91f20296
Revert "add max-caches option"
|
8 bulan lalu |
|
Alex Cheema
|
9e3ae2b4b4
add max-caches option
|
8 bulan lalu |
|
Alex Cheema
|
bc7acfd37b
update mlx to 0.19.3, mlx-lm to 0.19.2
|
8 bulan lalu |
|
Alex Cheema
|
661035f0e0
use KVCache instead of RotatingKVCache
|
8 bulan lalu |
|
Alex Cheema
|
3d9c58464e
Merge pull request #403 from maujim/api/small-model-default
|
9 bulan lalu |
