| { |
| "architectures": [ |
| "CheddarForCausalLM" |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_cheddar.CheddarConfig", |
| "AutoModelForCausalLM": "modeling_cheddar.CheddarForCausalLM" |
| }, |
| "dtype": "float32", |
| "max_seq_len": 4096, |
| "mlp_hidden": 2048, |
| "model_type": "gouda-cheddar", |
| "n_embd": 768, |
| "n_head": 12, |
| "n_kv_head": 4, |
| "n_layer": 44, |
| "name": "Cheddar-2.0", |
| "qk_norm": true, |
| "rms_eps": 1e-06, |
| "rope_base": 10000.0, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.17.0", |
| "vocab_size": 32768, |
| "z_loss": 0.0 |
| } |
|
|
