| { |
| "_name_or_path": "mistralai/Codestral-22B-v0.1", |
| "architectures": [ |
| "MistralForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 6144, |
| "initializer_range": 0.02, |
| "intermediate_size": 16384, |
| "max_position_embeddings": 32768, |
| "model_type": "mistral", |
| "neuron": { |
| "auto_cast_type": "bf16", |
| "batch_size": 4, |
| "checkpoint_id": "mistralai/Codestral-22B-v0.1", |
| "checkpoint_revision": "8f5fe23af91885222a1563283c87416745a5e212", |
| "compiler_type": "neuronx-cc", |
| "compiler_version": "2.15.128.0+56dc5a86", |
| "num_cores": 12, |
| "sequence_length": 4096, |
| "task": "text-generation" |
| }, |
| "num_attention_heads": 48, |
| "num_hidden_layers": 56, |
| "num_key_value_heads": 8, |
| "rms_norm_eps": 1e-05, |
| "rope_theta": 1000000.0, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.43.2", |
| "use_cache": true, |
| "vocab_size": 32768 |
| } |
|
|