| { |
| "_name_or_path": "optimum-internal-testing/tiny-random-snowflake", |
| "architectures": [ |
| "ArcticForCausalLM" |
| ], |
| "attention_dropout": 0, |
| "auto_map": { |
| "AutoConfig": "configuration_arctic.ArcticConfig", |
| "AutoModel": "modeling_arctic.ArcticModel", |
| "AutoModelForCausalLM": "modeling_arctic.ArcticForCausalLM", |
| "AutoModelForSequenceClassification": "modeling_arctic.ArcticForSequenceClassification" |
| }, |
| "bos_token_id": 1, |
| "enable_expert_tensor_parallelism": false, |
| "enc_index": [ |
| 0, |
| 1, |
| 2, |
| 3 |
| ], |
| "eos_token_id": 2, |
| "hidden_act": "silu", |
| "hidden_size": 32, |
| "initializer_range": 0.02, |
| "intermediate_size": 16, |
| "max_position_embeddings": 128, |
| "max_sequence_length": 128, |
| "model_type": "arctic", |
| "moe_eval_capacity_factor": 1, |
| "moe_layer_frequency": 1, |
| "moe_min_capacity": 0, |
| "moe_token_dropping": true, |
| "moe_train_capacity_factor": 1, |
| "num_attention_heads": 4, |
| "num_experts_per_tok": 2, |
| "num_hidden_layers": 4, |
| "num_key_value_heads": 4, |
| "num_local_experts": 4, |
| "parallel_attn_mlp_res": true, |
| "quantization": null, |
| "rms_norm_eps": 1e-05, |
| "rope_theta": 10000, |
| "router_aux_loss_coef": 0.001, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.40.2", |
| "use_cache": true, |
| "use_residual": true, |
| "vocab_size": 32000 |
| } |
|
|
