初始化项目，由ModelHub XC社区提供模型

Model: ErikDaska/lr_2e-04-sft Source: Original Platform
2026-06-11 09:16:17 +08:00
commit 05d38e37ca
16 changed files with 500870 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/README.md
+++ b/README.md
@@ -0,0 +1,71 @@
+---
+library_name: transformers
+base_model: ErikDaska/lr_2e-04_v2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: lr_2e-04-sft
+  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. -->
+
+# lr_2e-04-sft
+
+This model is a fine-tuned version of [ErikDaska/lr_2e-04_v2.0](https://huggingface.co/ErikDaska/lr_2e-04_v2.0) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7796
+
+## 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-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.03
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.0792        | 0.4444 | 200  | 0.9389          |
+| 0.9923        | 0.8889 | 400  | 0.8776          |
+| 0.9370        | 1.3333 | 600  | 0.8430          |
+| 0.9298        | 1.7778 | 800  | 0.8208          |
+| 0.8879        | 2.2222 | 1000 | 0.8084          |
+| 0.8611        | 2.6667 | 1200 | 0.7948          |
+| 0.8314        | 3.1111 | 1400 | 0.7884          |
+| 0.7953        | 3.5556 | 1600 | 0.7852          |
+| 0.8559        | 4.0    | 1800 | 0.7795          |
+| 0.8336        | 4.4444 | 2000 | 0.7800          |
+| 0.7885        | 4.8889 | 2200 | 0.7796          |
+| 0.8192        | 5.0    | 2250 | 0.7796          |
+
+
+### Framework versions
+
+- Transformers 5.10.2
+- Pytorch 2.11.0+cu128
+- Datasets 5.0.0
+- Tokenizers 0.22.2
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,7 @@
+{% for message in messages %}{% if message['role'] == 'system' %}System: {{ message['content'] }}
+
+{% elif message['role'] == 'user' %}User: {{ message['content'] }}
+
+{% elif message['role'] == 'assistant' %}Assistant: {{ message['content'] }}{{ eos_token }}
+
+{% endif %}{% endfor %}{% if add_generation_prompt %}Assistant: {% endif %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,41 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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": "5.10.2",
+  "use_cache": false,
+  "vocab_size": 50257
+}
--- a/final/chat_template.jinja
+++ b/final/chat_template.jinja
@@ -0,0 +1,7 @@
+{% for message in messages %}{% if message['role'] == 'system' %}System: {{ message['content'] }}
+
+{% elif message['role'] == 'user' %}User: {{ message['content'] }}
+
+{% elif message['role'] == 'assistant' %}Assistant: {{ message['content'] }}{{ eos_token }}
+
+{% endif %}{% endfor %}{% if add_generation_prompt %}Assistant: {% endif %}
--- a/final/config.json
+++ b/final/config.json
@@ -0,0 +1,41 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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": "5.10.2",
+  "use_cache": false,
+  "vocab_size": 50257
+}
--- a/final/generation_config.json
+++ b/final/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "pad_token_id": 50256,
+  "transformers_version": "5.10.2"
+}
--- a/final/model.safetensors
+++ b/final/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af63c46c9bf03608e3a6343673d8e10451314749be273be91ce40365fc9c19b7
+size 497774208
--- a/final/tokenizer.json
+++ b/final/tokenizer.json
--- a/final/tokenizer_config.json
+++ b/final/tokenizer_config.json
@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}
--- a/final/training_args.bin
+++ b/final/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fdef34fdda5aacea3fab0bc76a76043fdf39bfe1063102b05dc0fd706d78937
+size 5201
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "pad_token_id": 50256,
+  "transformers_version": "5.10.2"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af63c46c9bf03608e3a6343673d8e10451314749be273be91ce40365fc9c19b7
+size 497774208
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fdef34fdda5aacea3fab0bc76a76043fdf39bfe1063102b05dc0fd706d78937
+size 5201