Update README.md
Browse files
README.md
CHANGED
@@ -23,12 +23,23 @@ This repo contains a quantised 4-bit GPTQ model for [Gorilla 7B](https://hugging
|
|
23 |
|
24 |
It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
|
25 |
|
|
|
|
|
|
|
|
|
26 |
## Other repositories available
|
27 |
|
28 |
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/gorilla-7B-GPTQ)
|
29 |
* [4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/gorilla-7B-GGML)
|
30 |
* [Merged, unquantised fp16 model in HF format](https://huggingface.co/TheBloke/gorilla-7B-fp16)
|
31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
## How to easily download and use this model in text-generation-webui
|
33 |
|
34 |
Open the text-generation-webui UI as normal.
|
|
|
23 |
|
24 |
It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com/qwopqwop200/GPTQ-for-LLaMa).
|
25 |
|
26 |
+
**NOTE**: This is not a regular LLM. It is designed to allow LLMs to use tools by invoking APIs.
|
27 |
+
|
28 |
+
"Gorilla enables LLMs to use tools by invoking APIs. Given a natural language query, Gorilla can write a semantically- and syntactically- correct API to invoke. With Gorilla, we are the first to demonstrate how to use LLMs to invoke 1,600+ (and growing) API calls accurately while reducing hallucination. "
|
29 |
+
|
30 |
## Other repositories available
|
31 |
|
32 |
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/gorilla-7B-GPTQ)
|
33 |
* [4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/gorilla-7B-GGML)
|
34 |
* [Merged, unquantised fp16 model in HF format](https://huggingface.co/TheBloke/gorilla-7B-fp16)
|
35 |
|
36 |
+
## Prompt template
|
37 |
+
|
38 |
+
```
|
39 |
+
###USER: find me an API to generate cute cat images
|
40 |
+
###ASSISTANT:
|
41 |
+
```
|
42 |
+
|
43 |
## How to easily download and use this model in text-generation-webui
|
44 |
|
45 |
Open the text-generation-webui UI as normal.
|