kona2-12B-Base / config.json
RaphaelKalandadze's picture
Upload config.json with huggingface_hub
0536575 verified
raw
history blame
942 Bytes
{
"_name_or_path": "nemo_merged_7348",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151072,
"eos_token_id": 151073,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 1024000,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 40,
"num_key_value_heads": 8,
"pad_token_id": 10,
"rms_norm_eps": 1e-05,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"tool_call_bos_token_id": 151076,
"tool_call_eos_token_id": 151077,
"tool_response_bos_token_id": 151079,
"tool_response_eos_token_id": 151080,
"tool_response_token_id": 151078,
"tools_bos_token_id": 151074,
"tools_eos_token_id": 151075,
"torch_dtype": "bfloat16",
"transformers_version": "4.45.1",
"use_cache": false,
"vocab_size": 151081
}