| { | |
| "_attn_implementation_autoset": true, | |
| "_name_or_path": "kyutai/helium-1-preview-2b", | |
| "architectures": [ | |
| "HeliumForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2560, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 7040, | |
| "max_position_embeddings": 4096, | |
| "mlp_bias": false, | |
| "model_type": "helium", | |
| "num_attention_heads": 20, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 20, | |
| "pad_token_id": 3, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-08, | |
| "rope_theta": 100000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.49.0.dev0", | |
| "transformers.js_config": { | |
| "dtype": "q4", | |
| "use_external_data_format": { | |
| "model.onnx": true, | |
| "model_fp16.onnx": true, | |
| "model_int8.onnx": true, | |
| "model_quantized.onnx": true, | |
| "model_uint8.onnx": true | |
| } | |
| }, | |
| "use_cache": true, | |
| "vocab_size": 48000 | |
| } |