Update README.md
Browse files
README.md
CHANGED
@@ -26,12 +26,23 @@ GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/gger
|
|
26 |
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
|
27 |
* [ctransformers](https://github.com/marella/ctransformers)
|
28 |
|
|
|
|
|
|
|
|
|
29 |
## Other repositories available
|
30 |
|
31 |
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/gorilla-7B-GPTQ)
|
32 |
* [4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/gorilla-7B-GGML)
|
33 |
* [Merged, unquantised fp16 model in HF format](https://huggingface.co/TheBloke/gorilla-7B-fp16)
|
34 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
## THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 19th 2023 - commit 2d5db48)!
|
36 |
|
37 |
llama.cpp recently made another breaking change to its quantisation methods - https://github.com/ggerganov/llama.cpp/pull/1508
|
|
|
26 |
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
|
27 |
* [ctransformers](https://github.com/marella/ctransformers)
|
28 |
|
29 |
+
**NOTE**: This is not a regular LLM. It is designed to allow LLMs to use tools by invoking APIs.
|
30 |
+
|
31 |
+
"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. "
|
32 |
+
|
33 |
## Other repositories available
|
34 |
|
35 |
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/gorilla-7B-GPTQ)
|
36 |
* [4-bit, 5-bit, and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/gorilla-7B-GGML)
|
37 |
* [Merged, unquantised fp16 model in HF format](https://huggingface.co/TheBloke/gorilla-7B-fp16)
|
38 |
|
39 |
+
## Prompt template
|
40 |
+
|
41 |
+
```
|
42 |
+
###USER: find me an API to generate cute cat images
|
43 |
+
###ASSISTANT:
|
44 |
+
```
|
45 |
+
|
46 |
## THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 19th 2023 - commit 2d5db48)!
|
47 |
|
48 |
llama.cpp recently made another breaking change to its quantisation methods - https://github.com/ggerganov/llama.cpp/pull/1508
|