smk/graph-of-thoughts
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

- fixed typos and slightly improved language of the README files

Browse Source 
- added README file to the examples directory
- updated the citation section in the main README
This commit is contained in:
Robert Gerstenberger
2023-08-21 11:57:55 +02:00
committed by Nils Blach
parent 41a0a6e67c
commit 2f4b828aef
4 changed files with 23 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
graph_of_thoughts/controller/README.md
+7 -7
View File
@@ -9,14 +9,14 @@ Currently, the framework supports the following LLMs:
- Llama-2 (Local - HuggingFace Transformers)
The following section describes how to instantiate individual LLMs and the Controller to run a defined GoO.
Furthermore, process of adding new LLM into the framework is outlined at the end.
Furthermore, the process of adding new LLMs into the framework is outlined at the end.
## LLM Instantiation
- Create a copy of `config_template.json` named `config.json`.
- Fill configuration details based on the used model (below).
### GPT-4 / GPT-3.5
- Adjust predefined `chatgpt`, `chatgpt4` or create new configuration with unique key.
- Adjust predefined `chatgpt`, `chatgpt4` or create new configuration with an unique key.
| Key | Value |
|---------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
@@ -38,8 +38,8 @@ lm = controller.ChatGPT(
```
### Llama-2
- Requires local hardware to run inference and HuggingFace account.
- Adjust predefined `llama7b-hf`, `llama13b-hf`, `llama70b-hf` or create new configuration with unique key.
- Requires local hardware to run inference and a HuggingFace account.
- Adjust predefined `llama7b-hf`, `llama13b-hf`, `llama70b-hf` or create a new configuration with an unique key.
| Key | Value |
|---------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
@@ -58,8 +58,8 @@ lm = controller.Llama2HF(
model_name=<configuration key>
)
```
- Request access to Llama-2 via [Meta form](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) using same email address as for the HuggingFace account.
- After the access is granted, go to [HuggingFace Llama-2 model card](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf), log in and accept licence (_"You have been granted access to this model"_ message should appear).
- Request access to Llama-2 via the [Meta form](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) using the same email address as for the HuggingFace account.
- After the access is granted, go to [HuggingFace Llama-2 model card](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf), log in and accept the license (_"You have been granted access to this model"_ message should appear).
- Generate HuggingFace access token.
- Log in from CLI with: `huggingface-cli login --token <your token>`.
@@ -114,4 +114,4 @@ def query(self, query: str, num_responses: int = 1) -> Any:
```
def get_response_texts(self, query_response: Union[List[Dict], Dict]) -> List[str]:
# Retrieve list of raw strings from the LLM response structure
```
```