Views
No views yet
| 参数 | Full (190M) | Nano (26M) |
|---|---|---|
| hidden_size | 768 | 192 |
| num_layers | 12 | 6 |
| num_heads | 12 | 3 |
| intermediate_size | 3072 | 768 |
| vocab_size | 48000 | 48000 |
1from transformers import AutoModelForCausalLM, AutoTokenizer
2model = AutoModelForCausalLM.from_pretrained("cmz1024/olmo3-190m-zh-nano")
3tok = AutoTokenizer.from_pretrained("cmz1024/olmo3-190m-zh-nano")