Instructions to use meetkai/functionary-medium-v3.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meetkai/functionary-medium-v3.0 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="meetkai/functionary-medium-v3.0", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meetkai/functionary-medium-v3.0", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("meetkai/functionary-medium-v3.0", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use meetkai/functionary-medium-v3.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meetkai/functionary-medium-v3.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meetkai/functionary-medium-v3.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meetkai/functionary-medium-v3.0

SGLang

How to use meetkai/functionary-medium-v3.0 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "meetkai/functionary-medium-v3.0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meetkai/functionary-medium-v3.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "meetkai/functionary-medium-v3.0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meetkai/functionary-medium-v3.0",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use meetkai/functionary-medium-v3.0 with Docker Model Runner:
```
docker model run hf.co/meetkai/functionary-medium-v3.0
```

jeffreymeetkai commited on Aug 12, 2024

Commit

8c9e2fa

verified ·

1 Parent(s): 703922f

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -4

README.md CHANGED Viewed

@@ -21,13 +21,13 @@ The model determines when to execute functions, whether in parallel or serially,
 ## How to Get Started
-We provide custom code for both converting tool definitions into the system prompts and parsing raw model response into a JSON object containing `role`, `content` and `tool_calls` fields. This enables the model to be able to generate tool calls.
 ```python
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
-tokenizer = AutoTokenizer.from_pretrained("meetkai/functionary-medium-v3.0", trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
     "meetkai/functionary-medium-v3.0",
     device_map="auto",
@@ -57,7 +57,6 @@ tools = [
 messages = [{"role": "user", "content": "What is the weather in Istanbul and Singapore respectively?"}]
 final_prompt = tokenizer.apply_chat_template(messages, tools, add_generation_prompt=True, tokenize=False)
-tokenizer.padding_side = "left"
 inputs = tokenizer(final_prompt, return_tensors="pt").to("cuda")
 pred = model.generate_tool_use(**inputs, max_new_tokens=128, tokenizer=tokenizer)
 print(tokenizer.decode(pred.cpu()[0]))
@@ -67,7 +66,7 @@ print(tokenizer.decode(pred.cpu()[0]))
 We convert function definitions to a similar text to TypeScript definitions. Then we inject these definitions as system prompts. After that, we inject the default system prompt. Then we start the conversation messages.
-This formatting is also available via our vLLM server which we process the functions into Typescript definitions encapsulated in a system message and use a pre-defined Transformers chat template. This means that lists of messages can be formatted for you with the apply_chat_template() method within our server:
 ```python
 from openai import OpenAI

 ## How to Get Started
+We provide custom code for parsing raw model responses into a JSON object containing `role`, `content` and `tool_calls` fields. This enables the users to read the function-calling output of the model easily.
 ```python
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained("meetkai/functionary-medium-v3.0")
 model = AutoModelForCausalLM.from_pretrained(
     "meetkai/functionary-medium-v3.0",
     device_map="auto",
 messages = [{"role": "user", "content": "What is the weather in Istanbul and Singapore respectively?"}]
 final_prompt = tokenizer.apply_chat_template(messages, tools, add_generation_prompt=True, tokenize=False)
 inputs = tokenizer(final_prompt, return_tensors="pt").to("cuda")
 pred = model.generate_tool_use(**inputs, max_new_tokens=128, tokenizer=tokenizer)
 print(tokenizer.decode(pred.cpu()[0]))
 We convert function definitions to a similar text to TypeScript definitions. Then we inject these definitions as system prompts. After that, we inject the default system prompt. Then we start the conversation messages.
+This formatting is also available via our vLLM server which we process the functions into Typescript definitions encapsulated in a system message using a pre-defined Transformers Jinja chat template. This means that the lists of messages can be formatted for you with the apply_chat_template() method within our server:
 ```python
 from openai import OpenAI