tim-lawson commited on
Commit
68bb4dc
1 Parent(s): 0e162e6

Push model using huggingface_hub.

Browse files
Files changed (2) hide show
  1. config.json +15 -4
  2. model.safetensors +2 -2
config.json CHANGED
@@ -1,9 +1,20 @@
1
  {
 
2
  "auxk": 256,
3
- "dead_steps_threshold": 76,
 
 
4
  "dead_threshold": 0.001,
 
 
5
  "k": 32,
6
- "n_inputs": 512,
7
- "n_latents": 32768,
8
- "standardize": true
 
 
 
 
 
 
9
  }
 
1
  {
2
+ "accumulate_grad_batches": 64,
3
  "auxk": 256,
4
+ "auxk_coef": 0.03125,
5
+ "batch_size": 1,
6
+ "dead_steps_threshold": null,
7
  "dead_threshold": 0.001,
8
+ "dead_tokens_threshold": 10000000,
9
+ "expansion_factor": 64,
10
  "k": 32,
11
+ "layers": [
12
+ 4
13
+ ],
14
+ "lr": 0.0001,
15
+ "max_length": 2048,
16
+ "model_name": "EleutherAI/pythia-70m-deduped",
17
+ "skip_special_tokens": true,
18
+ "standardize": true,
19
+ "tuned_lens": false
20
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63d547105b50688bf07855a64cf72b9f26b241f1d78f8eab195269bc71d30d43
3
- size 134220048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44f75c3a29034819428ccce5db1cb28182e28567dcd71318791415f2bb693d23
3
+ size 415936592