Instructions to use NeuraCraft/Lance-AI-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NeuraCraft/Lance-AI-V2 with Transformers:

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

pipe = pipeline("text-generation", model="NeuraCraft/Lance-AI-V2", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("NeuraCraft/Lance-AI-V2", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NeuraCraft/Lance-AI-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NeuraCraft/Lance-AI-V2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeuraCraft/Lance-AI-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NeuraCraft/Lance-AI-V2

SGLang

How to use NeuraCraft/Lance-AI-V2 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 "NeuraCraft/Lance-AI-V2" \
    --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": "NeuraCraft/Lance-AI-V2",
		"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 "NeuraCraft/Lance-AI-V2" \
        --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": "NeuraCraft/Lance-AI-V2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NeuraCraft/Lance-AI-V2 with Docker Model Runner:
```
docker model run hf.co/NeuraCraft/Lance-AI-V2
```

NeuraCraft commited on May 23

Commit

2334367

1 Parent(s): ce83413

Upload lance_ai_model.py with huggingface_hub

Browse files

Files changed (1) hide show

lance_ai_model.py +13 -1

lance_ai_model.py CHANGED Viewed

@@ -348,8 +348,20 @@ class LanceAI(LanceAIPreTrainedModel, GenerationMixin):
         return CausalLMOutputWithPast(loss=loss, logits=logits, past_key_values=past)
     def prepare_inputs_for_generation(self, input_ids, past_key_values=None, attention_mask=None, **kwargs):
-        if past_key_values is not None:
             input_ids = input_ids[:, -1:]
         return {
             "input_ids": input_ids,

         return CausalLMOutputWithPast(loss=loss, logits=logits, past_key_values=past)
+    def _past_seq_len(self, past_key_values):
+        if past_key_values is None:
+            return 0
+        if hasattr(past_key_values, 'get_seq_length'):
+            return past_key_values.get_seq_length()
+        if isinstance(past_key_values, list) and len(past_key_values) > 0:
+            if past_key_values[0] is not None:
+                k, v = past_key_values[0]
+                if k is not None:
+                    return k.shape[2]
+        return 0
     def prepare_inputs_for_generation(self, input_ids, past_key_values=None, attention_mask=None, **kwargs):
+        if self._past_seq_len(past_key_values) > 0:
             input_ids = input_ids[:, -1:]
         return {
             "input_ids": input_ids,