Text Generation
Transformers
Safetensors
mixtral
Mixture of Experts
mergekit
Merge
chinese
arabic
english
multilingual
german
french
openchat/openchat-3.5-1210
beowolx/CodeNinja-1.0-OpenChat-7B
maywell/PiVoT-0.1-Starling-LM-RP
WizardLM/WizardMath-7B-V1.1
davidkim205/komt-mistral-7b-v1
OpenBuddy/openbuddy-zephyr-7b-v14.1
manishiitg/open-aditi-hi-v1
VAGOsolutions/SauerkrautLM-7b-v1-mistral
text-generation-inference
| { | |
| "_name_or_path": "mlabonne/NeuralMarcoro14-7B", | |
| "architectures": [ | |
| "MixtralForCausalLM" | |
| ], | |
| "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, | |
| "max_position_embeddings": 32768, | |
| "model_type": "mixtral", | |
| "num_attention_heads": 32, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "num_local_experts": 8, | |
| "output_router_logits": false, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "router_aux_loss_coef": 0.001, | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.36.2", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |