初始化项目，由ModelHub XC社区提供模型

Model: jondurbin/airoboros-65b-gpt4-1.3 Source: Original Platform
2026-05-02 00:30:32 +08:00
commit c9b389387d
22 changed files with 94472 additions and 0 deletions
--- a/config.json
+++ b/config.json
@@ -0,0 +1,24 @@
+{
+  "_name_or_path": "/workspace/llama-65b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 22016,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "pad_token_id": -1,
+  "rms_norm_eps": 1e-05,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}