Hugging Face's logo

ibm-granite
/
granite-3.0-1b-a400m-instruct

Text Generation
Transformers
Safetensors
granitemoe
language
granite-3.0
conversational
Eval Results
Model card Files Community
3
amezasor commited on
Commit
0643df2
·
verified ·
1 Parent(s): 43e5bb6

typo fix

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -327,7 +327,7 @@ Granite-3.0-1B-A400M-Instruct is based on a decoder-only sparse Mixture of Exper
327
  | Initialization std | 0.1 | 0.1 | **0.1** | 0.1 |
328
  | Sequence Length | 4096 | 4096 | **4096** | 4096 |
329
  | Position Embedding | RoPE | RoPE | **RoPE** | RoPE |
330
- | # Paremeters | 2.5B | 8.1B | **1.3B** | 3.3B |
331
  | # Active Parameters | 2.5B | 8.1B | **400M** | 800M |
332
  | # Training tokens | 12T | 12T | **10T** | 10T |
333
 
 
327
  | Initialization std | 0.1 | 0.1 | **0.1** | 0.1 |
328
  | Sequence Length | 4096 | 4096 | **4096** | 4096 |
329
  | Position Embedding | RoPE | RoPE | **RoPE** | RoPE |
330
+ | # Parameters | 2.5B | 8.1B | **1.3B** | 3.3B |
331
  | # Active Parameters | 2.5B | 8.1B | **400M** | 800M |
332
  | # Training tokens | 12T | 12T | **10T** | 10T |
333