Instructions to use andrijdavid/Meta-Llama-3-13B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use andrijdavid/Meta-Llama-3-13B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="andrijdavid/Meta-Llama-3-13B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("andrijdavid/Meta-Llama-3-13B-Instruct")
model = AutoModelForCausalLM.from_pretrained("andrijdavid/Meta-Llama-3-13B-Instruct")
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

vLLM

How to use andrijdavid/Meta-Llama-3-13B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "andrijdavid/Meta-Llama-3-13B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "andrijdavid/Meta-Llama-3-13B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/andrijdavid/Meta-Llama-3-13B-Instruct

SGLang

How to use andrijdavid/Meta-Llama-3-13B-Instruct 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 "andrijdavid/Meta-Llama-3-13B-Instruct" \
    --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": "andrijdavid/Meta-Llama-3-13B-Instruct",
		"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 "andrijdavid/Meta-Llama-3-13B-Instruct" \
        --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": "andrijdavid/Meta-Llama-3-13B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use andrijdavid/Meta-Llama-3-13B-Instruct with Docker Model Runner:
```
docker model run hf.co/andrijdavid/Meta-Llama-3-13B-Instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Meta-Llama-3-13B-Instruct

Meta-Llama-3-13B-Instruct is a meta-llama/Meta-Llama-3-8B-Instruct self-merge made with MergeKit.

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - layer_range: [0, 16]
    model: meta-llama/Meta-Llama-3-8B-Instruct
- sources:
  - layer_range: [4, 24]
    model: meta-llama/Meta-Llama-3-8B-Instruct
- sources:
  - layer_range: [8, 31]
    model: meta-llama/Meta-Llama-3-8B-Instruct
merge_method: passthrough
dtype: float16

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "andrijdavid/Meta-Llama-3-13B-Instruct"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

input_ids = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt"
).to(model.device)

terminators = [
    tokenizer.eos_token_id,
    tokenizer.convert_tokens_to_ids("<|eot_id|>")
]

outputs = model.generate(
    input_ids,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))

Downloads last month: 10

Safetensors

Model size

14B params

Tensor type

F16

Model tree for andrijdavid/Meta-Llama-3-13B-Instruct

Base model

meta-llama/Meta-Llama-3-8B-Instruct

Finetuned

(1093)

this model

Quantizations

1 model