Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,35 @@
-*.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
+*.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

README.md

@@ -1,3 +1,205 @@
----
-license: mit
----
+# COCONUT 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-coconut)
+
+</div>
+
+## Overview
+
+**COCONUT** (Continuous COnceptual Neural Thought) is a latent reasoning model based on GPT-2 that enables continuous thought generation in latent space. 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**: `COCONUTGPT2` (extends `GPT2LMHeadModel`)
+- **Latent Tokens**: Uses special tokens `<|latent|>`, `<|start-latent|>`, `<|end-latent|>` for latent reasoning
+- **Input Format**: Requires newline after input question before `<|start-latent|>` token
+
+## Related Models
+
+This repository includes other latent reasoning models that you might find useful:
+
+- **[CODI Model](../codi/README.md)** - GPT-2 based model with optional projector module for enhanced hidden states
+- **[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-coconut --local-dir checkpoints/coconut
+```
+
+## 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/coconut"
+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 LatentCOCONUT(MODELS["coconut"]["class"], LatentGenerationMixin):
+    def __init__(self, config):
+        super().__init__(config)
+
+# Load model
+model = LatentCOCONUT.from_pretrained(
+    model_id,
+    latent_id=latent_id,
+    latent_start_id=start_id,
+    latent_end_id=end_id,
+    device_map="auto",
+)
+
+# Prepare input (note: newline before <|start-latent|>)
+question = "What is 2 + 2?\n<|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:
+
+```python
+# Prepare batch inputs
+questions = [
+    "What is 2 + 2?\n<|start-latent|>",
+    "What is 5 * 3?\n<|start-latent|>",
+    "What is 10 - 4?\n<|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)
+```
+
+## 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
+
+COCONUT uses a special answer format with `#` separator:
+
+```python
+from src.paths import coconut_extract_answer_number
+
+# Extract answer from generated text
+answer = coconut_extract_answer_number(result)
+print(f"Answer: {answer}")
+```
+
+## Evaluation
+
+Run evaluation using the provided scripts:
+
+```bash
+# For COCONUT (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-coconut](https://huggingface.co/dd101bb/latent-tts-coconut)
+- **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{hao2025traininglargelanguagemodels,
+      title={Training Large Language Models to Reason in a Continuous Latent Space}, 
+      author={Shibo Hao and Sainbayar Sukhbaatar and DiJia Su and Xian Li and Zhiting Hu and Jason Weston and Yuandong Tian},
+      year={2025},
+      eprint={2412.06769},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2412.06769}, 
+}
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|end-latent|>": 50258,
+  "<|latent|>": 50259,
+  "<|start-latent|>": 50257
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "COCONUTGPT2"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "latent_end_id": -100,
+  "latent_id": -100,
+  "latent_start_id": -100,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "target_id": -100,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 50260
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.52.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad7f3ce896a610a4293556a30b7bf2b9e9c0d463a248eea448d44a7e962be390
+size 497783424

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<|start-latent|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "<|end-latent|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "<|latent|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}