Text Generation
Transformers
Safetensors
PyTorch
English
Korean
llama
saltlux
luxia
meta
llama-3
conversational
text-generation-inference
Instructions to use saltlux/Ko-Llama3-Luxia-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use saltlux/Ko-Llama3-Luxia-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="saltlux/Ko-Llama3-Luxia-8B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("saltlux/Ko-Llama3-Luxia-8B") model = AutoModelForCausalLM.from_pretrained("saltlux/Ko-Llama3-Luxia-8B", 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=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use saltlux/Ko-Llama3-Luxia-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "saltlux/Ko-Llama3-Luxia-8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "saltlux/Ko-Llama3-Luxia-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/saltlux/Ko-Llama3-Luxia-8B
- SGLang
How to use saltlux/Ko-Llama3-Luxia-8B 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 "saltlux/Ko-Llama3-Luxia-8B" \ --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": "saltlux/Ko-Llama3-Luxia-8B", "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 "saltlux/Ko-Llama3-Luxia-8B" \ --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": "saltlux/Ko-Llama3-Luxia-8B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use saltlux/Ko-Llama3-Luxia-8B with Docker Model Runner:
docker model run hf.co/saltlux/Ko-Llama3-Luxia-8B
Update README.md
Browse files
README.md
CHANGED
|
@@ -205,9 +205,9 @@ Llama-3-Tokenizerλ₯Ό νκ΅μ΄ νΉννκΈ° μν΄ νκ΅μ΄ ν ν° 17,536κ°λ₯Ό
|
|
| 205 |
</td>
|
| 206 |
</tr>
|
| 207 |
<tr>
|
| 208 |
-
<td><b>
|
| 209 |
</td>
|
| 210 |
-
<td><b>
|
| 211 |
</td>
|
| 212 |
</tr>
|
| 213 |
</table>
|
|
|
|
| 205 |
</td>
|
| 206 |
</tr>
|
| 207 |
<tr>
|
| 208 |
+
<td><b>νκ΅μ μ ν΅μμμΈ</b> ν볡과 μΌλ³Έμ μ ν΅μμμΈ μλ‘μΉ΄λ―Έλ λͺ¨λ 5λλ₯μ λ¬Ένλ₯Ό μμ©νκ³ , κ°κΈ° λ€λ₯Έ μ§μμ νΉμ§μ λ°μν μμμ κ°μΆκ³ μλ€. μ΄λ¬ν μμμ νΉμ§μ κ°κ°μ κ΅κ°μμ λ°μ ν΄ μ¨ μμ¬μ λ¬Ένμ κΈ°μ΄νλ€. ννΈ, νκ΅μ ν볡과 μΌλ³Έμ μλ‘μΉ΄λ―Έλ μλ‘ λΉμ·ν ννλ₯Ό κ°μ§κ³ μμ§λ§, κ·Έ μλ―Έλ λ€λ₯΄λ€. ν볡μ νκ΅μΈμ μ 체μ±μ λνλ΄λ©°, μλ‘μΉ΄λ―Έλ μΌλ³ΈμΈμ μ 체μ±μ λνλΈλ€. λ°λΌμ μ΄ λ κ°μ§ μμμ μλ‘ λ€λ₯Έ λ¬Ένμ λ°°κ²½μ κ°μ§ μ¬λλ€μ μ μ²΄μ± ννμ μ¬μ©λλ€.\nThe traditional costumes of Korea and Japan are hanbok and yorokami respectively. Both have been influenced by the cultures of other countries and reflect the characteristics of their respective regions. The distinctive features of these costumes are based on the history and culture of each country. However, although hanbok and yorokami share similar forms, they have different meanings. Hanbok represents Korean identity while yorokami represents Japanese identity. <μ΄ν μλ΅>
|
| 209 |
</td>
|
| 210 |
+
<td><b>νκ΅μ μ ν΅μμμΈ</b> ν볡μ νκ΅μ λ¬Ένμ μμ¬λ₯Ό κ³ μ€λν λ΄κ³ μλ μμ€ν λ¬Ένμ μ°μ΄λ€. νμ§λ§ μ΅κ·Ό λ€μ΄ ν볡μ λν κ΄μ¬μ΄ μ€μ΄λ€λ©΄μ, ν볡μ μ
λ μ¬λλ μ μ μ€μ΄λ€κ³ μλ€. μ΄μ λ°λΌ ν볡μ μλ¦λ€μκ³Ό κ°μΉλ₯Ό μλ¦¬κ³ , ν볡μ μ
λ κ²μ μ₯λ €νκΈ° μν λ€μν λ
Έλ ₯μ΄ νμνλ€.\n\n첫째, ν볡μ μλ¦λ€μκ³Ό κ°μΉλ₯Ό μ리기 μν΄μλ ν볡μ μμ¬μ λ¬Ένμ μλ―Έλ₯Ό κ΅μ‘νλ κ²μ΄ μ€μνλ€. ν볡μ νκ΅μΈμ μ 체μ±μ μμ§νλ μ볡μΌλ‘, μ€λ μΈμ λμ μ°λ¦¬ λ―Όμ‘±μ μΆ μμμ μ€μν μν μ ν΄μλ€. λ°λΌμ ν볡μ μμ¬μ λ¬Ένμ μλ―Έλ₯Ό μ΄ν΄νλ©΄, ν볡μ μλ¦λ€μκ³Ό κ°μΉλ₯Ό λμ± μ λλ μ μμ κ²μ΄λ€.\n\nλμ§Έ, ν볡μ μ
λ κ²μ μ₯λ €νκΈ° μν΄μλ ν볡μ μ
μ μ μλ κΈ°νλ₯Ό μ 곡νκ³ , ν볡μ μ
λ κ²μ νΈλ¦¬νκ² λ§λλ κ²μ΄ μ€μνλ€. <μ΄ν μλ΅>
|
| 211 |
</td>
|
| 212 |
</tr>
|
| 213 |
</table>
|