Text Generation
Transformers
Safetensors
GGUF
English
mistral
medical
conversational
text-generation-inference
Inference Endpoints
Medilora-Mistral-7B / config.json
yxzwayne's picture
Upload folder using huggingface_hub
2212d83
raw
history blame
654 Bytes
{
"_name_or_path": "Medilora/medilora-mistral-7b",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.36.0.dev0",
"use_cache": false,
"vocab_size": 32002
}