Vaibhav Srivastav
06b7c45c59
Add URLs to HF MLX-Community org. ( #153 )
...
* up
* Add ref to MLX org on the README.
* nit: language.
* Standardise org name.
2023-12-20 06:57:13 -08:00
Pedro Cuenca
03720a270e
Add --model_path to phi-2 example script ( #152 )
2023-12-20 06:14:35 -08:00
Sarthak Yadav
0fb147650f
Added Keyword Spotting Transformer + SpeechCommands example ( #123 )
...
* Added Keyword Transformer + SpeechCommands
* minor fixes in README
* some updates / simplifications
* nits
* fixed kwt skip connections
* readme + format
* updated acknowledgements
---------
Co-authored-by: Awni Hannun <awni@apple.com>
2023-12-19 14:17:48 -08:00
Juarez Bochi
50a703eb3b
T5: Change default dtype to bfloat16 ( #147 )
...
* T5: Change default to bfloat16
* Add myself to contributors
* t5: Change convert.py default to float32
2023-12-19 13:44:36 -08:00
Junyi Mei
b439b96aa1
Add Qwen example ( #134 )
...
* Add qwen model draft
* Add readme and requirements for qwen example
* Add model and tokenizer options
* Fix convert and tokenizer
* some updates / style consistency
* move to llm subdir
* readme nit
---------
Co-authored-by: Awni Hannun <awni@apple.com>
2023-12-19 13:06:19 -08:00
Juarez Bochi
b5ff25716f
Add T5 and Flan-T5 example ( #113 )
...
* Add skeleton
* Load all encoder weights
* Pass config to all modules, fix ln
* Load position bias embeddings
* Load decoder weights
* Move position biases to attention module
* translate pytorch to mx
* Fix default prompt
* Fix relative_attention_max_distance config
* No scaling, no encoder mask
* LM head
* Decode (broken after 1st token)
* Use position bias in all layers
* Utils to compare encoder output
* Fix layer norm
* Fix decoder mask
* Use position bias in decoder
* Concatenate tokens
* Remove prints
* Stop on eos
* Measure tokens/s
* with cache
* bug fix with bidirectional only for encoder, add offset to position bias
* format
* Fix T5.__call__
* Stream output
* Add argument to generate float16 npz
* Load config from HF to support any model
* Uncomment bidirectional param
* Add gitignore
* Add readme.md for t5
* Fix relative position scale
* Fix --encode-only
* Run hf_t5 with any model
* Add hf generation for comparison
* Fix type for attention mask
* Increase hf max_length
* Rescale output before projecting on vocab
* readme updates
* nits
* Pass ln2 to cross attention
* Fix example
* Fix attention for 3b model
* fp16, abstract tokenizer a bit, format
* clamp for low precision
* higher clipping, remove non-helpful casts
* default to fp32 for now
* Adds support for flan-t5
* Update t5 docs on variant support
* readme flan
* nit
---------
Co-authored-by: Awni Hannun <awni@apple.com>
2023-12-18 20:25:34 -08:00
Awni Hannun
9063f1a1e3
fix use for llama 2 from meta ( #144 )
2023-12-18 19:33:17 -08:00
Daniel Strobusch
60c3bd9bc7
Pass few shot file name to --few-shot arg( #141 )
2023-12-18 13:30:04 -08:00
Awni Hannun
fd00c22224
Citation + contributor acknowledgments section ( #136 )
...
* citation + acks section
* nits
2023-12-18 10:12:35 -08:00
Daniel Strobusch
ca5a8ec273
fix renamed arg ( #140 )
2023-12-18 10:11:51 -08:00
Awni Hannun
17d2efaebe
support for tiny llama ( #129 )
2023-12-18 07:47:55 -08:00
Awni Hannun
6ae68777aa
Rope theta to support Coda Llama ( #121 )
...
* rope theta for llama model
* llama chat/code
* nit
2023-12-15 19:51:51 -08:00
Awni Hannun
376b273b2f
Merge pull request #115 from ml-explore/lora_custom
...
Customize dataset with lora
2023-12-15 13:54:58 -08:00
Awni Hannun
ad77bc4c3b
minimum version
2023-12-15 13:54:31 -08:00
Pawel Kowalski
4c88163941
Stable diffusion - check model weights shape and support int for "attention_head_dim" ( #85 )
...
* Allow integer as attention_head_dim
* Reshape downloaded weights to match model if there is a mismatch
2023-12-15 13:01:02 -08:00
Awni Hannun
fc13e96e6c
Merge pull request #116 from idoru/fix-phi-2-temp-arg
...
phi-2: fix --temp/--seed arguments.
2023-12-15 12:29:19 -08:00
Awni Hannun
e709b846ff
32 GB example
2023-12-15 12:20:15 -08:00
Awni Hannun
24a6de2acb
32 GB example
2023-12-15 12:18:29 -08:00
Sam Coward
a5bacfd04f
Pass along temp argument to generate()
2023-12-15 15:16:41 -05:00
Awni Hannun
f019d836ee
keep base weights in fp16
2023-12-15 10:42:18 -08:00
Awni Hannun
6dc067d30c
use lower precision base weights
2023-12-15 10:29:42 -08:00
Awni Hannun
4444c7a4a5
more nits
2023-12-15 10:06:14 -08:00
Awni Hannun
c889e09773
fix readme
2023-12-15 09:59:07 -08:00
Awni Hannun
9550e1de17
custom data with lora
2023-12-15 09:56:10 -08:00
Awni Hannun
7d4a41ace8
Merge pull request #112 from ml-explore/fix_mixtral
...
[Bugfix] Fix RoPE base bug in Mixtral example
2023-12-15 08:39:02 -08:00
Awni Hannun
737db11152
Merge pull request #108 from devonthomas35/phi2_eos
...
Phi-2: Stop generating at eos token
2023-12-15 07:34:11 -08:00
Awni Hannun
001b5803ce
fix RoPE bug + minor updates
2023-12-14 21:45:25 -08:00
devonthomas35
f6ac70c736
Refactor EOS check
2023-12-14 21:11:23 -08:00
Awni Hannun
12a5597ac3
Merge pull request #107 from ml-explore/hf_mixtral
...
Use official HF for mixtral
2023-12-14 16:57:19 -08:00
Awni Hannun
7cf66dc88c
format
2023-12-14 16:56:50 -08:00
devonthomas35
7f992db5bc
Remove unnecessary return
2023-12-14 15:52:22 -08:00
devonthomas35
8d496ba61a
Stop generating at eos token
2023-12-14 15:50:59 -08:00
Awni Hannun
6249f46215
incude instruct option
2023-12-14 15:40:38 -08:00
Awni Hannun
449f7a694b
use official HF for mixtral
2023-12-14 15:30:32 -08:00
Awni Hannun
95a1d50318
Merge pull request #106 from fahnub/main
...
minor dependency fix in phi-2
2023-12-14 14:15:19 -08:00
Fahad Nadeem
330e8e8bc9
minor dep fix in phi
2023-12-15 03:09:33 +05:00
Awni Hannun
53e58795c2
Merge pull request #77 from SarthakYadav/main
...
Added CIFAR-10 + ResNet example
2023-12-14 12:19:40 -08:00
Awni Hannun
e12e4d5825
typo / nits
2023-12-14 12:14:01 -08:00
Awni Hannun
5673716daa
updates + format
2023-12-14 12:09:10 -08:00
Awni Hannun
4cac181917
Merge pull request #103 from arpitingle/patch-1
...
added phi in readme
2023-12-14 10:19:40 -08:00
arpit
541265b74d
Update README.md
2023-12-14 23:40:50 +05:30
Awni Hannun
f4745d8576
Merge pull request #97 from jbarrow/main
...
Phi-2
2023-12-14 09:21:26 -08:00
Awni Hannun
fa9e34b041
cleanup conversion to use single qkv matrix
2023-12-14 09:19:44 -08:00
Awni Hannun
45c1800fc6
update readme
2023-12-14 08:37:34 -08:00
Awni Hannun
c2eb435697
change file name for consistency, update readme.
2023-12-14 08:34:24 -08:00
Awni Hannun
5822639f23
don't drop last tokens
2023-12-14 08:27:44 -08:00
Awni Hannun
c26eafc125
fix args, update README, remove extra files
2023-12-14 08:18:01 -08:00
Awni Hannun
05c82ddf5f
fix fp16 + nits
2023-12-14 08:08:28 -08:00
Sarthak Yadav
879a576fb6
updated header
2023-12-14 16:28:00 +01:00
Awni Hannun
bb44222a86
Merge pull request #98 from finnless/patch-1
...
Fix typo in stable_diffusion README
2023-12-14 07:13:19 -08:00
