Update README.md
Browse files
README.md
CHANGED
@@ -21,12 +21,23 @@ These files are fp16 format model files for [Gorilla 7B](https://huggingface.co/
|
|
21 |
|
22 |
They are the result of merging the deltas and then uploading in fp16 format.
|
23 |
|
|
|
|
|
|
|
|
|
24 |
## Other repositories available
|
25 |
|
26 |
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/gorilla-7B-GPTQ)
|
27 |
* [4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/gorilla-7B-GGML)
|
28 |
* [Merged, unquantised fp16 model in HF format](https://huggingface.co/TheBloke/gorilla-7B-fp16)
|
29 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
## Want to support my work?
|
31 |
|
32 |
I've had a lot of people ask if they can contribute. I love providing models and helping people, but it is starting to rack up pretty big cloud computing bills.
|
|
|
21 |
|
22 |
They are the result of merging the deltas and then uploading in fp16 format.
|
23 |
|
24 |
+
**NOTE**: This is not a regular LLM. It is designed to allow LLMs to use tools by invoking APIs.
|
25 |
+
|
26 |
+
"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. "
|
27 |
+
|
28 |
## Other repositories available
|
29 |
|
30 |
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/gorilla-7B-GPTQ)
|
31 |
* [4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/gorilla-7B-GGML)
|
32 |
* [Merged, unquantised fp16 model in HF format](https://huggingface.co/TheBloke/gorilla-7B-fp16)
|
33 |
|
34 |
+
## Prompt template
|
35 |
+
|
36 |
+
```
|
37 |
+
###USER: find me an API to generate cute cat images
|
38 |
+
###ASSISTANT:
|
39 |
+
```
|
40 |
+
|
41 |
## Want to support my work?
|
42 |
|
43 |
I've had a lot of people ask if they can contribute. I love providing models and helping people, but it is starting to rack up pretty big cloud computing bills.
|