Update README.md

README.md

@@ -14,11 +14,11 @@ tags:
 <center><img src="crystalcoder_logo.jpg" alt="crystal coder logo" width="300"/></center>
 
 
-CrystalCoder is a 7B parameter language model, distinctively trained on the SlimPajama and StarCoder datasets. 
+Crystal is a 7B parameter language model, distinctively trained on the SlimPajama and StarCoder datasets. 
 This model excels in balancing natural language processing and coding capabilities. 
-Despite being trained on a smaller dataset of 1.4 trillion tokens—compared to LLaMA 2's 2 trillion—CrystalCoder surpasses LLaMA 2 in some challenging English and coding tasks. 
+Despite being trained on a smaller dataset of 1.4 trillion tokens—compared to LLaMA 2's 2 trillion—Crystal surpasses LLaMA 2 in some challenging English and coding tasks. 
 It demonstrates superior performance in benchmarks like MMLU, HumanEval, and MBPP. 
-By comparing CrystalCoder with other similar work, CrystalCoder is quite balance on language and coding tasks.
+By comparing Crystal with other similar work, Crystal is quite balance on language and coding tasks.
 
 <center><img src="performance_in_benchmarks.png" alt="performance in benchmarks" /></center>
 
@@ -35,7 +35,7 @@ By comparing CrystalCoder with other similar work, CrystalCoder is quite balance
 - As reported in prior work, the choice of temperature affect the programming metrics a lot, we evaluate all models with the following temperature:
    - Scores for HumanEval is computed with a temperature of 0.2
    - Scores for MBPP is computed with a temperature of 0.1
-- For detailed token breakdown of CrystalCoder dataset, refer to the [CrystalCoder dataset repository](https://huggingface.co/datasets/LLM360/CrystalCoderDatasets).
+- For detailed token breakdown of Crystal dataset, refer to the [Crystal dataset repository](https://huggingface.co/datasets/LLM360/CrystalCoderDatasets).
 
 
  
@@ -61,11 +61,11 @@ Get access now at [LLM360 site](https://www.llm360.ai/)
   - [Training Code](https://github.com/LLM360/crystalcoder-train)
   - [Data Preparation](https://github.com/LLM360/crystalcoder-data-prep)
   - [Metrics](https://github.com/LLM360/Analysis360)
-  - [Fully processed CrystalCoder pretraining data](https://huggingface.co/datasets/LLM360/CrystalCoderDatasets)
+  - [Fully processed Crystal pretraining data](https://huggingface.co/datasets/LLM360/CrystalCoderDatasets)
 
 # 🟣 Model Architecture
 
-CrystalCoder leverages a GPT-like architecture, akin to LLaMA, but with the addition of maximal update parameterization (**muP**). 
+Crystal leverages a GPT-like architecture, akin to LLaMA, but with the addition of maximal update parameterization (**muP**). 
 
 Key modifications introduced by muP include:
 
@@ -106,7 +106,7 @@ Our training has 3 stages:
 - Stage 2: Pretraining on the other half of SlimPajama (50% x 690B = 345B), plus two epochs of StarCoder Data (2 x 291B).
 - Stage 3: Pretraining on `100B` additional Python and web-related data (HTML, JavaScript, CSS) sampled from StarCoder Data, and `10B` tokens sampled from SlimPajama.
 
-For details of the training dataset for each stage, please refer to the Dataset section and our CrystalCoder Data Card.
+For details of the training dataset for each stage, please refer to the Dataset section and our Crystal Data Card.
 
 For hyperparameters used in each stage, please refer to the following table:
 <center><img src="hyperparameters.png" alt="hyperparameter table" /></center>
@@ -115,7 +115,7 @@ For more details of training, please refer to [our paper](https://arxiv.org/pdf/
 
 # 🟣 Dataset
 
-Our tokenized datasets for all phases are available at [CrystalCoderDatasets](https://huggingface.co/datasets/LLM360/CrystalCoderDatasets).
+Our tokenized datasets for all phases are available at [CrystalDatasets](https://huggingface.co/datasets/LLM360/CrystalCoderDatasets).
 
 
 # 🟣 Model Usage
@@ -203,9 +203,9 @@ Selected Metrics are displayed below.
 |<img src="cc-mmlu-1.png" alt="mmlu" width="400"/> | <img src="cc-truthful-1.png" alt="truthfulqa" width="400"/> |
 
 
-# 🟣 CrystalCoder-Instruct
+# 🟣 Crystal-Instruct
 
-We also have instruction tuned versions of CrystalCoder, based on stage 2 and stage 3 final checkpoints. The Instruct version will be released later.
+We also have instruction tuned versions of Crystal, based on stage 2 and stage 3 final checkpoints. The Instruct version will be released later.
 
 # 🟣 Citation