Instructions to use Eurdem/Defne_llama3_2x8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Eurdem/Defne_llama3_2x8B with Transformers:

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

pipe = pipeline("text-generation", model="Eurdem/Defne_llama3_2x8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Eurdem/Defne_llama3_2x8B")
model = AutoModelForCausalLM.from_pretrained("Eurdem/Defne_llama3_2x8B")
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 Eurdem/Defne_llama3_2x8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Eurdem/Defne_llama3_2x8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Eurdem/Defne_llama3_2x8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Eurdem/Defne_llama3_2x8B

SGLang

How to use Eurdem/Defne_llama3_2x8B 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 "Eurdem/Defne_llama3_2x8B" \
    --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": "Eurdem/Defne_llama3_2x8B",
		"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 "Eurdem/Defne_llama3_2x8B" \
        --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": "Eurdem/Defne_llama3_2x8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Eurdem/Defne_llama3_2x8B with Docker Model Runner:
```
docker model run hf.co/Eurdem/Defne_llama3_2x8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

💻 For English

Defne_llama3_2x8B is a Mixure of Experts (MoE) (two llama3 models). (Change the system prompt for Turkish as shown below)

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "Eurdem/Defne_llama3_2x8B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto", load_in_8bit= True)

messages = [{"role": "system", "content": "You are a helpful chatbot, named Defne, who always responds friendly."},
            {"role": "user", "content": "Answer the questions: 1) Who are you? 2) f(x)=3x^2+4x+12 so what is f(3)?"},
]

input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
outputs = model.generate(input_ids, max_new_tokens=1024, do_sample=True, temperature=0.7, top_p=0.7, top_k=500,)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))

Output

Hello there! I'm Defne, a friendly chatbot here to help with any questions you may have.

Now, let's get to the math problem!

The function is f(x) = 3x^2 + 4x + 12, and we want to find f(3). To do that, we can plug in 3 for x in the function:

f(3) = 3(3)^2 + 4(3) + 12
f(3) = 3(9) + 12 + 12
f(3) = 27 + 24
f(3) = 51

So, f(3) is equal to 51!

💻 Türkçe İçin

Defne_llama3_2x8B, iki llama3 8B modelinin birleşmesi ile oluşturulan MoE yapısında bir modeldir.

!pip install -qU transformers bitsandbytes accelerate

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = "Eurdem/Defne_llama3_2x8B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto", load_in_8bit= True)

messages = [{"role": "system", "content": "Sen, Defne isimli Türkçe konuşan bir chatbotsun."},
            {"role": "user", "content": "Soruları numaralandırarak cevapla. 1) Sen kimsin?  2)f(x)=3x^2+4x+12 ise f(3) kaçtır?"}
]

input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
outputs = model.generate(input_ids, max_new_tokens=1024, do_sample=True, temperature=0.7, top_p=0.7, top_k=500,)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))

Çıktı

Merhaba!

1. Ben Defne, Türkçe konuşan bir chatbot.

2. f(x) = 3x^2 + 4x + 12 formülüne göre, f(3)'ü hesaplamak isterseniz, x'in değeri 3 olarak girelim:

f(3) = 3(3)^2 + 4(3) + 12
= 3(9) + 12 + 12
= 27 + 24
= 51

Bu nedenle, f(3) 51'dir.

Downloads last month: 15

Safetensors

Model size

14B params

Tensor type

BF16

Model tree for Eurdem/Defne_llama3_2x8B

Adapters

78 models

Quantizations

3 models