stellaathena commited on
Commit
b7076fa
·
verified ·
1 Parent(s): ac0bd7b

Update model card for log-spaced checkpoints

Browse files
Files changed (1) hide show
  1. README.md +5 -2
README.md CHANGED
@@ -28,14 +28,17 @@ Each branch contains a full training checkpoint at a given step, including:
28
 
29
  ## Branches
30
 
31
- 154 checkpoints are available as branches:
32
 
33
  - `step0` — initialization
34
  - `step{1,2,4,8,16,32,64,128,256,512}` — log-spaced early checkpoints
35
- - `step1000` through `step143000` every 1,000 steps
 
36
 
37
  Branch `step143000` corresponds to the final model.
38
 
 
 
39
  ## Converting to HuggingFace Format
40
 
41
  To convert a checkpoint to HuggingFace Transformers format, use the conversion script from [GPT-NeoX](https://github.com/EleutherAI/gpt-neox):
 
28
 
29
  ## Branches
30
 
31
+ 20 log-spaced checkpoints are available as branches:
32
 
33
  - `step0` — initialization
34
  - `step{1,2,4,8,16,32,64,128,256,512}` — log-spaced early checkpoints
35
+ - `step{1000,2000,4000,8000,16000,32000,64000,128000}` — log-spaced training checkpoints
36
+ - `step143000` — final model
37
 
38
  Branch `step143000` corresponds to the final model.
39
 
40
+ > **Note:** To keep storage requirements manageable, this repository provides a log-spaced subset of 20 checkpoints rather than all 154 training checkpoints. If you need linearly-spaced checkpoints (every 1,000 steps), the HuggingFace Transformers-compatible weights for all 154 checkpoints are available at [`EleutherAI/pythia-2.8b`](https://huggingface.co/EleutherAI/pythia-2.8b).
41
+
42
  ## Converting to HuggingFace Format
43
 
44
  To convert a checkpoint to HuggingFace Transformers format, use the conversion script from [GPT-NeoX](https://github.com/EleutherAI/gpt-neox):