Instructions to use BAAI/AquilaCode-py with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BAAI/AquilaCode-py with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BAAI/AquilaCode-py")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("BAAI/AquilaCode-py", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use BAAI/AquilaCode-py with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BAAI/AquilaCode-py" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BAAI/AquilaCode-py", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BAAI/AquilaCode-py
- SGLang
How to use BAAI/AquilaCode-py 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 "BAAI/AquilaCode-py" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BAAI/AquilaCode-py", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "BAAI/AquilaCode-py" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BAAI/AquilaCode-py", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BAAI/AquilaCode-py with Docker Model Runner:
docker model run hf.co/BAAI/AquilaCode-py
Commit ·
f359e84
1
Parent(s): 06213d5
Update README_zh.md
Browse files- README_zh.md +7 -9
README_zh.md
CHANGED
|
@@ -49,20 +49,18 @@ Aquila-7B v0.8 在 FlagEval 大模型评测中( “客观”)相比0.7的版
|
|
| 49 |
```python
|
| 50 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 51 |
import torch
|
| 52 |
-
from cyg_conversation import covert_prompt_to_input_ids_with_history
|
| 53 |
|
| 54 |
-
|
| 55 |
-
|
|
|
|
| 56 |
model.eval()
|
| 57 |
-
model.to("cuda:
|
| 58 |
-
vocab = tokenizer.vocab
|
| 59 |
-
print(len(vocab))
|
| 60 |
|
| 61 |
-
text = "
|
| 62 |
|
| 63 |
-
tokens =
|
| 64 |
|
| 65 |
-
tokens = torch.tensor(tokens)[None,].to("cuda:
|
| 66 |
|
| 67 |
|
| 68 |
with torch.no_grad():
|
|
|
|
| 49 |
```python
|
| 50 |
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 51 |
import torch
|
|
|
|
| 52 |
|
| 53 |
+
model_info = "BAAI/AquilaCode-py"
|
| 54 |
+
tokenizer = AutoTokenizer.from_pretrained(model_info, trust_remote_code=True)
|
| 55 |
+
model = AutoModelForCausalLM.from_pretrained(model_info, trust_remote_code=True)
|
| 56 |
model.eval()
|
| 57 |
+
model.to("cuda:4")
|
|
|
|
|
|
|
| 58 |
|
| 59 |
+
text = "#补全代码\ndef quick_sort(x):"
|
| 60 |
|
| 61 |
+
tokens = tokenizer.encode_plus(text)['input_ids'][:-1]
|
| 62 |
|
| 63 |
+
tokens = torch.tensor(tokens)[None,].to("cuda:4")
|
| 64 |
|
| 65 |
|
| 66 |
with torch.no_grad():
|