empower-dev
/

llama3-empower-functions-small

@@ -23,19 +23,19 @@ Empower Functions is a family of LLMs(large language models) that offer GPT-4 le
 ## Family of Models
-| Model                    | Specs                                                                                             | Links                  |                                     |
-| ------------------------ | ------------------------------------------------------------------------------------------------- | ---------------------- | ----------------------------------- |
-| empower-functions-small  | 8k context, based on [Llama3 8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)               | model, GGUF, GGUF 4bit | most cost effective, local runnable |
-| empower-functions-medium | 32k context, based on [Mixtral 8x7B](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) | model                  | balance in accuracy and cost        |
-| empower-functions-large  | 65k context, based on [Mixtral 8x22B](https://huggingface.co/mistralai/Mixtral-8x22B-v0.1)        | model                  | best accuracy                       |
 ### Hardware Requirement
 We have tested and the family of models in following setup:
-- empower-functions-small: fp16 on 1xA100 40G, GGUF and 4bit GGUF on Macbook M2 Pro with 32G RAM, in minimal the 4bit GGUF version requires 7.56G RAM.
 - empower-functions-medium: fp16 on 2xA100 80G
-- empower-functions-large: fp16 on 4xA100 80G
 ## Usage

 ## Family of Models
+| Model                           | Specs                                                                                             | Links                                                                                                                           | Notes                                |
+| ------------------------------- | ------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------ |
+| llama3-empower-functions-small  | 8k context, based on [Llama3 8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)               | [model](https://huggingface.co/empower-dev/llama3-empower-functions-small), [GGUF](https://huggingface.co/empower-dev/llama3-empower-functions-small-gguf)   | Most cost-effective, locally runnable |
+| empower-functions-medium        | 32k context, based on [Mixtral 8x7B](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) | [model](https://huggingface.co/empower-dev/empower-functions-medium)                                                             | Balance in accuracy and cost         |
+| llama3-empower-functions-large  | 65k context, based on [Llama3 70B](https://huggingface.co/meta-llama/Meta-Llama-3-70B)            | [model](https://huggingface.co/empower-dev/llama3-empower-functions-large)                                                      | Best accuracy                        |
 ### Hardware Requirement
 We have tested and the family of models in following setup:
+- empower-functions-small:  fp16 on 1xA100 40G, GGUF and 4bit GGUF on Macbook M2 Pro with 32G RAM, in minimal the 4bit GGUF version requires 7.56G RAM.
 - empower-functions-medium: fp16 on 2xA100 80G
+- empower-functions-large:  fp16 on 4xA100 80G
 ## Usage