CroissantLLMChat-v0.1 / config.json
nunonmg's picture
Upload LlamaForCausalLM
231e906 verified
raw
history blame
732 Bytes
{
"_name_or_path": "/mnt/data/nunomg/axolotl/croissantllm-2001-190k/checkpoint-3236",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 32000,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5504,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.36.0.dev0",
"use_cache": false,
"vocab_size": 32002
}