Update README.md

README.md

@@ -16,20 +16,17 @@ language:
 tags:
   - text-generation
   - transformers
+  - llama
   - research
   - code
   - mathematics
   - reasoning
   - multilingual
   - long-context
+  - safetensors
 pipeline_tag: text-generation
 library_name: transformers
-datasets:
-  - scientific_papers
-  - code_repositories
-  - mathematical_proofs
-  - conversational_data
-  - multilingual_corpus
+model_type: llama
 inference: true
 ---
 
@@ -45,9 +42,9 @@ The model demonstrates exceptional performance in complex reasoning tasks, scori
 
 ### Core Specifications
 
-Helion-2.5-Rnd is built upon the LLaMA architecture with significant enhancements:
+Helion-2.5-Rnd is built upon an advanced transformer architecture with the following specifications:
 
-- **Parameters**: 70 billion+ parameters
+- **Parameters**: 70 billion parameters
 - **Architecture Type**: Transformer-based causal language model
 - **Hidden Size**: 4096 dimensions
 - **Layers**: 32 transformer blocks
@@ -57,7 +54,8 @@ Helion-2.5-Rnd is built upon the LLaMA architecture with significant enhancement
 - **Context Window**: 131,072 tokens (128K)
 - **Positional Encoding**: YARN (Yet Another RoPE extensioN) with factor 8.0
 - **RoPE Theta**: 500,000
-- **Precision**: BF16/FP16 native, INT8/INT4 quantization supported
+- **Precision**: BF16/FP16 native (no quantization)
+- **Weight Format**: SafeTensors for secure model storage
 
 ### Technical Innovations
 
@@ -75,20 +73,8 @@ The model incorporates several key architectural improvements:
 
 ## Training Methodology
 
-### Data Composition
-
-The model was trained on 2.5 trillion tokens drawn from diverse high-quality sources:
-
-- Scientific papers and academic literature
-- Open-source code repositories across multiple programming languages
-- Mathematical proofs and computational reasoning datasets
-- High-quality conversational data
-- Multilingual text corpus covering 50+ languages
-- Technical documentation and structured knowledge
-
 ### Training Configuration
 
-- **Base Model**: Meta-Llama-3.1-70B
 - **Training Steps**: 150,000 steps
 - **Warmup Steps**: 2,000 steps
 - **Learning Rate**: 2.0e-5 with cosine scheduling
@@ -139,6 +125,18 @@ The model maintains consistent performance across its full 131K token context wi
 
 ## Installation and Deployment
 
+### Model Files
+
+The model is distributed using SafeTensors format for enhanced security and faster loading:
+
+```
+model.safetensors.index.json  # Model shard index
+model-00001-of-00015.safetensors
+model-00002-of-00015.safetensors
+...
+model-00015-of-00015.safetensors
+```
+
 ### Prerequisites
 
 ```bash
@@ -329,14 +327,7 @@ inference:
 - **Storage**: 1TB+ NVMe SSD
 - **Network**: 100Gbps InfiniBand for optimal performance
 
-### Quantization Options
-
-For reduced memory requirements:
-
-- **INT8**: ~50% memory reduction, minimal quality loss
-- **INT4**: ~75% memory reduction, acceptable for many tasks
-- **GPTQ**: Optimized 4-bit quantization
-- **AWQ**: Activation-aware weight quantization
+**Note**: This model is provided in full precision (BF16/FP16) without quantization to maintain maximum quality and accuracy.
 
 ## Use Cases and Applications