 Alex Cheema
|
8ad19a5f53
Merge pull request #221 from exo-explore/qwen2.5
|
1 rok temu |
 Alex Cheema
|
68028cc980
ignore Qwen models in tokenizers test until bos issue is fixed
|
1 rok temu |
|
Alex Cheema
|
dee83e4840
add more qwen2.5 models: mlx-community/Qwen2.5-7B-Instruct-4bit mlx-community/Qwen2.5-Math-7B-Instruct-4bit mlx-community/Qwen2.5-72B-Instruct-4bit mlx-community/Qwen2.5-Math-72B-Instruct-4bit
|
1 rok temu |
|
Alex Cheema
|
3597fba356
add support for qwen2.5, initially adding mlx-community/Qwen2.5-14B-Instruct-4bit
|
1 rok temu |
|
Alex Cheema
|
db9f44d16d
website link
|
1 rok temu |
|
Alex Cheema
|
6c875dcc81
update hiring link
|
1 rok temu |
|
Alex Cheema
|
074228e326
update README with hiring
|
1 rok temu |
|
Alex Cheema
|
198cd6fb17
trigger ci
|
1 rok temu |
|
Alex Cheema
|
20522e0638
update docs to make tinygrad usage clearer
|
1 rok temu |
|
Alex Cheema
|
e0ed9170db
Merge pull request #209 from GaetanLepage/used-ports
|
1 rok temu |
 Gaetan Lepage
|
4b009401f9
move `.exo_used_ports` to `/tmp`
|
1 rok temu |
|
Alex Cheema
|
0fa15367f7
Merge pull request #208 from exo-explore/broken_links_readme
|
1 rok temu |
|
Alex Cheema
|
ca64456260
fix broken links in README
|
1 rok temu |
|
Alex Cheema
|
87e08f89f1
Merge pull request #203 from exo-explore/non_blocking
|
1 rok temu |
|
Alex Cheema
|
874886abc4
simplify mlx non blocking
|
1 rok temu |
|
Alex Cheema
|
e616d4e86b
run realize on the result in tinygrad
|
1 rok temu |
|
Alex Cheema
|
9345684b38
closely match prev impl mlx non blocking
|
1 rok temu |
|
Alex Cheema
|
d6e661fd69
match previous impl with np.array in mlx
|
1 rok temu |
|
Alex Cheema
|
caf9b57a2a
trigger ci
|
1 rok temu |
|
Alex Cheema
|
84187113de
add a test for hf get_weight_map
|
1 rok temu |
|
Alex Cheema
|
4ec613d4e8
simplify tinygrad non blocking
|
1 rok temu |
|
Alex Cheema
|
6342384df4
Merge branch 'main' into non_blocking
|
1 rok temu |
|
Alex Cheema
|
a1a0ffac55
add tinychat option for llama-3.1-70b-bf16
|
1 rok temu |
|
Alex Cheema
|
de19f0ab42
Merge branch 'main' into non_blocking
|
1 rok temu |
|
Alex Cheema
|
2948a83448
add llama-3.1-70b-bf16 model option
|
1 rok temu |
|
Alex Cheema
|
11dd952d26
use set for shard specific patterns
|
1 rok temu |
|
Alex Cheema
|
ea3322dea4
remove comment
|
1 rok temu |
|
Alex Cheema
|
e0fda94d20
use sets for shard specific patterns
|
1 rok temu |
|
Alex Cheema
|
b239c8a6d0
Merge branch 'main' into non_blocking
|
1 rok temu |
|
Alex Cheema
|
8f65e1e697
fix weight_map resolution. previously we were always defaulting to allow pattern *.safetensors
|
1 rok temu |
