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

@@ -0,0 +1,101 @@
+# Nyx: Core-Outline Transformer Model
+
+Nyx is a transformer-based language model designed for efficient text generation and understanding. This model is part of the Core-Outline project, focusing on providing high-quality text generation capabilities with a focus on financial, SaaS, social media, customer, and customer feedback analytics data.
+
+## Model Architecture
+
+Nyx is built on a transformer decoder-only architecture with the following key components:
+
+- **Rotary Position Embeddings (RoPE)**: For better handling of sequence positions
+- **Multi-head Self-Attention**: With grouped-query attention for efficient inference
+- **SwiGLU Activation**: For the feed-forward networks
+- **RMSNorm**: For layer normalization
+- **Sliding Window Attention**: For handling longer sequences efficiently
+
+### Model Specifications
+
+| Parameter | Value |
+|-----------|-------|
+| Hidden Size | 1024 |
+| Number of Layers | 24 |
+| Number of Attention Heads | 16 |
+| Number of Key-Value Heads | 16 |
+| Intermediate Size | 2816 |
+| Max Sequence Length | 32,768 tokens |
+| Vocabulary Size | 151,936 |
+| Activation | SwiGLU (SiLU) |
+
+## Usage
+
+### Prerequisites
+
+- Python 3.11+
+- PyTorch 2.0+
+- Transformers library
+- FastAPI (for API server)
+
+### Loading the Model
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_path = "core-outline/nyx"
+model = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("core-outline/nyx")  # Using Qwen tokenizer
+```
+
+### Text Generation
+
+```python
+def generate_text(prompt, max_length=100, temperature=0.7):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    outputs = model.generate(
+        inputs.input_ids,
+        max_length=max_length,
+        temperature=temperature,
+        do_sample=True,
+        pad_token_id=tokenizer.eos_token_id
+    )
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+```
+
+
+## Model Configuration
+
+The model uses the following key configuration parameters (from `config.json`):
+
+```json
+{
+  "hidden_size": 1024,
+  "intermediate_size": 2816,
+  "num_hidden_layers": 24,
+  "num_attention_heads": 16,
+  "num_key_value_heads": 16,
+  "max_position_embeddings": 32768,
+  "rms_norm_eps": 1e-6,
+  "rope_theta": 1000000.0
+}
+```
+
+## Tokenizer
+
+The model uses the Qwen tokenizer, which is a BPE-based tokenizer with a vocabulary size of 151,936 tokens.
+
+## Training Data
+
+The model has been trained on a diverse dataset including:
+- Financial analytics
+- SaaS metrics
+- Social media data
+- Customer data
+- Customer feedback
+
+## License
+
+[Specify your license here]
+
+## Acknowledgements
+
+- The model architecture is based on the Qwen/Llama architecture
+- Uses Rotary Position Embeddings (RoPE) for position encoding
+- Implements grouped-query attention for efficient inference

config.json

@@ -0,0 +1,21 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "gradient_checkpointing": false,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 2816,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": false,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.37.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68940f6d8fb061c8f066c157ef91ad94e62232df90dde755f5eceb581f8d97c5
+size 2478319800

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}