emrgnt-cmplxty commited on
Commit
a360c0d
1 Parent(s): 3d165dc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -6
README.md CHANGED
@@ -2,13 +2,11 @@
2
  license: apache-2.0
3
  ---
4
 
5
- # SciPhi-SearchAgent-Alpha-7B Model Card
6
 
7
- The SciPhi-SearchAgent-Alpha-7B 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 work aims to train an agent which specializes 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 the agent end-to-end.
8
 
9
- Currently, SciPhi-SearchAgent-Alpha-7B is available via hosted api at https://www.sciphi.ai.
10
-
11
- You can try a demonstration of SearchAgent [here](https://search.sciphi.ai/).
12
 
13
  ## Model Architecture
14
 
@@ -28,7 +26,7 @@ It is recommended to use a single search query. The model will return an answer
28
  Using the AgentSearch package an example is shown below.
29
  ```
30
  export SCIPHI_API_KEY=MY_SCIPHI_API_KEY
31
- # Use the SciPhi `SearchAgent` for LLM RAG w/ AgentSearch
32
  python -m agent_search.scripts.run_rag run --query="What is Fermat's last theorem?"
33
  ```
34
 
 
2
  license: apache-2.0
3
  ---
4
 
5
+ # Sensei-7B-v0.1 Model Card
6
 
7
+ Sensei-7B-v0.1 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.
8
 
9
+ Currently, Sensei is available via hosted api at https://www.sciphi.ai. You can try a demonstration [here](https://search.sciphi.ai/).
 
 
10
 
11
  ## Model Architecture
12
 
 
26
  Using the AgentSearch package an example is shown below.
27
  ```
28
  export SCIPHI_API_KEY=MY_SCIPHI_API_KEY
29
+ # Use `Sensei` for LLM RAG w/ AgentSearch
30
  python -m agent_search.scripts.run_rag run --query="What is Fermat's last theorem?"
31
  ```
32