Files
ModelHub XC cc7fa7a606 初始化项目,由ModelHub XC社区提供模型
Model: rghosh8/gsm8k-deepseek-llm-7b-chat-rajat-seed-42-G-16_merged
Source: Original Platform
2026-04-22 16:34:06 +08:00

30 lines
682 B
JSON

{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 100000,
"dtype": "float32",
"eos_token_id": 100001,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 30,
"num_key_value_heads": 32,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"transformers_version": "4.56.2",
"use_cache": true,
"vocab_size": 102400
}