Text Generation
Transformers
English
llama
Inference Endpoints
LoneStriker's picture
ExLLaMA V2 quant of TinyLlama-1.1B-Chat-v0.3-6.0bpw-h6-exl2
58aa995
raw
history blame contribute delete
707 Bytes
{
"_name_or_path": "TinyLlama/sft/output/503B_FT_lr1e-5_ep5_top1_2023-08-25/checkpoint-3890",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5632,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 22,
"num_key_value_heads": 4,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.34.0.dev0",
"use_cache": false,
"vocab_size": 32003
}