Instructions to use Snowflake/snowflake-arctic-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Snowflake/snowflake-arctic-instruct with Transformers:

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

pipe = pipeline("text-generation", model="Snowflake/snowflake-arctic-instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Snowflake/snowflake-arctic-instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Snowflake/snowflake-arctic-instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Snowflake/snowflake-arctic-instruct

SGLang

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

Docker Model Runner
How to use Snowflake/snowflake-arctic-instruct with Docker Model Runner:
```
docker model run hf.co/Snowflake/snowflake-arctic-instruct
```

jeffra commited on May 7, 2024

Commit

5d68b84

verified ·

1 Parent(s): 125e72e

Upload modeling_arctic.py with huggingface_hub

Browse files

Files changed (1) hide show

modeling_arctic.py +2 -2

modeling_arctic.py CHANGED Viewed

@@ -56,7 +56,7 @@ from transformers.utils import (
 )
 from transformers.utils.import_utils import is_torch_fx_available
 from .configuration_arctic import ArcticConfig
-from transformers.integrations.deepspeed import is_deepspeed_available
 from transformers.utils.versions import require_version
 if is_deepspeed_available():
@@ -354,7 +354,7 @@ class ArcticAttention(nn.Module):
                                      ds_optimized_quantization_config=quantization_config,
                                      ds_optimized_base_weight_sharding=True,
                                      dtype=torch.bfloat16)
-        self.o_proj = get_arctic_linear(self.hidden_size, self.num_key_value_heads * self.head_dim, bias=False,
                                      use_deepspeed_implementation=self.use_deepspeed_implementation,
                                      ds_optimized_lora_config=deepspeed_lora_config,
                                      ds_optimized_quantization_config=quantization_config,

 )
 from transformers.utils.import_utils import is_torch_fx_available
 from .configuration_arctic import ArcticConfig
+from transformers.integrations.deepspeed import is_deepspeed_available
 from transformers.utils.versions import require_version
 if is_deepspeed_available():
                                      ds_optimized_quantization_config=quantization_config,
                                      ds_optimized_base_weight_sharding=True,
                                      dtype=torch.bfloat16)
+        self.o_proj = get_arctic_linear(self.hidden_size, self.hidden_size, bias=False,
                                      use_deepspeed_implementation=self.use_deepspeed_implementation,
                                      ds_optimized_lora_config=deepspeed_lora_config,
                                      ds_optimized_quantization_config=quantization_config,