BucketOfFish
/

simplified_phi2

Text Generation

feature-extraction

Model card Files Files and versions Community

simplified_phi2

Commit History

Got output to match Phi2 exactly

3649bbb

BucketOfFish commited on Jan 6

Fixed inference script bug and made deterministic

4f25dda

BucketOfFish commited on Jan 6

Passing KV cache through iterations

c07c430

BucketOfFish commited on Jan 6

Edited comments

455129a

BucketOfFish commited on Jan 2

Added YAML to README

76e8ee6

BucketOfFish commited on Jan 2

Updated README

32d8f06

BucketOfFish commited on Jan 2

Corrected rotary embedding

df388cc

BucketOfFish commited on Jan 2

Corrected param name

c572a14

BucketOfFish commited on Jan 2

Got model running, but results are incorrect

0f3418e

BucketOfFish commited on Jan 2

Fixed weight loading from original Phi2 model

10aca20

BucketOfFish commited on Jan 2

Renaming state dict keys from Phi2

78f6f3b

BucketOfFish commited on Jan 2

Updated imports in script

16cc769

BucketOfFish commited on Jan 2

Just uploading entire rewritten codebase at once

a420fe7

BucketOfFish commited on Jan 2

Another small fix

41127ee

BucketOfFish commited on Jan 2

Rotary embedding correction

2380737

BucketOfFish commited on Jan 2

Simplified rotary embedding

3c52426

BucketOfFish commited on Jan 2

Removed all flash_attn usage

5e8c4af

BucketOfFish commited on Jan 2

Revert "Removed non-flash configs"

8a5eabe

BucketOfFish commited on Jan 2

Revert "Removed non-flash classes"

7c0c66d

BucketOfFish commited on Jan 2

Removed non-flash configs

23b970e

BucketOfFish commited on Jan 2

Removed non-flash classes

6be42f2

BucketOfFish commited on Jan 2

Removed output check

7da2fc9

BucketOfFish commited on Jan 2

Streaming inference script

dc6124b

BucketOfFish commited on Jan 2

Copy of Phi2

89d375e

BucketOfFish commited on Jan 2