Update README.md

README.md

@@ -4,13 +4,13 @@
 
 # Sensei-7B-V1 Model Card
 
-Sensei-7B-V1 is a Large Language Model (LLM) fine-tuned from Mistral-7B-v0.1. This model was fine tuned with a fully synthetic dataset to specialize at performing retrieval-augmented generation (RAG) over detailed web search results. This model strives to specialize in using search, such as [AgentSearch](https://huggingface.co/datasets/SciPhi/AgentSearch-V1), to generate accurate and well-cited summaries from a range of search results, providing more accurate answers to user queries. Please refer to the [docs here](https://agent-search.readthedocs.io/en/latest/) for more information on how to run Sensei end-to-end.
+Sensei-7B-V1 is a Large Language Model (LLM) fine-tuned from OpenPipe's mistral-ft-optimized-1218, which is based on Mistral-7B. Sensei-7B-V1 was was fine-tuned with a fully synthetic dataset to specialize at performing retrieval-augmented generation (RAG) over detailed web search results. This model strives to specialize in using search, such as [AgentSearch](https://huggingface.co/datasets/SciPhi/AgentSearch-V1), to generate accurate and well-cited summaries from a range of search results, providing more accurate answers to user queries. Please refer to the [docs here](https://agent-search.readthedocs.io/en/latest/) for more information on how to run Sensei end-to-end.
 
 Currently, Sensei is available via hosted api at https://www.sciphi.ai. You can try a demonstration [here](https://search.sciphi.ai/). 
 
 ## Model Architecture
 
-Base Model: Mistral-7B-v0.1
+Base Model: mistral-ft-optimized-1218
 
 **Architecture Features:**
 - Transformer-based model
@@ -33,17 +33,17 @@ python -m agent_search.scripts.run_rag run --query="What is Fermat's last theore
 Alternatively, you may provide your own search context directly to the model by adhereing to the following format:
 
 ```
-### Instruction:
-Your task is to perform retrieval augmented generation (RAG) over the given query and search results. Return your answer with three sections `My Work`, `My Answer`, and `My Further Considerations`. 
+### Instruction: 
+Your task is to perform retrieval augmented generation (RAG) over the given query and search results. Return your answer in a json format that includes a summary of the search results and a list of related queries. 
 
 Query:
-{query}
-
+{prompt}
+\n\n
 Search Results:
-{search_results}
-
+{context}
+\n\n
 Query:
-{query}
+{prompt}
 
 ### Response:
 {"summary":
@@ -55,4 +55,4 @@ __Note__: The inclusion of the text '{"summary":' following the Response footer
 
 ## References
 
-1. Mistral AI. (2023). Model Card for Mistral-7B-v0.1. The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks tested. For full details, please refer to the paper and release blog post. Model Architecture: Transformer with Grouped-Query Attention, Sliding-Window Attention, and Byte-fallback BPE tokenizer. [Link](https://huggingface.co/mistralai/Mistral-7B-v0.1)
+1. OpenPipe AI. (2023). Model Card for mistral-ft-optimized-1218. The mistral-ft-1218 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters optimized for  downstream fine-tuning on a variety of tasks. For full details, please refer to the release blog post. Model Architecture: Transformer with Grouped-Query Attention, Sliding-Window Attention, and Byte-fallback BPE tokenizer. [Link](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218)