Instructions to use mzbac/llama-3-8B-Instruct-function-calling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mzbac/llama-3-8B-Instruct-function-calling with Transformers:

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

pipe = pipeline("text-generation", model="mzbac/llama-3-8B-Instruct-function-calling")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mzbac/llama-3-8B-Instruct-function-calling")
model = AutoModelForCausalLM.from_pretrained("mzbac/llama-3-8B-Instruct-function-calling")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mzbac/llama-3-8B-Instruct-function-calling with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mzbac/llama-3-8B-Instruct-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": "mzbac/llama-3-8B-Instruct-function-calling",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mzbac/llama-3-8B-Instruct-function-calling

SGLang

How to use mzbac/llama-3-8B-Instruct-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 "mzbac/llama-3-8B-Instruct-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": "mzbac/llama-3-8B-Instruct-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 "mzbac/llama-3-8B-Instruct-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": "mzbac/llama-3-8B-Instruct-function-calling",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mzbac/llama-3-8B-Instruct-function-calling with Docker Model Runner:
```
docker model run hf.co/mzbac/llama-3-8B-Instruct-function-calling
```

mzbac commited on Apr 28, 2024

Commit

d51b6b7

verified ·

1 Parent(s): aaab974

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -98,7 +98,7 @@ lora_layers: 32
 batch_size: 1
 # Iterations to train for.
-iters: 113000
 # Number of validation batches, -1 uses the entire validation set.
 val_batches: 25
@@ -144,9 +144,9 @@ lora_parameters:
   dropout: 0.05
 # Schedule can only be specified in a config file, uncomment to use.
-lr_schedule:
-  name: cosine_decay
-  warmup: 100 # 0 for no warmup
-  warmup_init: 1e-7 # 0 if not specified
-  arguments: [1e-6, 1000, 1e-7] # passed to scheduler
 ```

 batch_size: 1
 # Iterations to train for.
+iters: 6000
 # Number of validation batches, -1 uses the entire validation set.
 val_batches: 25
   dropout: 0.05
 # Schedule can only be specified in a config file, uncomment to use.
+#lr_schedule:
+#  name: cosine_decay
+#  warmup: 100 # 0 for no warmup
+#  warmup_init: 1e-7 # 0 if not specified
+#  arguments: [1e-6, 1000, 1e-7] # passed to scheduler
 ```