初始化项目，由ModelHub XC社区提供模型

Model: fpadovani/tur_10mb_baseline_seed21
Source: Original Platform

checkpoint-5000/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "goldfish-models/tur_latn_10mb",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50000,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50001,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 4,
+  "n_positions": 2048,
+  "pad_token_id": 50002,
+  "prefix": "[CLS]",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "vocab_size": 51200
+}

checkpoint-5000/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50000,
+  "eos_token_id": 50001,
+  "pad_token_id": 50002,
+  "transformers_version": "4.47.0"
+}

checkpoint-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8135d81ece72dd7644fbe64e2b54b6b93c5d7e9101671b11b47675593ee7837
+size 79752272

checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:192a623c744ac0fd8ba5376ad930cfb29fefac6e6fcb464342e01c67d7d0a9ba
+size 159538443

checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb37df80c5f2d92497fd534e957fcff8bcd489f7022201b9a85c94fcd3088582
+size 14709

checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ff2ab183ac3438c73e3152ef5bf274c4bf4198fe8bfc2e520d27cbc6c1be00f
+size 1465

checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac10c9a0a0065866f0ca68b93e1723ca44323b512b13f4353ec884277977f08e
+size 6097