Update README.md

README.md

@@ -1,47 +1,73 @@
 ---
-license: Apache License 2.0
-
-#model-type:
-##如 gpt、phi、llama、chatglm、baichuan 等
-#- gpt
-
-#domain:
-##如 nlp、cv、audio、multi-modal
-#- nlp
-
-#language:
-##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
-#- cn 
-
-#metrics:
-##如 CIDEr、Blue、ROUGE 等
-#- CIDEr
-
-#tags:
-##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
-#- pretrained
-
-#tools:
-##如 vllm、fastchat、llamacpp、AdaSeq 等
-#- vllm
+license: gemma
+base_model: HuggingFaceH4/zephyr-7b-gemma-sft-v0.1
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- argilla/dpo-mix-7k
+model-index:
+- name: DiscoPOP-zephyr-7b-gemma
+  results: []
 ---
-### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
-#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
 
-SDK下载
-```bash
-#安装ModelScope
-pip install modelscope
+# DiscoPOP-zephyr-7b-gemma
+
+This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-gemma-sft-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-sft-v0.1) on the argilla/dpo-mix-7k dataset.
+
+This model is from the paper ["Discovering Preference Optimization Algorithms with and for Large Language Models"](https://arxiv.org/abs/2406.08414)
+
+Read the [blog post on it here!](https://sakana.ai/llm-squared)
+
+See the codebase to generate it here: [https://github.com/SakanaAI/DiscoPOP](https://github.com/SakanaAI/DiscoPOP)
+
+## Model description
+
+This model is identical in training to [HuggingFaceH4/zephyr-7b-gemma-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-7b-gemma-v0.1), except instead of using Direct Preference Optimization (DPO), it uses DiscoPOP.
+
+DiscoPOP is our Discovered Preference Optimization algorithm, which is defined as follows:
+
 ```
-```python
-#SDK模型下载
-from modelscope import snapshot_download
-model_dir = snapshot_download('SakanaAI/DiscoPOP-zephyr-7b-gemma')
-```
-Git下载
-```
-#Git模型下载
-git clone https://www.modelscope.cn/SakanaAI/DiscoPOP-zephyr-7b-gemma.git
+def log_ratio_modulated_loss(
+    self,
+    policy_chosen_logps: torch.FloatTensor,
+    policy_rejected_logps: torch.FloatTensor,
+    reference_chosen_logps: torch.FloatTensor,
+    reference_rejected_logps: torch.FloatTensor,
+) -> torch.FloatTensor:
+    pi_logratios = policy_chosen_logps - policy_rejected_logps
+    ref_logratios = reference_chosen_logps - reference_rejected_logps
+    logits = pi_logratios - ref_logratios
+    # Modulate the mixing coefficient based on the log ratio magnitudes
+    log_ratio_modulation = torch.sigmoid(logits)
+    logistic_component = -F.logsigmoid(self.beta * logits)
+    exp_component = torch.exp(-self.beta * logits)
+    # Blend between logistic and exponential component based on log ratio modulation
+    losses = logistic_component * (1 - log_ratio_modulation) + exp_component * log_ratio_modulation
+    return losses
 ```
 
-<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-07
+- train_batch_size: 2
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1