f43199de7d
Model: C10X/Nanbeige4-3B-Thinking-2511-Claude-4.5-Opus-High-Reasoning-Distill-heretic Source: Original Platform
33 lines
779 B
JSON
33 lines
779 B
JSON
{
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 166100,
|
|
"dtype": "bfloat16",
|
|
"embd_pdrop": 0.0,
|
|
"eos_token_id": 166101,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 2560,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 10496,
|
|
"max_position_embeddings": 65536,
|
|
"mlp_bias": false,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 20,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 4,
|
|
"pad_token_id": 0,
|
|
"pretraining_tp": 1,
|
|
"resid_pdrop": 0.0,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 5000000,
|
|
"tie_word_embeddings": false,
|
|
"transformers_version": "4.57.1",
|
|
"use_cache": true,
|
|
"vocab_size": 166144
|
|
}
|