Instructions to use BAAI/AquilaChat2-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BAAI/AquilaChat2-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BAAI/AquilaChat2-7B", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("BAAI/AquilaChat2-7B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use BAAI/AquilaChat2-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BAAI/AquilaChat2-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BAAI/AquilaChat2-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BAAI/AquilaChat2-7B
- SGLang
How to use BAAI/AquilaChat2-7B 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/AquilaChat2-7B" \ --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/AquilaChat2-7B", "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/AquilaChat2-7B" \ --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/AquilaChat2-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BAAI/AquilaChat2-7B with Docker Model Runner:
docker model run hf.co/BAAI/AquilaChat2-7B
Update config.json
Browse files- config.json +6 -8
config.json
CHANGED
|
@@ -9,20 +9,18 @@
|
|
| 9 |
"bos_token_id": 100006,
|
| 10 |
"eos_token_id": 100007,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
-
"hidden_size":
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size":
|
| 15 |
-
"max_position_embeddings":
|
| 16 |
"model_type": "aquila",
|
| 17 |
-
"num_attention_heads":
|
| 18 |
-
"num_hidden_layers":
|
| 19 |
-
"num_key_value_heads": 8,
|
| 20 |
"pad_token_id": 0,
|
| 21 |
-
"pretraining_tp": 1,
|
| 22 |
"rms_norm_eps": 1e-05,
|
| 23 |
"rope_scaling": null,
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
-
"torch_dtype": "
|
| 26 |
"transformers_version": "4.31.0",
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_size": 100008
|
|
|
|
| 9 |
"bos_token_id": 100006,
|
| 10 |
"eos_token_id": 100007,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 11008,
|
| 15 |
+
"max_position_embeddings": 2048,
|
| 16 |
"model_type": "aquila",
|
| 17 |
+
"num_attention_heads": 32,
|
| 18 |
+
"num_hidden_layers": 32,
|
|
|
|
| 19 |
"pad_token_id": 0,
|
|
|
|
| 20 |
"rms_norm_eps": 1e-05,
|
| 21 |
"rope_scaling": null,
|
| 22 |
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "float16",
|
| 24 |
"transformers_version": "4.31.0",
|
| 25 |
"use_cache": true,
|
| 26 |
"vocab_size": 100008
|