Update README.md

README.md

@@ -1,230 +1,229 @@
----
-library_name: transformers
-license: mit
-base_model:
-- openai-community/gpt2
----
-# CODI Model
-
-<div align="center">
-
-[![HuggingFace](https://img.shields.io/badge/🤗%20HuggingFace-Model-fcc21b?style=for-the-badge&logo=huggingface&logoColor=white)](https://huggingface.co/dd101bb/latent-tts-codi)
-
-</div>
-
-## Overview
-
-**CODI** (Continuous Output with Discrete Input) is a latent reasoning model based on GPT-2 that extends the base architecture with an optional projector module for enhanced hidden state representations. This model is part of the [Parallel Test-Time Scaling for Latent Reasoning Models](https://arxiv.org/abs/2510.07745) framework.
-
-## Model Details
-
-- **Base Architecture**: GPT-2 Language Model
-- **Model Class**: `CODIGPT2` (extends `GPT2LMHeadModel`)
-- **Special Features**: Optional projector module for extended hidden states
-- **Latent Tokens**: Uses special tokens `<|latent|>`, `<|start-latent|>`, `<|end-latent|>` for latent reasoning
-- **Input Format**: Direct input without newline before `<|start-latent|>` token
-
-## Related Models
-
-This repository includes other latent reasoning models that you might find useful:
-
-- **[COCONUT Model](../coconut/README.md)** - GPT-2 based model for continuous thought generation
-- **[CoLaR Model](../colar/README.md)** - LLaMA based model with specialized LatentHead module
-
-## Installation
-
-Download the model from HuggingFace:
-
-```bash
-huggingface-cli download dd101bb/latent-tts-codi --local-dir checkpoints/codi
-```
-
-## Quick Start
-
-### Basic Usage
-
-```python
-from transformers import AutoTokenizer
-from src.generation_mixin import LatentGenerationMixin, LatentGenerationConfig
-from src.paths import MODELS
-
-# Load tokenizer
-model_id = "checkpoints/codi"
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-if tokenizer.pad_token is None:
-    tokenizer.pad_token = tokenizer.eos_token
-
-# Get latent token IDs
-latent_id = tokenizer.convert_tokens_to_ids("<|latent|>")
-start_id = tokenizer.convert_tokens_to_ids("<|start-latent|>")
-end_id = tokenizer.convert_tokens_to_ids("<|end-latent|>")
-
-# Create model class with generation mixin
-class LatentCODI(MODELS["codi"]["class"], LatentGenerationMixin):
-    def __init__(self, config):
-        super().__init__(config)
-
-# Load model
-model = LatentCODI.from_pretrained(
-    model_id,
-    latent_id=latent_id,
-    latent_start_id=start_id,
-    latent_end_id=end_id,
-    device_map="auto",
-)
-
-# Prepare input (note: no newline before <|start-latent|>)
-question = "What is 2 + 2?<|start-latent|>"
-inputs = tokenizer(question, return_tensors="pt").to(model.device)
-
-# Configure generation
-generation_config = LatentGenerationConfig(
-    max_new_tokens=512,
-    latent_length=6,
-    latent_do_sample=True,
-    latent_do_sample_by="dropout",  # or "noise"
-    dropout_p=0.1,
-    pad_token_id=tokenizer.pad_token_id,
-    eos_token_id=tokenizer.eos_token_id,
-)
-
-# Generate
-output = model.generate(
-    **inputs,
-    generation_config=generation_config,
-    num_return_sequences=1,
-)
-
-# Decode result
-result = tokenizer.decode(output[0], skip_special_tokens=True)
-print(result)
-```
-
-### Batch Processing
-
-The model fully supports batch processing with Transformers:
-
-```python
-# Prepare batch inputs
-questions = [
-    "What is 2 + 2?<|start-latent|>",
-    "What is 5 * 3?<|start-latent|>",
-    "What is 10 - 4?<|start-latent|>",
-]
-inputs = tokenizer(questions, return_tensors="pt", padding=True).to(model.device)
-
-# Generate for batch
-outputs = model.generate(
-    **inputs,
-    generation_config=generation_config,
-    num_return_sequences=1,
-)
-
-# Decode batch results
-results = tokenizer.batch_decode(outputs, skip_special_tokens=True)
-for result in results:
-    print(result)
-```
-
-## Model Architecture
-
-### Projector Module
-
-CODI includes an optional projector module that extends hidden states:
-
-```python
-# Projector configuration (if enabled in model)
-projector = nn.Sequential(
-    nn.Dropout(projector_dropout),
-    nn.Linear(hidden_size, projector_hidden_size),
-    nn.GELU(),
-    nn.Linear(projector_hidden_size, hidden_size),
-    nn.LayerNorm(hidden_size),
-)
-```
-
-The projector is used when `output_hidden_states=True` and `config.projector=True`.
-
-## Generation Parameters
-
-### LatentGenerationConfig
-
-- `max_new_tokens` (int): Maximum number of tokens to generate
-- `latent_length` (int): Number of latent tokens (default: 6)
-- `latent_do_sample` (bool): Whether to use stochastic sampling
-- `latent_do_sample_by` (str): Sampling method - `"dropout"` or `"noise"`
-- `dropout_p` (float): Dropout probability for Monte Carlo Dropout (e.g., 0.1)
-- `noise_std` (float): Standard deviation for Additive Gaussian Noise
-
-### Sampling Methods
-
-1. **Monte Carlo Dropout**: Randomly drops activations during forward passes
-   ```python
-   generation_config = LatentGenerationConfig(
-       latent_do_sample_by="dropout",
-       dropout_p=0.1,
-       # ...
-   )
-   ```
-
-2. **Additive Gaussian Noise**: Injects noise into latent embeddings
-   ```python
-   generation_config = LatentGenerationConfig(
-       latent_do_sample_by="noise",
-       noise_std=0.1,
-       # ...
-   )
-   ```
-
-## Answer Extraction
-
-CODI uses standard number extraction from the generated text:
-
-```python
-from src.paths import extract_answer_number
-
-# Extract answer from generated text
-answer = extract_answer_number(result)
-print(f"Answer: {answer}")
-```
-
-## Evaluation
-
-Run evaluation using the provided scripts:
-
-```bash
-# For CODI (GPT-2 based models)
-./run_tests.sh
-```
-
-## Model Card
-
-- **Paper**: [Parallel Test-Time Scaling for Latent Reasoning Models](https://arxiv.org/abs/2510.07745)
-- **HuggingFace**: [dd101bb/latent-tts-codi](https://huggingface.co/dd101bb/latent-tts-codi)
-- **Benchmarks**: GSM8K Test, GSM8K Hard, MultiArith
-
-## Citation
-
-If you use this model, please cite:
-
-```bibtex
-@misc{you2025paralleltesttimescalinglatent,
-      title={Parallel Test-Time Scaling for Latent Reasoning Models}, 
-      author={Runyang You and Yongqi Li and Meng Liu and Wenjie Wang and Liqiang Nie and Wenjie Li},
-      year={2025},
-      eprint={2510.07745},
-      archivePrefix={arXiv},
-      primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2510.07745}, 
-}
-
-@misc{shen2025codicompressingchainofthoughtcontinuous,
-      title={CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation}, 
-      author={Zhenyi Shen and Hanqi Yan and Linhai Zhang and Zhanghao Hu and Yali Du and Yulan He},
-      year={2025},
-      eprint={2502.21074},
-      archivePrefix={arXiv},
-      primaryClass={cs.CL},
-      url={https://arxiv.org/abs/2502.21074}, 
-}
+---
+library_name: transformers
+license: mit
+base_model:
+- openai-community/gpt2
+---
+# CODI Model
+
+<div align="center">
+
+[![HuggingFace](https://img.shields.io/badge/🤗%20HuggingFace-Model-fcc21b?style=for-the-badge&logo=huggingface&logoColor=white)](https://huggingface.co/ModalityDance/latent-tts-codi)
+
+</div>
+
+## Overview
+
+**CODI** (Continuous Output with Discrete Input) is a latent reasoning model based on GPT-2 that extends the base architecture with an optional projector module for enhanced hidden state representations. This model is part of the [Parallel Test-Time Scaling for Latent Reasoning Models](https://arxiv.org/abs/2510.07745) framework.
+
+## Model Details
+
+- **Base Architecture**: GPT-2 Language Model
+- **Model Class**: `CODIGPT2` (extends `GPT2LMHeadModel`)
+- **Special Features**: Optional projector module for extended hidden states
+- **Latent Tokens**: Uses special tokens `<|latent|>`, `<|start-latent|>`, `<|end-latent|>` for latent reasoning
+- **Input Format**: Direct input without newline before `<|start-latent|>` token
+
+## Related Models
+
+This repository includes other latent reasoning models that you might find useful:
+
+[ModalityDance/latent-tts](https://huggingface.co/collections/ModalityDance/latent-tts)
+
+## Installation
+
+Download the model from HuggingFace:
+
+```bash
+huggingface-cli download ModalityDance/latent-tts-codi --local-dir checkpoints/codi
+```
+
+## Quick Start
+
+### Basic Usage
+
+```python
+from transformers import AutoTokenizer
+from src.generation_mixin import LatentGenerationMixin, LatentGenerationConfig
+from src.paths import MODELS
+
+# Load tokenizer
+model_id = "checkpoints/codi"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+if tokenizer.pad_token is None:
+    tokenizer.pad_token = tokenizer.eos_token
+
+# Get latent token IDs
+latent_id = tokenizer.convert_tokens_to_ids("<|latent|>")
+start_id = tokenizer.convert_tokens_to_ids("<|start-latent|>")
+end_id = tokenizer.convert_tokens_to_ids("<|end-latent|>")
+
+# Create model class with generation mixin
+class LatentCODI(MODELS["codi"]["class"], LatentGenerationMixin):
+    def __init__(self, config):
+        super().__init__(config)
+
+# Load model
+model = LatentCODI.from_pretrained(
+    model_id,
+    latent_id=latent_id,
+    latent_start_id=start_id,
+    latent_end_id=end_id,
+    device_map="auto",
+)
+
+# Prepare input (note: no newline before <|start-latent|>)
+question = "What is 2 + 2?<|start-latent|>"
+inputs = tokenizer(question, return_tensors="pt").to(model.device)
+
+# Configure generation
+generation_config = LatentGenerationConfig(
+    max_new_tokens=512,
+    latent_length=6,
+    latent_do_sample=True,
+    latent_do_sample_by="dropout",  # or "noise"
+    dropout_p=0.1,
+    pad_token_id=tokenizer.pad_token_id,
+    eos_token_id=tokenizer.eos_token_id,
+)
+
+# Generate
+output = model.generate(
+    **inputs,
+    generation_config=generation_config,
+    num_return_sequences=1,
+)
+
+# Decode result
+result = tokenizer.decode(output[0], skip_special_tokens=True)
+print(result)
+```
+
+### Batch Processing
+
+The model fully supports batch processing with Transformers:
+
+```python
+# Prepare batch inputs
+questions = [
+    "What is 2 + 2?<|start-latent|>",
+    "What is 5 * 3?<|start-latent|>",
+    "What is 10 - 4?<|start-latent|>",
+]
+inputs = tokenizer(questions, return_tensors="pt", padding=True).to(model.device)
+
+# Generate for batch
+outputs = model.generate(
+    **inputs,
+    generation_config=generation_config,
+    num_return_sequences=1,
+)
+
+# Decode batch results
+results = tokenizer.batch_decode(outputs, skip_special_tokens=True)
+for result in results:
+    print(result)
+```
+
+## Model Architecture
+
+### Projector Module
+
+CODI includes an optional projector module that extends hidden states:
+
+```python
+# Projector configuration (if enabled in model)
+projector = nn.Sequential(
+    nn.Dropout(projector_dropout),
+    nn.Linear(hidden_size, projector_hidden_size),
+    nn.GELU(),
+    nn.Linear(projector_hidden_size, hidden_size),
+    nn.LayerNorm(hidden_size),
+)
+```
+
+The projector is used when `output_hidden_states=True` and `config.projector=True`.
+
+## Generation Parameters
+
+### LatentGenerationConfig
+
+- `max_new_tokens` (int): Maximum number of tokens to generate
+- `latent_length` (int): Number of latent tokens (default: 6)
+- `latent_do_sample` (bool): Whether to use stochastic sampling
+- `latent_do_sample_by` (str): Sampling method - `"dropout"` or `"noise"`
+- `dropout_p` (float): Dropout probability for Monte Carlo Dropout (e.g., 0.1)
+- `noise_std` (float): Standard deviation for Additive Gaussian Noise
+
+### Sampling Methods
+
+1. **Monte Carlo Dropout**: Randomly drops activations during forward passes
+   ```python
+   generation_config = LatentGenerationConfig(
+       latent_do_sample_by="dropout",
+       dropout_p=0.1,
+       # ...
+   )
+   ```
+
+2. **Additive Gaussian Noise**: Injects noise into latent embeddings
+   ```python
+   generation_config = LatentGenerationConfig(
+       latent_do_sample_by="noise",
+       noise_std=0.1,
+       # ...
+   )
+   ```
+
+## Answer Extraction
+
+CODI uses standard number extraction from the generated text:
+
+```python
+from src.paths import extract_answer_number
+
+# Extract answer from generated text
+answer = extract_answer_number(result)
+print(f"Answer: {answer}")
+```
+
+## Evaluation
+
+Run evaluation using the provided scripts:
+
+```bash
+# For CODI (GPT-2 based models)
+./run_tests.sh
+```
+
+## Model Card
+
+- **Paper**: [Parallel Test-Time Scaling for Latent Reasoning Models](https://arxiv.org/abs/2510.07745)
+- **HuggingFace**: [ModalityDance/latent-tts-codi](https://huggingface.co/ModalityDance/latent-tts-codi)
+- **Benchmarks**: GSM8K Test, GSM8K Hard, MultiArith
+
+## Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{you2025paralleltesttimescalinglatent,
+      title={Parallel Test-Time Scaling for Latent Reasoning Models}, 
+      author={Runyang You and Yongqi Li and Meng Liu and Wenjie Wang and Liqiang Nie and Wenjie Li},
+      year={2025},
+      eprint={2510.07745},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2510.07745}, 
+}
+
+@misc{shen2025codicompressingchainofthoughtcontinuous,
+      title={CODI: Compressing Chain-of-Thought into Continuous Space via Self-Distillation}, 
+      author={Zhenyi Shen and Hanqi Yan and Linhai Zhang and Zhanghao Hu and Yali Du and Yulan He},
+      year={2025},
+      eprint={2502.21074},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2502.21074}, 
+}
 ```