Instructions to use InterSync/Mistral-7B-Instruct-v0.2-Function-Calling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use InterSync/Mistral-7B-Instruct-v0.2-Function-Calling with Transformers:

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

pipe = pipeline("text-generation", model="InterSync/Mistral-7B-Instruct-v0.2-Function-Calling")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("InterSync/Mistral-7B-Instruct-v0.2-Function-Calling")
model = AutoModelForCausalLM.from_pretrained("InterSync/Mistral-7B-Instruct-v0.2-Function-Calling", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use InterSync/Mistral-7B-Instruct-v0.2-Function-Calling with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "InterSync/Mistral-7B-Instruct-v0.2-Function-Calling"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "InterSync/Mistral-7B-Instruct-v0.2-Function-Calling",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/InterSync/Mistral-7B-Instruct-v0.2-Function-Calling

SGLang

How to use InterSync/Mistral-7B-Instruct-v0.2-Function-Calling 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 "InterSync/Mistral-7B-Instruct-v0.2-Function-Calling" \
    --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": "InterSync/Mistral-7B-Instruct-v0.2-Function-Calling",
		"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 "InterSync/Mistral-7B-Instruct-v0.2-Function-Calling" \
        --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": "InterSync/Mistral-7B-Instruct-v0.2-Function-Calling",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use InterSync/Mistral-7B-Instruct-v0.2-Function-Calling with Docker Model Runner:
```
docker model run hf.co/InterSync/Mistral-7B-Instruct-v0.2-Function-Calling
```

kinqsradio commited on Mar 31, 2024

Commit

6a0d9f1

verified ·

1 Parent(s): 51da8aa

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -31

README.md CHANGED Viewed

@@ -53,33 +53,7 @@ tools = [
                 "required": ["location", "format"],
             },
         }
-    },
-    {
-        "type": "function",
-        "function": {
-            "name": "get_n_day_weather_forecast",
-            "description": "Get an N-day weather forecast",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "location": {
-                        "type": "string",
-                        "description": "The city and state, e.g. San Francisco, CA",
-                    },
-                    "format": {
-                        "type": "string",
-                        "enum": ["celsius", "fahrenheit"],
-                        "description": "The temperature unit to use. Infer this from the user's location.",
-                    },
-                    "num_days": {
-                        "type": "integer",
-                        "description": "The number of days to forecast",
-                    }
-                },
-                "required": ["location", "format", "num_days"]
-            },
-        }
-    },
 ]
 ```
@@ -107,10 +81,9 @@ messages = [
     },
     {
         "role": "user",
-        "content": "What is the current weather in San Francisco? And can you forecast that in the next 10 days?"
     },
 ]
 ```
 ### Preparing Model Inputs
@@ -122,14 +95,15 @@ model_inputs = inputs.to(device)
 ### Generating the Response
 ```python
 model.to(device)
 generate_ids = model.generate(model_inputs, streamer=streamer, do_sample=True, max_length=4096)
 decoded = tokenizer.batch_decode(generate_ids)
 ```
 ### Output
 ```python
-Sure, I can help with that. Here is the current weather in San Francisco: <tool_call>{'arguments': {'location': 'San Francisco, CA', 'format': 'celsius'}, 'name': 'get_current_weather'}</tool_call> And here is the weather forecast for the next 10 days in San Francisco: <tool_call>{'arguments': {'location': 'San Francisco, CA', 'format': 'celsius', 'num_days': 10}, 'name': 'get_n_day_weather_forecast'}</tool_call>
 ```

                 "required": ["location", "format"],
             },
         }
+    }
 ]
 ```
     },
     {
         "role": "user",
+        "content": "What is the current weather in San Francisco?"
     },
 ]
 ```
 ### Preparing Model Inputs
 ### Generating the Response
 ```python
 model.to(device)
 generate_ids = model.generate(model_inputs, streamer=streamer, do_sample=True, max_length=4096)
 decoded = tokenizer.batch_decode(generate_ids)
 ```
 ### Output
 ```python
+<tool_call>
+{"arguments": {"location": "San Francisco, CA", "format": "celsius"}, "name": "get_current_weather"}
+</tool_call>
 ```