29 lines
787 B
JSON
29 lines
787 B
JSON
|
{
|
||
|
|
"_name_or_path": "/lustre/fsw/portfolios/llmservice/users/mengruw/sft_mistral_4b_8k/conversion_models/deployment_workspace/Mistral-Nemo-Base-2407",
|
||
|
|
"activation": "silu",
|
||
|
|
"architectures": [
|
||
|
|
"MistralForCausalLM"
|
||
|
|
],
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"bos_token_id": 1,
|
||
|
|
"eos_token_id": 2,
|
||
|
|
"head_dim": 128,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"hidden_size": 3072,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 8640,
|
||
|
|
"max_position_embeddings": 8192,
|
||
|
|
"model_type": "mistral",
|
||
|
|
"num_attention_heads": 32,
|
||
|
|
"num_hidden_layers": 34,
|
||
|
|
"num_key_value_heads": 8,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"rope_theta": 1000000.0,
|
||
|
|
"sliding_window": null,
|
||
|
|
"tie_word_embeddings": true,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "4.45.1",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 131072
|
||
|
|
}
|