初始化项目,由ModelHub XC社区提供模型

Model: deepseek-ai/deepseek-coder-1.3b-instruct
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-02 15:58:45 +08:00
commit 5b4718e152
10 changed files with 64302 additions and 0 deletions

28
config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 32013,
"eos_token_id": 32021,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5504,
"max_position_embeddings": 16384,
"model_type": "llama",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": {
"factor": 4.0,
"type": "linear"
},
"rope_theta": 100000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.33.1",
"use_cache": true,
"vocab_size": 32256
}