初始化项目，由ModelHub XC社区提供模型

Model: HWERI/pythia-70m-deduped-cleansharegpt-en Source: Original Platform
2026-05-01 17:12:30 +08:00
commit 5e3249109d
8 changed files with 150642 additions and 0 deletions
--- a/config.json
+++ b/config.json
@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/mnt/llm10t/c00669034/models/pythia-70m-deduped",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "end_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "pad_token_id": 0,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50280
+}