初始化项目,由ModelHub XC社区提供模型

Model: luffycodes/llama-shishya-7b-ep3-v2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-09 17:26:20 +08:00
commit 30249827e2
12 changed files with 93843 additions and 0 deletions

27
config.json Normal file
View File

@@ -0,0 +1,27 @@
{
"_name_or_path": "/data/ss164/teachllm_models/llama-shishya-7b-ep3-v2",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"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": 32,
"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": "float32",
"transformers_version": "4.34.0",
"use_cache": true,
"vocab_size": 32000
}