Skip to content

Commit a495196

Browse files
Update README.md
1 parent d8bd378 commit a495196

File tree

1 file changed

+9
-6
lines changed

1 file changed

+9
-6
lines changed

examples/simple-function-call/README.md

Lines changed: 9 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -37,10 +37,9 @@ The LLM has access to a single tool:
3737
```
3838

3939
### Basic Usage
40-
```bash
40+
```
4141
./simple-function-call -m model.gguf -p "your request here"
4242
```
43-
4443
### Command Line Arguments
4544
- `--jinja` Is enabled by default
4645
- `-m model.gguf` - Model file path (REQUIRED)
@@ -53,8 +52,9 @@ The LLM has access to a single tool:
5352

5453
### Examples
5554

56-
```bash
55+
5756
# List files in current directory
57+
```
5858
./simple-function-call -m llama-3.2-1b.gguf -p "list all files in this directory" # I've had success even with this small model but I think it has trouble solving complex tasks it can still generate proper JSON for execution
5959
6060
{"name": "shell_command", "parameters": {"command": "ls -l"}}
@@ -122,9 +122,11 @@ Continuing conversation with command result...
122122
/usr/lib/libc.so.6(__libc_start_main+0x89) [0x7fdfb4112769]
123123
./build/bin/simple-function-call(+0x37615) [0x557f2b78b615]
124124
Aborted (core dumped)
125-
125+
```
126126

127127
# Check system information
128+
129+
```
128130
./simple-function-call -m llama-2-7b.gguf -p "check the current time" # might produce some JSON
129131
{
130132
"type": "function",
@@ -173,8 +175,9 @@ Response:
173175
} # The command in tried to use was probably too complex for the actual tool
174176
}
175177
main: decoded 134 tokens in 5.85 s, speed: 22.89 t/s # A better parser bigger model should produce better results
176-
177-
# You'll have less of these types of problems but you can't still nudge the smaller ones, if you have some knowledge you can always tell it to run commands directly but it defeats the purpose of it a bit, it would be good with some Speech to Text system where you wouldn't have to type but just say what you want the computer to do
178+
```
179+
# You'll have less of these types of problems with bigger models but you can't still nudge the smaller ones, if you have some knowledge you can always tell it to run commands directly but it defeats the purpose of it a bit, it would be good with some Speech to Text system where you wouldn't have to type but just say what you want the computer to do
180+
```
178181
./simple-function-call -m llama-3.2-1b-instruct.gguf -p "Check the current date" # And it will run the date command
179182
180183
{"type": "function", "name": "shell_command", "parameters": {"command": "date"}}

0 commit comments

Comments
 (0)