 Nel Nibcord
|
82cce4408e
Some initial inference engine refactors for enabling training
|
10 mesi fa |
 Alex Cheema
|
4713bc5acd
Merge pull request #431 from exo-explore/qwen32b
|
10 mesi fa |
 Alex Cheema
|
e9ba815c21
add qwen2.5 coder 3b,14b,32b
|
10 mesi fa |
|
Alex Cheema
|
a0b6adad85
Merge pull request #430 from austinbv/patch-1
|
10 mesi fa |
 Austin
|
5435671cd9
Add 32b Qwen 2.5
|
10 mesi fa |
|
Alex Cheema
|
526f8a7ad5
Merge pull request #429 from exo-explore/readme_hf_home
|
10 mesi fa |
|
Alex Cheema
|
167e756b31
add documentation of HF_HOME model storage location in README. fixes #427
|
10 mesi fa |
|
Alex Cheema
|
b41b7d778a
Merge pull request #426 from exo-explore/tinygrad_ci_test
|
10 mesi fa |
|
Alex Cheema
|
9e4366f36b
tinygrad ci
|
10 mesi fa |
|
Alex Cheema
|
6cd78b94d4
run tinygrad test with CLANG=1
|
10 mesi fa |
|
Alex Cheema
|
49c4394dfa
enable tinygrad test
|
10 mesi fa |
|
Alex Cheema
|
77d78935b7
remove redundant expected_content
|
10 mesi fa |
|
Alex Cheema
|
8cc3f51e79
test for tinygrad e2e
|
10 mesi fa |
|
Alex Cheema
|
858421a3a7
Merge pull request #418 from BatSmacker84/llama-3.2-support
|
10 mesi fa |
|
Alex Cheema
|
832a860b34
Merge pull request #424 from exo-explore/llama405b-8bit
|
10 mesi fa |
|
Alex Cheema
|
472359147d
ignore 8bit llama 405b from tokenizers test
|
10 mesi fa |
|
Alex Cheema
|
49833e1fde
Merge pull request #423 from exo-explore/llama405b-8bit
|
10 mesi fa |
|
Alex Cheema
|
98948441e3
add llama 3.1 405b 8bit at mlx-community/Meta-Llama-3.1-405B-Instruct-8bit
|
10 mesi fa |
|
Alex Cheema
|
5133885095
Merge pull request #422 from samiamjidkhan/history-button
|
10 mesi fa |
 Sami Khan
|
0d8a1ee41e
Added clear all history button
|
10 mesi fa |
|
Alex Cheema
|
f1c74732d5
m4 device capabilities
|
10 mesi fa |
|
Alex Cheema
|
815529867e
Merge pull request #419 from exo-explore/gemma
|
10 mesi fa |
|
Alex Cheema
|
fcaebd3b50
add Gemma2 9b and Gemma2 27bg
|
10 mesi fa |
|
Alex Cheema
|
83d4d2b3d8
update mlx to 0.20.0, mlx-lm to 0.19.3
|
10 mesi fa |
 Ogden Wells
|
fbec1d2b10
formatted changes
|
10 mesi fa |
|
Ogden Wells
|
af01b23a07
added rope_scaling and tie_word_embeddings to llama transformer
|
10 mesi fa |
|
Ogden Wells
|
029dc5f8a7
added new model info for 1B and 3B model sizes
|
10 mesi fa |
|
Alex Cheema
|
e80ed76c03
ignore in test-tokenizers
|
10 mesi fa |
|
Alex Cheema
|
36c1f68cc7
update llama-3.1-405b-8bit model id to IntuitIntel/Meta-Llama-3.1-405B-Instruct-8bit
|
10 mesi fa |
|
Alex Cheema
|
c8438b6d23
add llama-3.1-405b-8bit
|
10 mesi fa |
