初始化项目，由ModelHub XC社区提供模型

Model: JustACluelessKid2/gpt2-chatml-fp32
Source: Original Platform

checkpoint-6412/chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-6412/config.json

@@ -0,0 +1,41 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50257,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50258,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.0",
+  "use_cache": false,
+  "vocab_size": 50259
+}

checkpoint-6412/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50257,
+  "do_sample": true,
+  "eos_token_id": [
+    50258,
+    50256
+  ],
+  "pad_token_id": 50256,
+  "transformers_version": "5.5.0"
+}

checkpoint-6412/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e3e3ce4ce5b46b87817f9cc36b542db60c2d54bd29d5ee67f2e98781fa7eef
+size 497780352

checkpoint-6412/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:875625284f4a8f83d74b4992b2122f66f972b5aa29ff3f9d6fcc7a990aa13df2
+size 995657099

checkpoint-6412/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ea264c027cb01e87bb481b14ec8fdf28f83ddecdfb6d011fbe427cbaae076d3
+size 14645

checkpoint-6412/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00cc3a2c2eee5efc2eb9f976bd8e013c2a5120b0dfa8d365f2d44ed1b96ed2a6
+size 1465

checkpoint-6412/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "legacy": true,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "use_fast": true
+}

checkpoint-6412/tokens_state.json

@@ -0,0 +1 @@
+{"total": 42091648, "trainable": 27106544}

checkpoint-6412/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80efb8d8ed387bb24eb17cd0379f57c7a4ace64557f55355bd28eb4229d8e8fe
+size 6993