初始化项目，由ModelHub XC社区提供模型

Model: manucif/latamgpt-1b-dpo-vanilla
Source: Original Platform

.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

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+model_name: dpo_output_vanilla
+tags:
+- generated_from_trainer
+- dpo
+- trl
+licence: license
+---
+
+# Model Card for dpo_output_vanilla
+
+This model is a fine-tuned version of [None](https://huggingface.co/None).
+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="None", 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/ouhenio/llama32-1b-dpo/runs/8p59m9tb) 
+
+
+
+This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
+
+### Framework versions
+
+- TRL: 1.6.0
+- Transformers: 5.12.1
+- Pytorch: 2.9.1+cu128
+- Datasets: 5.0.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+Cite DPO as:
+
+```bibtex
+@inproceedings{rafailov2023direct,
+    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
+    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
+    year         = 2023,
+    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
+    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
+    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
+}
+```
+
+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}
+}
+```

all_results.json

@@ -0,0 +1,20 @@
+{
+    "entropy": 1.178030303030303,
+    "epoch": 1.0,
+    "logits/chosen": -0.30206525592803823,
+    "logits/rejected": -0.0929858402560999,
+    "logps/chosen": -472.09090909090907,
+    "logps/rejected": -557.5757575757576,
+    "mean_token_accuracy": 0.7097648002884605,
+    "num_tokens": 358277178.0,
+    "rewards/accuracies": 0.7234848484848485,
+    "rewards/chosen": -0.24461780894886365,
+    "rewards/margins": 1.0697687322443181,
+    "rewards/rejected": -1.3149266098484849,
+    "total_flos": 4.975817267087409e+18,
+    "train_loss": 0.527936527665322,
+    "train_runtime": 22045.0555,
+    "train_samples": 272898,
+    "train_samples_per_second": 12.379,
+    "train_steps_per_second": 0.097
+}

chat_template.jinja

@@ -0,0 +1,5 @@
+{% for message in messages %}{% if loop.index0 == 0 %}{{ bos_token }}{% endif %}<|start_header_id|>{{ message['role'] }}<|end_header_id|>
+
+{% if message['role'] == 'assistant' %}{% generation %}{{ message['content'] | trim }}<|eot_id|>{% endgeneration %}{% else %}{{ message['content'] | trim }}<|eot_id|>{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>
+
+' }}{% endif %}

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128001,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000.0,
+    "rope_type": "llama3"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001
+  ],
+  "pad_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "5.12.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbe99621483fb7061cdfc5d4424fc81f040993e8bb92403e441f714193e30cb7
+size 2996982344

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "TokenizersBackend"
+}

train_results.json

@@ -0,0 +1,20 @@
+{
+    "entropy": 1.178030303030303,
+    "epoch": 1.0,
+    "logits/chosen": -0.30206525592803823,
+    "logits/rejected": -0.0929858402560999,
+    "logps/chosen": -472.09090909090907,
+    "logps/rejected": -557.5757575757576,
+    "mean_token_accuracy": 0.7097648002884605,
+    "num_tokens": 358277178.0,
+    "rewards/accuracies": 0.7234848484848485,
+    "rewards/chosen": -0.24461780894886365,
+    "rewards/margins": 1.0697687322443181,
+    "rewards/rejected": -1.3149266098484849,
+    "total_flos": 4.975817267087409e+18,
+    "train_loss": 0.527936527665322,
+    "train_runtime": 22045.0555,
+    "train_samples": 272898,
+    "train_samples_per_second": 12.379,
+    "train_steps_per_second": 0.097
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8828eabdb4b872c3014098f2096552dbfaf34429265b98e632bffaa738211407
+size 7377