Instructions to use communityai/apt_zp_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use communityai/apt_zp_v1 with Transformers:

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

pipe = pipeline("text-generation", model="communityai/apt_zp_v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("communityai/apt_zp_v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use communityai/apt_zp_v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "communityai/apt_zp_v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "communityai/apt_zp_v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/communityai/apt_zp_v1

SGLang

How to use communityai/apt_zp_v1 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 "communityai/apt_zp_v1" \
    --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": "communityai/apt_zp_v1",
		"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 "communityai/apt_zp_v1" \
        --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": "communityai/apt_zp_v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use communityai/apt_zp_v1 with Docker Model Runner:
```
docker model run hf.co/communityai/apt_zp_v1
```

communityai commited on Nov 1, 2023

Commit

a2f382b

1 Parent(s): d7fae75

Update config.json

Browse files

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
   "architectures": [
-    "MistralForCausalLM"
   ],
   "bos_token_id": 1,
   "eos_token_id": 2,
@@ -10,7 +10,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 14336,
   "max_position_embeddings": 32768,
-  "model_type": "mistral",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,

 {
   "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
   "architectures": [
+    "LuminaForCausalLM"
   ],
   "bos_token_id": 1,
   "eos_token_id": 2,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
   "max_position_embeddings": 32768,
+  "model_type": "lumina",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,