Daniel Han-Chen
|
334c5ed1f0
|
Update llama.py
|
2024-02-01 22:48:54 +11:00 |
|
Daniel Han-Chen
|
cd39f6108f
|
lm_head
|
2024-02-01 22:34:33 +11:00 |
|
Daniel Han-Chen
|
24c4c37b7c
|
revert
|
2024-02-01 22:21:35 +11:00 |
|
Daniel Han-Chen
|
e791db9b06
|
Update llama.py
|
2024-02-01 20:12:59 +11:00 |
|
Daniel Han-Chen
|
1793a16c8f
|
faster inference
|
2024-02-01 20:03:54 +11:00 |
|
Daniel Han-Chen
|
19fb50e244
|
Update utils.py
|
2024-02-01 19:56:54 +11:00 |
|
Daniel Han-Chen
|
b83cea7cb4
|
Update llama.py
|
2024-02-01 19:56:06 +11:00 |
|
Daniel Han-Chen
|
8920cafbe7
|
inference
|
2024-02-01 19:46:38 +11:00 |
|
Daniel Han-Chen
|
38b59825b1
|
Update llama.py
|
2024-02-01 19:36:36 +11:00 |
|
Daniel Han-Chen
|
e8ec80a4c2
|
Update llama.py
|
2024-02-01 19:19:44 +11:00 |
|
Daniel Han-Chen
|
a2cb7a113b
|
Update llama.py
|
2024-02-01 19:07:30 +11:00 |
|
Daniel Han-Chen
|
a5ee70b63f
|
Update llama.py
|
2024-02-01 18:34:43 +11:00 |
|
Daniel Han-Chen
|
e2f0dd8683
|
Update llama.py
|
2024-02-01 18:16:46 +11:00 |
|
Daniel Han-Chen
|
3f0ddf0c7c
|
Update llama.py
|
2024-02-01 18:16:15 +11:00 |
|
Daniel Han-Chen
|
e90b3bf192
|
Update llama.py
|
2024-02-01 17:59:21 +11:00 |
|
Daniel Han-Chen
|
57044509ad
|
Update llama.py
|
2024-02-01 17:44:22 +11:00 |
|
Daniel Han-Chen
|
cf4b58eeb6
|
inference
|
2024-02-01 17:20:02 +11:00 |
|
Daniel Han-Chen
|
648c79ec1b
|
faster inference
|
2024-02-01 03:47:51 +11:00 |
|
Daniel Han-Chen
|
20f19391e6
|
Update mistral.py
|
2024-02-01 03:05:02 +11:00 |
|
Daniel Han-Chen
|
e2f72fe52f
|
Revert
|
2024-02-01 03:04:46 +11:00 |
|
Daniel Han-Chen
|
329f80ac4c
|
Update llama.py
|
2024-02-01 02:47:57 +11:00 |
|
Daniel Han-Chen
|
713a95ca0e
|
Inference
|
2024-02-01 02:46:26 +11:00 |
|
Daniel Han-Chen
|
acbdef7ff5
|
padding
|
2024-01-31 20:16:08 +11:00 |
|
Daniel Han-Chen
|
0dc26ed98a
|
Update llama.py
|
2024-01-31 20:06:28 +11:00 |
|
Daniel Han-Chen
|
9f31254539
|
Fix SDPA
|
2024-01-31 20:02:21 +11:00 |
|
Daniel Han-Chen
|
7227de48cf
|
Update llama.py
|
2024-01-31 19:48:33 +11:00 |
|
Daniel Han-Chen
|
5edad55b5d
|
Update llama.py
|
2024-01-31 19:44:19 +11:00 |
|
Daniel Han-Chen
|
c928c57aa9
|
Merge branch 'main' into nightly
|
2024-01-31 19:38:27 +11:00 |
|
Daniel Han
|
051a73b0e6
|
Hotfix - fix inference (#146)
* faster saving & inference
* Update llama.py
* Update save.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update mistral.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* fast inference
* Update llama.py
* Update save.py
* Update llama.py
* Mistral correct RoPE scaling
* Max sequence lengths
* Apache 2
* fast_linear_forward
* Update utils.py
* Update utils.py
* No print
* Update utils.py
* Update utils.py
* inference
* Update llama.py
* Fast inference RoPE
* Update llama.py
* Update llama.py
* RoPE
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* LoRA
* Fast LoRA saving
* Update llama.py
* hidden_states
* q_len == 1
* q_len issue
* Update mistral.py
* Update mistral.py
* incorrect inference
* Update to transformers 4.37
* Graceful FA2 error + torch 2.1.1
* Update mapper.py
* Update pyproject.toml
* Fix saving and bnb-4bit
* Update fast_lora.py
* Update fast_lora.py
* remove patching
* Update llama.py
* Update llama.py
* Update swiglu.py
* Repatch
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update llama.py
* Update fast_lora.py
* Update llama.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update swiglu.py
* Update fast_lora.py
* Update swiglu.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update save.py
* Update fast_lora.py
* Update utils.py
* Update llama.py
* Update fast_lora.py
* Update swiglu.py
* Update save.py
* Update save.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Revert "Update llama.py"
This reverts commit a208ec46e0.
* Update llama.py
* Works?
* Update pyproject.toml
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Swiglu
* Update swiglu.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update swiglu.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* attention_mask
* Update llama.py
* Update llama.py
* labels
* Update mistral.py
* Update llama.py
* attention mask
* Update save.py
* Update save.py
* Update mistral.py
* attention mask
* Update llama.py
* Update llama.py
* Update mistral.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update dpo.py
* Patch saving
* Update save.py
* Update save.py
* patch_saving_functions
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* print
* Mistral patch
* Update mistral.py
* Update save.py
* saving
* Update llama.py
* Update llama.py
* Fast inference repatch
* Update llama.py
* Update utils.py
* Update utils.py
* Update utils.py
* Update mistral.py
* Update __init__.py
* Fix inference
* Update mistral.py
* fast lm_head
* Remove fast path
* Update rope_embedding.py
* Update loader.py
* LlamaAttention_fast_forward_inference
* if past_key_value is not None and q_len == 1:
* revert inference
* Update loader.py
* past_key_value
|
2024-01-31 04:03:37 +11:00 |
|
Daniel Han-Chen
|
5da05558a0
|
past_key_value
|
2024-01-31 03:50:47 +11:00 |
|
Daniel Han-Chen
|
d347db0944
|
Update loader.py
|
2024-01-31 03:46:11 +11:00 |
|
Daniel Han-Chen
|
c0edaa46db
|
revert inference
|
2024-01-31 03:40:55 +11:00 |
|
Daniel Han-Chen
|
55fe6052ca
|
if past_key_value is not None and q_len == 1:
|
2024-01-31 03:36:40 +11:00 |
|
Daniel Han-Chen
|
248887b51c
|
LlamaAttention_fast_forward_inference
|
2024-01-31 03:35:24 +11:00 |
|
Daniel Han-Chen
|
c68a3bc9ec
|
Update loader.py
|
2024-01-31 03:28:30 +11:00 |
|
Daniel Han-Chen
|
44168377f3
|
Update rope_embedding.py
|
2024-01-31 01:32:56 +11:00 |
|
Daniel Han-Chen
|
270df81b60
|
Remove fast path
|
2024-01-30 17:33:08 +11:00 |
|
Daniel Han-Chen
|
b8f665bf22
|
fast lm_head
|
2024-01-30 17:26:45 +11:00 |
|
Daniel Han-Chen
|
ed5a653ecf
|
Update mistral.py
|
2024-01-30 04:16:39 +11:00 |
|
Daniel Han-Chen
|
e0bad0eec5
|
Fix inference
|
2024-01-30 04:10:14 +11:00 |
|
Daniel Han-Chen
|
71725aeea5
|
Update __init__.py
|
2024-01-30 03:23:42 +11:00 |
|
Daniel Han-Chen
|
3ddda6f492
|
Update mistral.py
|
2024-01-30 03:08:46 +11:00 |
|
Daniel Han-Chen
|
6f74c98fbc
|
Update utils.py
|
2024-01-29 23:19:43 +11:00 |
|
Daniel Han-Chen
|
a7bfeec919
|
Update utils.py
|
2024-01-29 23:14:51 +11:00 |
|
Daniel Han-Chen
|
7c87d60bc1
|
Update utils.py
|
2024-01-29 23:07:40 +11:00 |
|
Daniel Han-Chen
|
bb364204cc
|
Update llama.py
|
2024-01-29 20:09:59 +11:00 |
|
Daniel Han-Chen
|
4700d51916
|
Fast inference repatch
|
2024-01-29 19:55:40 +11:00 |
|
Daniel Han-Chen
|
58cabcbc06
|
Merge branch 'main' into nightly
|
2024-01-29 17:59:34 +11:00 |
|
Daniel Han-Chen
|
01b8162244
|
Merge branch 'main' into nightly
|
2024-01-29 17:49:57 +11:00 |
|
Daniel Han
|
0562464280
|
Fix inference attention mask (#142)
* faster saving & inference
* Update llama.py
* Update save.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update mistral.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* fast inference
* Update llama.py
* Update save.py
* Update llama.py
* Mistral correct RoPE scaling
* Max sequence lengths
* Apache 2
* fast_linear_forward
* Update utils.py
* Update utils.py
* No print
* Update utils.py
* Update utils.py
* inference
* Update llama.py
* Fast inference RoPE
* Update llama.py
* Update llama.py
* RoPE
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* LoRA
* Fast LoRA saving
* Update llama.py
* hidden_states
* q_len == 1
* q_len issue
* Update mistral.py
* Update mistral.py
* incorrect inference
* Update to transformers 4.37
* Graceful FA2 error + torch 2.1.1
* Update mapper.py
* Update pyproject.toml
* Fix saving and bnb-4bit
* Update fast_lora.py
* Update fast_lora.py
* remove patching
* Update llama.py
* Update llama.py
* Update swiglu.py
* Repatch
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update llama.py
* Update fast_lora.py
* Update llama.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update swiglu.py
* Update fast_lora.py
* Update swiglu.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update save.py
* Update fast_lora.py
* Update utils.py
* Update llama.py
* Update fast_lora.py
* Update swiglu.py
* Update save.py
* Update save.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update llama.py
* Revert "Update llama.py"
This reverts commit a208ec46e0.
* Update llama.py
* Works?
* Update pyproject.toml
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Swiglu
* Update swiglu.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update swiglu.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* Update fast_lora.py
* attention_mask
* Update llama.py
* Update llama.py
* labels
* Update mistral.py
* Update llama.py
* attention mask
* Update save.py
* Update save.py
* Update mistral.py
* attention mask
* Update llama.py
* Update llama.py
* Update mistral.py
* Update llama.py
* Update llama.py
* Update llama.py
* Update dpo.py
* Patch saving
* Update save.py
* Update save.py
* patch_saving_functions
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* Update save.py
* print
* Mistral patch
* Update mistral.py
* Update save.py
* saving
* Update llama.py
* Update llama.py
|
2024-01-29 17:49:54 +11:00 |
|