初始化项目，由ModelHub XC社区提供模型

Model: QpiEImitation/opd_math500_S-Qwen2-0.5B-Instruct_T-Qwen2-7B-Instruct Source: Original Platform
2026-06-16 06:06:15 +08:00
commit 4e17d76798
10 changed files with 236 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,69 @@
+---
+base_model: Qwen/Qwen2-0.5B-Instruct
+library_name: transformers
+model_name: opd_math500_S-Qwen2-0.5B-Instruct_T-Qwen2-7B-Instruct
+tags:
+- generated_from_trainer
+- trl
+- gkd
+licence: license
+---
+
+# Model Card for opd_math500_S-Qwen2-0.5B-Instruct_T-Qwen2-7B-Instruct
+
+This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="QpiEImitation/opd_math500_S-Qwen2-0.5B-Instruct_T-Qwen2-7B-Instruct", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/viano/huggingface/runs/xndmaxpp) 
+
+
+
+This model was trained with GKD, a method introduced in [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://huggingface.co/papers/2306.13649).
+
+### Framework versions
+
+- TRL: 1.0.0.dev0
+- Transformers: 5.3.0
+- Pytorch: 2.6.0+cu124
+- Datasets: 4.8.2
+- Tokenizers: 0.22.2
+
+## Citations
+
+Cite GKD as:
+
+```bibtex
+@inproceedings{agarwal2024on-policy,
+    title        = {{On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes}},
+    author       = {Rishabh Agarwal and Nino Vieillard and Yongchao Zhou and Piotr Stanczyk and Sabela Ramos Garea and Matthieu Geist and Olivier Bachem},
+    year         = 2024,
+    booktitle    = {The Twelfth International Conference on Learning Representations, {ICLR} 2024, Vienna, Austria, May 7-11, 2024},
+    publisher    = {OpenReview.net},
+    url          = {https://openreview.net/forum?id=3zKtaqxLhW},
+}
+```
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```
--- a/chat_template.jinja
+++ b/chat_template.jinja
@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant.<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,57 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.3.0"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abfda77e79047bc45d86e52cea01501c5d73b14f00e89848e4859b38d64e1d91
+size 988097824
--- a/run_config.json
+++ b/run_config.json
@@ -0,0 +1,28 @@
+{
+  "method": "opd",
+  "student_model": "Qwen/Qwen2-0.5B-Instruct",
+  "teacher_model": "Qwen/Qwen2-7B-Instruct",
+  "train_dataset": "EleutherAI/hendrycks_math/all",
+  "eval_dataset": "HuggingFaceH4/MATH-500",
+  "train_samples": 7500,
+  "eval_samples": 500,
+  "opd_mode": "expectation",
+  "trust_region": true,
+  "ppo_clip_eps": 0.2,
+  "use_correction": false,
+  "correction_alpha": 0.2,
+  "correction_lr": 0.001,
+  "num_inner_steps": 10,
+  "replay_buffer_size": 10,
+  "max_steps": 800,
+  "num_epochs": 1.0,
+  "lr": 2e-06,
+  "batch_size": 1,
+  "grad_accum": 8,
+  "output_dir": "opd_math500_S-Qwen2-0.5B-Instruct_T-Qwen2-7B-Instruct_expectation_tr_L10_buf10_20260420_154437",
+  "use_lora": false,
+  "lora_r": null,
+  "lora_alpha": null,
+  "lora_dropout": null,
+  "lora_target_modules": null
+}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f722bc04c884e2fe1525fdcd85a1293a8499b6e620c1ac7c083c49632305fb
+size 11418262
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,18 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44aca0d7a5d3469071f110c245514f3bd292d0053bc35ec49b5d84c702040e4b
+size 5560