Text Generation
Transformers
NeMo
Safetensors
mistral
text-generation-inference
Inference Endpoints
srvm's picture
Add model weights and config
4c0b638
raw
history blame contribute delete
698 Bytes
{
"_name_or_path": "nvidia/Mistral-NeMo-Minitron-8B-Base",
"activation": "silu",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11520,
"max_position_embeddings": 8192,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 40,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.40.2",
"use_cache": true,
"vocab_size": 131072
}