初始化项目,由ModelHub XC社区提供模型

Model: deepseek-ai/deepseek-coder-7b-base-v1.5
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-10 11:21:55 +08:00
commit 1aaa8a6ce7
12 changed files with 200433 additions and 0 deletions

26
config.json Normal file
View File

@@ -0,0 +1,26 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 100000,
"eos_token_id": 100001,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"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,
"torch_dtype": "bfloat16",
"transformers_version": "4.35.2",
"use_cache": true,
"vocab_size": 102400
}