TIGER-Lab
/

AceCodeRM-32B

@@ -3,197 +3,151 @@ library_name: transformers
 tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
 ## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 tags: []
 ---
 ## Uses
+```python
+import torch
+import torch.nn as nn
+from transformers import Qwen2ForCausalLM, AutoTokenizer
+class ValueHead(nn.Module):
+    r"""
+    The ValueHead class implements a head for GPT2 that returns a scalar for each output token.
+    """
+    def __init__(self, config, **kwargs):
+        super().__init__()
+        if not hasattr(config, "summary_dropout_prob"):
+            summary_dropout_prob = kwargs.pop("summary_dropout_prob", 0.1)
+        else:
+            summary_dropout_prob = config.summary_dropout_prob
+        self.dropout = (
+            nn.Dropout(summary_dropout_prob) if summary_dropout_prob else nn.Identity()
+        )
+        # some models such as OPT have a projection layer before the word embeddings - e.g. OPT-350m
+        if hasattr(config, "hidden_size"):
+            hidden_size = config.hidden_size
+        if hasattr(config, "word_embed_proj_dim"):
+            hidden_size = config.word_embed_proj_dim
+        elif hasattr(config, "is_encoder_decoder"):
+            if config.is_encoder_decoder and hasattr(config, "decoder"):
+                if hasattr(config.decoder, "hidden_size"):
+                    hidden_size = config.decoder.hidden_size
+        self.summary = nn.Linear(hidden_size, 1)
+        self.flatten = nn.Flatten()
+    def forward(self, hidden_states):
+        output = self.dropout(hidden_states)
+        # For now force upcast in fp32 if needed. Let's keep the
+        # output in fp32 for numerical stability.
+        if output.dtype != self.summary.weight.dtype:
+            output = output.to(self.summary.weight.dtype)
+        output = self.summary(output)
+        return output
+class Qwen2ForCausalRM(Qwen2ForCausalLM):
+    def __init__(self, config):
+        super().__init__(config)
+        self.v_head = ValueHead(config)
+    def forward(
+        self,
+        input_ids=None,
+        past_key_values=None,
+        attention_mask=None,
+        return_past_key_values=False,
+        **kwargs,
+    ):
+        r"""
+        Applies a forward pass to the wrapped model and returns the logits of the value head.
+        Args:
+            input_ids (`torch.LongTensor` of shape `(batch_size, sequence_length)`):
+                Indices of input sequence tokens in the vocabulary.
+            past_key_values (`tuple(tuple(torch.FloatTensor))`, `optional`):
+                Contains pre-computed hidden-states (key and values in the attention blocks) as computed by the model
+                (see `past_key_values` input) to speed up sequential decoding.
+            attention_mask (`torch.FloatTensor` of shape `(batch_size, sequence_length)`, `optional`):
+                Mask to avoid performing attention on padding token indices. Mask values selected in ``[0, 1]``:
+                - 1 for tokens that are **not masked**,
+                - 0 for tokens that are **masked**.
+            return_past_key_values (bool): A flag indicating if the computed hidden-states should be returned.
+            kwargs (`dict`, `optional`):
+                Additional keyword arguments, that are passed to the wrapped model.
+        """
+        kwargs["output_hidden_states"] = (
+            True  # this had already been set in the LORA / PEFT examples
+        )
+        kwargs["past_key_values"] = past_key_values
+        # if (
+        #     self.is_peft_model
+        #     and
+        #     self.pretrained_model.active_peft_config.peft_type == "PREFIX_TUNING"
+        # ):
+        #     kwargs.pop("past_key_values")
+        base_model_output = super().forward(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            **kwargs,
+        )
+        last_hidden_state = base_model_output.hidden_states[-1]
+        lm_logits = base_model_output.logits
+        loss = base_model_output.loss
+        if last_hidden_state.device != self.v_head.summary.weight.device:
+            last_hidden_state = last_hidden_state.to(self.v_head.summary.weight.device)
+        value = self.v_head(last_hidden_state).squeeze(-1)
+        # force upcast in fp32 if logits are in half-precision
+        if lm_logits.dtype != torch.float32:
+            lm_logits = lm_logits.float()
+        if return_past_key_values:
+            return (lm_logits, loss, value, base_model_output.past_key_values)
+        else:
+            return (lm_logits, loss, value)
+model_path = "CodeDPO/qwen_coder_2.5_rm"
+model = Qwen2ForCausalRM.from_pretrained(model_path, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+input_chat = [
+                {"role": "user", "content": "Hello, how are you?"},
+                {
+                    "role": "assistant",
+                    "content": "I'm doing great. How can I help you today?",
+                },
+                {
+                    "role": "user",
+                    "content": "I'd like to show off how chat templating works!",
+                },
+            ]
+input_tokens = tokenizer.apply_chat_template(
+        input_chat,
+        tokenize=True,
+        return_dict=True,
+        padding=True,
+        return_tensors="pt",
+    ).to(model.device)
+_, _, values = model(
+    **input_tokens,
+    output_hidden_states=True,
+    return_dict=True,
+    use_cache=False,
+)
+masks = input_tokens["attention_mask"]
+chosen_scores = values.gather(
+    dim=-1, index=(masks.sum(dim=-1, keepdim=True) - 1)
+) # find the last token (eos) in each sequence, a
+chosen_scores = chosen_scores.squeeze()
+print(chosen_scores)
+```