Instructions to use BAAI/AquilaDense-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BAAI/AquilaDense-7B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="BAAI/AquilaDense-7B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("BAAI/AquilaDense-7B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BAAI/AquilaDense-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BAAI/AquilaDense-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BAAI/AquilaDense-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BAAI/AquilaDense-7B

SGLang

How to use BAAI/AquilaDense-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/AquilaDense-7B" \
    --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": "BAAI/AquilaDense-7B",
		"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 "BAAI/AquilaDense-7B" \
        --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": "BAAI/AquilaDense-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BAAI/AquilaDense-7B with Docker Model Runner:
```
docker model run hf.co/BAAI/AquilaDense-7B
```

ldwang commited on Jun 16, 2024

Commit

f66731c

verified ·

1 Parent(s): 4a9e3d2

Update config.json

Browse files

Files changed (1) hide show

config.json +7 -7

config.json CHANGED Viewed

@@ -2,25 +2,25 @@
   "architectures": [
     "AquilaDenseForCausalLM"
   ],
   "auto_map": {
     "AutoConfig": "configuration_aquiladense.AquilaDenseConfig",
     "AutoModelForCausalLM": "modeling_aquiladense.AquilaDenseForCausalLM"
   },
-  "attention_dropout": 0.0,
   "bos_token_id": 151849,
   "eos_token_id": 151850,
   "hidden_act": "silu",
-  "hidden_size": 5120,
   "initializer_range": 0.02,
-  "intermediate_size": 17920,
-  "rms_norm_eps": 1e-05,
   "max_position_embeddings": 4096,
   "model_type": "aquiladense",
-  "num_attention_heads": 40,
-  "num_hidden_layers": 40,
   "num_key_value_heads": 8,
   "pad_token_id": 151643,
   "pretraining_tp": 1,
   "rope_scaling": null,
   "rope_theta": 1000000.0,
   "tie_word_embeddings": false,
@@ -29,4 +29,4 @@
   "_attn_implementation": "flash_attention_2",
   "use_cache": true,
   "vocab_size": 151851
-}

   "architectures": [
     "AquilaDenseForCausalLM"
   ],
+  "attention_dropout": 0.0,
   "auto_map": {
     "AutoConfig": "configuration_aquiladense.AquilaDenseConfig",
     "AutoModelForCausalLM": "modeling_aquiladense.AquilaDenseForCausalLM"
   },
   "bos_token_id": 151849,
   "eos_token_id": 151850,
   "hidden_act": "silu",
+  "hidden_size": 4096,
   "initializer_range": 0.02,
+  "intermediate_size": 14336,
   "max_position_embeddings": 4096,
   "model_type": "aquiladense",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pad_token_id": 151643,
   "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 1000000.0,
   "tie_word_embeddings": false,
   "_attn_implementation": "flash_attention_2",
   "use_cache": true,
   "vocab_size": 151851
+}