| { |
| "_name_or_path": "stabilityai/stablelm-zephyr-3b", |
| "architectures": [ |
| "MixtralForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "stabilityai/stablelm-zephyr-3b--configuration_stablelm_epoch.StableLMEpochConfig", |
| "AutoModelForCausalLM": "stabilityai/stablelm-zephyr-3b--modeling_stablelm_epoch.StableLMEpochForCausalLM" |
| }, |
| "bos_token_id": 0, |
| "eos_token_id": 0, |
| "hidden_act": "silu", |
| "hidden_size": 2560, |
| "initializer_range": 0.02, |
| "intermediate_size": 6912, |
| "max_position_embeddings": 4096, |
| "model_type": "mixtral", |
| "norm_eps": 1e-05, |
| "num_attention_heads": 32, |
| "num_experts_per_tok": 2, |
| "num_heads": 32, |
| "num_hidden_layers": 32, |
| "num_key_value_heads": 32, |
| "num_local_experts": 2, |
| "output_router_logits": false, |
| "rms_norm_eps": 1e-06, |
| "rope_pct": 0.25, |
| "rope_theta": 10000, |
| "rotary_scaling_factor": 1.0, |
| "router_aux_loss_coef": 0.001, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.37.0", |
| "use_cache": true, |
| "vocab_size": 50304 |
| } |
|
|