Update README.md

README.md

@@ -2,8 +2,11 @@
 license: apache-2.0
 ---
 
-# Synthia-11B-v3.0
-SynthIA-11B-v3.0 (Synthetic Intelligent Agent) is a model trained with guidance on Orca-2 paper. It has been fine-tuned for instruction following as well as having long-form conversations. SynthIA-3.0 dataset contains the Generarized Tree-of-Thought prompt plus 10 more new long-form system contexts. However, in the training phase the system context was removed as suggested in Orca-2 paper.
+# Synthia-v3.0-11B
+SynthIA-v3.0-11B (Synthetic Intelligent Agent) is a general purpose Large Language Model (LLM). It was trained on the Synthia-v3.0 dataset that contains the Generarized Tree-of-Thought prompt plus 10 more new long-form system contexts.
+
+This model was trained on the principles of LIMA (Less Is More for Alignment) paper, with ~10K high-quality samples generated using GPT-4-Turbo. It has been fine-tuned for instruction following as well as having long-form conversations.
+
 
 <br>
 
@@ -20,7 +23,7 @@ Elaborate on the topic using a Tree of Thoughts and backtrack when necessary to
 
 ## Evaluation
 
-We evaluated Synthia-11B-v3.0 on a wide range of tasks using [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) from EleutherAI. 
+We evaluated Synthia-v3.0-11B on a wide range of tasks using [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) from EleutherAI. 
 
 Here are the results on metrics used by [HuggingFaceH4 Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). Section to follow.
 
@@ -51,8 +54,8 @@ ASSISTANT:
 import torch, json
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_path = "migtissera/Synthia-11B-v3.0"
-output_file_path = "./Synthia-11B-conversations.jsonl"
+model_path = "migtissera/Synthia-v3.0-11B"
+output_file_path = "./Synthia-v3.0-11B-conversations.jsonl"
 
 model = AutoModelForCausalLM.from_pretrained(
     model_path,