| { | |
| "_name_or_path": "gradientai/v-alpha-tross", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 8192, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 28672, | |
| "max_position_embeddings": 4096, | |
| "model_type": "llama", | |
| "neuron": { | |
| "auto_cast_type": "bf16", | |
| "batch_size": 1, | |
| "checkpoint_id": "gradientai/v-alpha-tross", | |
| "checkpoint_revision": "6d51ed47fe16e37d819dc52c8c55fd7a7150d2b3", | |
| "compiler_type": "neuronx-cc", | |
| "compiler_version": "2.12.68.0+4480452af", | |
| "sequence_length": 2048, | |
| "num_cores": 24, | |
| "task": "text-generation" | |
| }, | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 80, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.35.1", | |
| "use_cache": false, | |
| "vocab_size": 32001 | |
| } | |