Instructions to use TeamDelta/llama3-8B-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TeamDelta/llama3-8B-test with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TeamDelta/llama3-8B-test") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("TeamDelta/llama3-8B-test") model = AutoModelForCausalLM.from_pretrained("TeamDelta/llama3-8B-test") 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 TeamDelta/llama3-8B-test with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TeamDelta/llama3-8B-test" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TeamDelta/llama3-8B-test", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/TeamDelta/llama3-8B-test
- SGLang
How to use TeamDelta/llama3-8B-test 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 "TeamDelta/llama3-8B-test" \ --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": "TeamDelta/llama3-8B-test", "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 "TeamDelta/llama3-8B-test" \ --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": "TeamDelta/llama3-8B-test", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use TeamDelta/llama3-8B-test with Docker Model Runner:
docker model run hf.co/TeamDelta/llama3-8B-test
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,50 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: llama3
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
|
| 6 |
+
## how to use
|
| 7 |
+
|
| 8 |
+
```python
|
| 9 |
+
import torch
|
| 10 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 11 |
+
|
| 12 |
+
DEFAULT_SYSTEM_PROMPT = "あなたは誠実で優秀な日本人のアシスタントです。特に指示が無い場合は、常に日本語で回答してください。"
|
| 13 |
+
text = "優秀なAIとはなんですか? またあなたの考える優秀なAIに重要なポイントを5つ挙げて下さい。"
|
| 14 |
+
|
| 15 |
+
model_name = "TeamDelta/llama3-8B-test"
|
| 16 |
+
|
| 17 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 18 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 19 |
+
model_name,
|
| 20 |
+
torch_dtype="auto",
|
| 21 |
+
device_map="auto",
|
| 22 |
+
)
|
| 23 |
+
model.eval()
|
| 24 |
+
|
| 25 |
+
messages = [
|
| 26 |
+
{"role": "system", "content": DEFAULT_SYSTEM_PROMPT},
|
| 27 |
+
{"role": "user", "content": text},
|
| 28 |
+
]
|
| 29 |
+
prompt = tokenizer.apply_chat_template(
|
| 30 |
+
messages,
|
| 31 |
+
tokenize=False,
|
| 32 |
+
add_generation_prompt=True
|
| 33 |
+
)
|
| 34 |
+
token_ids = tokenizer.encode(
|
| 35 |
+
prompt, add_special_tokens=False, return_tensors="pt"
|
| 36 |
+
)
|
| 37 |
+
|
| 38 |
+
with torch.no_grad():
|
| 39 |
+
output_ids = model.generate(
|
| 40 |
+
token_ids.to(model.device),
|
| 41 |
+
max_new_tokens=1200,
|
| 42 |
+
do_sample=True,
|
| 43 |
+
temperature=0.6,
|
| 44 |
+
top_p=0.9,
|
| 45 |
+
)
|
| 46 |
+
output = tokenizer.decode(
|
| 47 |
+
output_ids.tolist()[0][token_ids.size(1):], skip_special_tokens=True
|
| 48 |
+
)
|
| 49 |
+
print(output)
|
| 50 |
+
```
|