Text Generation
Transformers
PyTorch
English
mistral
text-generation-inference
Inference Endpoints
InstructLM-500M / config.json
instruction-pretrain's picture
Upload 8 files
6bcbd8a verified
raw
history blame contribute delete
615 Bytes
{
"architectures": [
"MistralForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 1536,
"initializer_range": 0.02,
"intermediate_size": 4320,
"max_position_embeddings": 2048,
"model_type": "mistral",
"num_attention_heads": 24,
"num_hidden_layers": 16,
"num_key_value_heads": 24,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 2048,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.34.0.dev0",
"use_cache": true,
"vocab_size": 32000
}