Instructions to use BAAI/AquilaChat2-70B-Expr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BAAI/AquilaChat2-70B-Expr with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BAAI/AquilaChat2-70B-Expr")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("BAAI/AquilaChat2-70B-Expr", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use BAAI/AquilaChat2-70B-Expr with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BAAI/AquilaChat2-70B-Expr" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BAAI/AquilaChat2-70B-Expr", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BAAI/AquilaChat2-70B-Expr
- SGLang
How to use BAAI/AquilaChat2-70B-Expr 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/AquilaChat2-70B-Expr" \ --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/AquilaChat2-70B-Expr", "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/AquilaChat2-70B-Expr" \ --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/AquilaChat2-70B-Expr", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BAAI/AquilaChat2-70B-Expr with Docker Model Runner:
docker model run hf.co/BAAI/AquilaChat2-70B-Expr
Update modeling_aquila.py
Browse files- modeling_aquila.py +1 -1
modeling_aquila.py
CHANGED
|
@@ -931,7 +931,7 @@ class AquilaForCausalLM(AquilaPreTrainedModel):
|
|
| 931 |
topk = 1
|
| 932 |
temperature = 1.0
|
| 933 |
if sft:
|
| 934 |
-
tokens = covert_prompt_to_input_ids_with_history(text, history=[], tokenizer=tokenizer, max_token=
|
| 935 |
tokens = torch.tensor(tokens)[None,].to(device)
|
| 936 |
else :
|
| 937 |
tokens = tokenizer.encode_plus(text)["input_ids"]
|
|
|
|
| 931 |
topk = 1
|
| 932 |
temperature = 1.0
|
| 933 |
if sft:
|
| 934 |
+
tokens = covert_prompt_to_input_ids_with_history(text, history=[], tokenizer=tokenizer, max_token=20480, convo_template=convo_template)
|
| 935 |
tokens = torch.tensor(tokens)[None,].to(device)
|
| 936 |
else :
|
| 937 |
tokens = tokenizer.encode_plus(text)["input_ids"]
|