|
{ |
|
"_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407", |
|
"architectures": [ |
|
"MistralForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 1, |
|
"eos_token_id": 2, |
|
"head_dim": 128, |
|
"hidden_act": "silu", |
|
"hidden_size": 5120, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 14336, |
|
"max_position_embeddings": 1024000, |
|
"model_type": "mistral", |
|
"num_attention_heads": 32, |
|
"num_hidden_layers": 40, |
|
"num_key_value_heads": 8, |
|
"quantization_config": { |
|
"activation_scheme": "static", |
|
"ignored_layers": [ |
|
"lm_head" |
|
], |
|
"quant_method": "fp8" |
|
}, |
|
"rms_norm_eps": 1e-05, |
|
"rope_theta": 1000000.0, |
|
"sliding_window": null, |
|
"tie_word_embeddings": false, |
|
"torch_dtype": "float16", |
|
"transformers_version": "4.43.0.dev0", |
|
"use_cache": false, |
|
"vocab_size": 131072 |
|
} |
|
|