Instructions to use Nexusflow/Starling-LM-7B-beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nexusflow/Starling-LM-7B-beta with Transformers:

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

pipe = pipeline("text-generation", model="Nexusflow/Starling-LM-7B-beta")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nexusflow/Starling-LM-7B-beta")
model = AutoModelForCausalLM.from_pretrained("Nexusflow/Starling-LM-7B-beta")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Nexusflow/Starling-LM-7B-beta with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Nexusflow/Starling-LM-7B-beta

SGLang

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

Docker Model Runner
How to use Nexusflow/Starling-LM-7B-beta with Docker Model Runner:
```
docker model run hf.co/Nexusflow/Starling-LM-7B-beta
```

SafetensorError: Error while deserializing header: MetadataIncompleteBuffer

#16

by chandrak - opened Apr 10, 2024

Discussion

chandrak

Apr 10, 2024

What could be the reason for this? It was working fine until a while ago.
```

SafetensorError Traceback (most recent call last)
/tmp/ipykernel_2268/3485156104.py in <cell line: 1>()
----> 1 model = AutoModelForCausalLM.from_pretrained("Nexusflow/Starling-LM-7B-beta")

~/conda/pytorch21_p39_gpu_v1/lib/python3.9/site-packages/transformers/models/auto/auto_factory.py in from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
564 elif type(config) in cls._model_mapping.keys():
565 model_class = _get_model_class(config, cls._model_mapping)
--> 566 return model_class.from_pretrained(
567 pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs
568 )

~/conda/pytorch21_p39_gpu_v1/lib/python3.9/site-packages/transformers/modeling_utils.py in from_pretrained(cls, pretrained_model_name_or_path, config, cache_dir, ignore_mismatched_sizes, force_download, local_files_only, token, revision, use_safetensors, *model_args, **kwargs)
3848 offload_index,
3849 error_msgs,
-> 3850 ) = cls._load_pretrained_model(
3851 model,
3852 state_dict,

~/conda/pytorch21_p39_gpu_v1/lib/python3.9/site-packages/transformers/modeling_utils.py in _load_pretrained_model(cls, model, state_dict, loaded_keys, resolved_archive_file, pretrained_model_name_or_path, ignore_mismatched_sizes, sharded_metadata, _fast_init, low_cpu_mem_usage, device_map, offload_folder, offload_state_dict, dtype, is_quantized, keep_in_fp32_modules)
4257 if shard_file in disk_only_shard_files:
4258 continue
-> 4259 state_dict = load_state_dict(shard_file)
4260
4261 # Mistmatched keys contains tuples key/shape1/shape2 of weights in the checkpoint that have a shape not

~/conda/pytorch21_p39_gpu_v1/lib/python3.9/site-packages/transformers/modeling_utils.py in load_state_dict(checkpoint_file)
504 if checkpoint_file.endswith(".safetensors") and is_safetensors_available():
505 # Check format of the archive
--> 506 with safe_open(checkpoint_file, framework="pt") as f:
507 metadata = f.metadata()
508 if metadata.get("format") not in ["pt", "tf", "flax"]:

SafetensorError: Error while deserializing header: MetadataIncompleteBuffer
```

karthik-ganesan-nexusflow

Apr 11, 2024

@chandrak could you check your transformers version , also try clearing HF cache and try again

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

SafetensorError: Error while deserializing header: MetadataIncompleteBuffer

What could be the reason for this? It was working fine until a while ago.```

What could be the reason for this? It was working fine until a while ago.
```