| { | |
| "_name_or_path": "yam-peleg/Experiment26-7B", | |
| "adapter_dim": 16, | |
| "architectures": [ | |
| "MistralForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "layer_id": 31, | |
| "lora_alpha": 16, | |
| "lora_r": 16, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mistral", | |
| "moe_dtype": "float16", | |
| "moe_scaling": 0.25, | |
| "num_attention_heads": 32, | |
| "num_experts": 64, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "output_router_logits": false, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": false, | |
| "topk": 2, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.38.0", | |
| "use_cache": false, | |
| "vocab_size": 32000 | |
| } | |