| { | |
| "_name_or_path": "/lustre/teams/text_embeddings/experiments/msmd_cse/sbint_ja-v6_en-v3_code-v2_1b__10Ttoken/PROTO_sbint_ja-v6_en-v3_code-v2_1b_10Ttoken_anneal___multistage_v002ALL20241107_stg2_v1__stg2/hf_checkpoints/checkpoint-225", | |
| "architectures": [ | |
| "LlamaModel" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 112, | |
| "hidden_act": "silu", | |
| "hidden_size": 1792, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6272, | |
| "max_position_embeddings": 8192, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 500000, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.46.3", | |
| "use_cache": true, | |
| "vocab_size": 102400 | |
| } | |