jon-tow commited on
Commit
118ff73
1 Parent(s): f5eaca1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -51,10 +51,10 @@ print(tokenizer.decode(tokens[0], skip_special_tokens=True))
51
 
52
  ## Training
53
 
54
- | Parameters | Hidden Size | Layers | Heads |
55
- |------------|-------------|--------|-------|
56
- | 3B | 5120 | 40 | 40 |
57
- | 7B | 5120 | 40 | 40 |
58
 
59
  ### Training Dataset
60
 
@@ -78,7 +78,7 @@ Models are learned via supervised fine-tuning on the aforementioned datasets, tr
78
 
79
  ### Intended Use
80
 
81
- These models are intended to be used by the open-source community for chat-like applications in adherence with the [CC BY-NC-SA-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license.
82
 
83
  ### Limitations and bias
84
 
 
51
 
52
  ## Training
53
 
54
+ | Parameters | Hidden Size | Layers | Heads | Sequence Length |
55
+ |------------|-------------|--------|-------|-----------------|
56
+ | 3B | 4096 | 16 | 32 | 4096 |
57
+ | 7B | 6144 | 16 | 48 | 4096 |
58
 
59
  ### Training Dataset
60
 
 
78
 
79
  ### Intended Use
80
 
81
+ These models are intended to be used by the open-source community chat-like applications in adherence with the [CC BY-NC-SA-4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) license.
82
 
83
  ### Limitations and bias
84