初始化项目，由ModelHub XC社区提供模型

Model: AlekseyKorshuk/pygmalion-6b-vicuna-chatml Source: Original Platform
2026-06-28 06:08:18 +08:00
commit 8f0f05447d
16 changed files with 303116 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
--- a/.gitignore
+++ b/.gitignore
@@ -0,0 +1 @@
+checkpoint-*/
--- a/README.md
+++ b/README.md
@@ -0,0 +1,56 @@
+---
+license: creativeml-openrail-m
+tags:
+- generated_from_trainer
+model-index:
+- name: pygmalion-6b-vicuna-chatml
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# pygmalion-6b-vicuna-chatml
+
+This model is a fine-tuned version of [PygmalionAI/pygmalion-6b](https://huggingface.co/PygmalionAI/pygmalion-6b) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 4
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.28.1
+- Pytorch 2.0.1+cu117
+- Datasets 2.11.0
+- Tokenizers 0.13.3
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,145 @@
+{
+  "<|extratoken_100|>": 50356,
+  "<|extratoken_101|>": 50357,
+  "<|extratoken_102|>": 50358,
+  "<|extratoken_103|>": 50359,
+  "<|extratoken_104|>": 50360,
+  "<|extratoken_105|>": 50361,
+  "<|extratoken_106|>": 50362,
+  "<|extratoken_107|>": 50363,
+  "<|extratoken_108|>": 50364,
+  "<|extratoken_109|>": 50365,
+  "<|extratoken_10|>": 50266,
+  "<|extratoken_110|>": 50366,
+  "<|extratoken_111|>": 50367,
+  "<|extratoken_112|>": 50368,
+  "<|extratoken_113|>": 50369,
+  "<|extratoken_114|>": 50370,
+  "<|extratoken_115|>": 50371,
+  "<|extratoken_116|>": 50372,
+  "<|extratoken_117|>": 50373,
+  "<|extratoken_118|>": 50374,
+  "<|extratoken_119|>": 50375,
+  "<|extratoken_11|>": 50267,
+  "<|extratoken_120|>": 50376,
+  "<|extratoken_121|>": 50377,
+  "<|extratoken_122|>": 50378,
+  "<|extratoken_123|>": 50379,
+  "<|extratoken_124|>": 50380,
+  "<|extratoken_125|>": 50381,
+  "<|extratoken_126|>": 50382,
+  "<|extratoken_127|>": 50383,
+  "<|extratoken_128|>": 50384,
+  "<|extratoken_129|>": 50385,
+  "<|extratoken_12|>": 50268,
+  "<|extratoken_130|>": 50386,
+  "<|extratoken_131|>": 50387,
+  "<|extratoken_132|>": 50388,
+  "<|extratoken_133|>": 50389,
+  "<|extratoken_134|>": 50390,
+  "<|extratoken_135|>": 50391,
+  "<|extratoken_136|>": 50392,
+  "<|extratoken_137|>": 50393,
+  "<|extratoken_138|>": 50394,
+  "<|extratoken_139|>": 50395,
+  "<|extratoken_13|>": 50269,
+  "<|extratoken_140|>": 50396,
+  "<|extratoken_141|>": 50397,
+  "<|extratoken_142|>": 50398,
+  "<|extratoken_143|>": 50399,
+  "<|extratoken_14|>": 50270,
+  "<|extratoken_15|>": 50271,
+  "<|extratoken_16|>": 50272,
+  "<|extratoken_17|>": 50273,
+  "<|extratoken_18|>": 50274,
+  "<|extratoken_19|>": 50275,
+  "<|extratoken_1|>": 50257,
+  "<|extratoken_20|>": 50276,
+  "<|extratoken_21|>": 50277,
+  "<|extratoken_22|>": 50278,
+  "<|extratoken_23|>": 50279,
+  "<|extratoken_24|>": 50280,
+  "<|extratoken_25|>": 50281,
+  "<|extratoken_26|>": 50282,
+  "<|extratoken_27|>": 50283,
+  "<|extratoken_28|>": 50284,
+  "<|extratoken_29|>": 50285,
+  "<|extratoken_2|>": 50258,
+  "<|extratoken_30|>": 50286,
+  "<|extratoken_31|>": 50287,
+  "<|extratoken_32|>": 50288,
+  "<|extratoken_33|>": 50289,
+  "<|extratoken_34|>": 50290,
+  "<|extratoken_35|>": 50291,
+  "<|extratoken_36|>": 50292,
+  "<|extratoken_37|>": 50293,
+  "<|extratoken_38|>": 50294,
+  "<|extratoken_39|>": 50295,
+  "<|extratoken_3|>": 50259,
+  "<|extratoken_40|>": 50296,
+  "<|extratoken_41|>": 50297,
+  "<|extratoken_42|>": 50298,
+  "<|extratoken_43|>": 50299,
+  "<|extratoken_44|>": 50300,
+  "<|extratoken_45|>": 50301,
+  "<|extratoken_46|>": 50302,
+  "<|extratoken_47|>": 50303,
+  "<|extratoken_48|>": 50304,
+  "<|extratoken_49|>": 50305,
+  "<|extratoken_4|>": 50260,
+  "<|extratoken_50|>": 50306,
+  "<|extratoken_51|>": 50307,
+  "<|extratoken_52|>": 50308,
+  "<|extratoken_53|>": 50309,
+  "<|extratoken_54|>": 50310,
+  "<|extratoken_55|>": 50311,
+  "<|extratoken_56|>": 50312,
+  "<|extratoken_57|>": 50313,
+  "<|extratoken_58|>": 50314,
+  "<|extratoken_59|>": 50315,
+  "<|extratoken_5|>": 50261,
+  "<|extratoken_60|>": 50316,
+  "<|extratoken_61|>": 50317,
+  "<|extratoken_62|>": 50318,
+  "<|extratoken_63|>": 50319,
+  "<|extratoken_64|>": 50320,
+  "<|extratoken_65|>": 50321,
+  "<|extratoken_66|>": 50322,
+  "<|extratoken_67|>": 50323,
+  "<|extratoken_68|>": 50324,
+  "<|extratoken_69|>": 50325,
+  "<|extratoken_6|>": 50262,
+  "<|extratoken_70|>": 50326,
+  "<|extratoken_71|>": 50327,
+  "<|extratoken_72|>": 50328,
+  "<|extratoken_73|>": 50329,
+  "<|extratoken_74|>": 50330,
+  "<|extratoken_75|>": 50331,
+  "<|extratoken_76|>": 50332,
+  "<|extratoken_77|>": 50333,
+  "<|extratoken_78|>": 50334,
+  "<|extratoken_79|>": 50335,
+  "<|extratoken_7|>": 50263,
+  "<|extratoken_80|>": 50336,
+  "<|extratoken_81|>": 50337,
+  "<|extratoken_82|>": 50338,
+  "<|extratoken_83|>": 50339,
+  "<|extratoken_84|>": 50340,
+  "<|extratoken_85|>": 50341,
+  "<|extratoken_86|>": 50342,
+  "<|extratoken_87|>": 50343,
+  "<|extratoken_88|>": 50344,
+  "<|extratoken_89|>": 50345,
+  "<|extratoken_8|>": 50264,
+  "<|extratoken_90|>": 50346,
+  "<|extratoken_91|>": 50347,
+  "<|extratoken_92|>": 50348,
+  "<|extratoken_93|>": 50349,
+  "<|extratoken_94|>": 50350,
+  "<|extratoken_95|>": 50351,
+  "<|extratoken_96|>": 50352,
+  "<|extratoken_97|>": 50353,
+  "<|extratoken_98|>": 50354,
+  "<|extratoken_99|>": 50355,
+  "<|extratoken_9|>": 50265
+}
--- a/all_results.json
+++ b/all_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.650876347066808,
+    "train_runtime": 60670.5076,
+    "train_samples": 268680,
+    "train_samples_per_second": 13.286,
+    "train_steps_per_second": 0.415
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "PygmalionAI/pygmalion-6b",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTJForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gptj",
+  "n_embd": 4096,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 28,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 64,
+  "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,
+      "temperature": 1.0
+    }
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 50400
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.28.1"
+}
--- a/merges.txt
+++ b/merges.txt
--- a/pytorch_model.bin
+++ b/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40cb33c136cfd67bf1e862338f8d11f615c4144f614be4d2b23e36caa1b2d0ae
+size 12219316137
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,12 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 2048,
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "left",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/train_results.json
+++ b/train_results.json
@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.650876347066808,
+    "train_runtime": 60670.5076,
+    "train_samples": 268680,
+    "train_samples_per_second": 13.286,
+    "train_steps_per_second": 0.415
+}
--- a/trainer_state.json
+++ b/trainer_state.json
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2911331292e13033ad418a312b6952f34e1e63eb64ad1eb36eb6347299fe5d3d
+size 5051
--- a/vocab.json
+++ b/vocab.json