| { |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 166100, |
| "dtype": "bfloat16", |
| "embd_pdrop": 0.0, |
| "eos_token_id": 166101, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 2560, |
| "initializer_range": 0.02, |
| "intermediate_size": 10752, |
| "max_position_embeddings": 262144, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 20, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 4, |
| "pad_token_id": 0, |
| "pretraining_tp": 1, |
| "resid_pdrop": 0.0, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 70000000, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.51.3", |
| "use_cache": true, |
| "vocab_size": 166144, |
| "addr_qk": 5120, |
| "addr_kv": 34048, |
| "addr_l_begin_mha": 54016, |
| "addr_l_end_mha": 25344, |
| "addr_kk": 33280, |
| "flm_version": "0.9.38" |
| } |
|
|
|
|