Instructions to use dphn/dolphin-2.1-mistral-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dphn/dolphin-2.1-mistral-7b with Transformers:

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

pipe = pipeline("text-generation", model="dphn/dolphin-2.1-mistral-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dphn/dolphin-2.1-mistral-7b")
model = AutoModelForCausalLM.from_pretrained("dphn/dolphin-2.1-mistral-7b")
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 dphn/dolphin-2.1-mistral-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dphn/dolphin-2.1-mistral-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": "dphn/dolphin-2.1-mistral-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dphn/dolphin-2.1-mistral-7b

SGLang

How to use dphn/dolphin-2.1-mistral-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 "dphn/dolphin-2.1-mistral-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": "dphn/dolphin-2.1-mistral-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 "dphn/dolphin-2.1-mistral-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": "dphn/dolphin-2.1-mistral-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dphn/dolphin-2.1-mistral-7b with Docker Model Runner:
```
docker model run hf.co/dphn/dolphin-2.1-mistral-7b
```

tokenizer = AutoTokenizer.from_pretrained("ehartford/dolphin-2.1-mistral-7b") results in unk error related to tokens greater than 32000

#13

by LaferriereJC - opened Oct 25, 2023

Discussion

LaferriereJC

Oct 25, 2023

ValueError Traceback (most recent call last)
Cell In[57], line 1
----> 1 tokenizer = AutoTokenizer.from_pretrained("ehartford/dolphin-2.1-mistral-7b")

File H:\py310-venv\lib\site-packages\transformers\models\auto\tokenization_auto.py:694, in AutoTokenizer.from_pretrained(cls, pretrained_model_name_or_path, *inputs, **kwargs)
690 if tokenizer_class is None:
691 raise ValueError(
692 f"Tokenizer class {tokenizer_class_candidate} does not exist or is not currently imported."
693 )
--> 694 return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
696 # Otherwise we have to be creative.
697 # if model is an encoder decoder, the encoder tokenizer class is used by default
698 if isinstance(config, EncoderDecoderConfig):

File H:\py310-venv\lib\site-packages\transformers\tokenization_utils_base.py:1812, in PreTrainedTokenizerBase.from_pretrained(cls, pretrained_model_name_or_path, *init_inputs, **kwargs)
1809 else:
1810 logger.info(f"loading file {file_path} from cache at {resolved_vocab_files[file_id]}")
-> 1812 return cls._from_pretrained(
1813 resolved_vocab_files,
1814 pretrained_model_name_or_path,
1815 init_configuration,
1816 *init_inputs,
1817 use_auth_token=use_auth_token,
1818 cache_dir=cache_dir,
1819 local_files_only=local_files_only,
1820 _commit_hash=commit_hash,
1821 _is_local=is_local,
1822 **kwargs,
1823 )

File H:\py310-venv\lib\site-packages\transformers\tokenization_utils_base.py:1844, in PreTrainedTokenizerBase._from_pretrained(cls, resolved_vocab_files, pretrained_model_name_or_path, init_configuration, use_auth_token, cache_dir, local_files_only, _commit_hash, _is_local, *init_inputs, **kwargs)
1842 has_tokenizer_file = resolved_vocab_files.get("tokenizer_file", None) is not None
1843 if (from_slow or not has_tokenizer_file) and cls.slow_tokenizer_class is not None:
-> 1844 slow_tokenizer = (cls.slow_tokenizer_class)._from_pretrained(
1845 copy.deepcopy(resolved_vocab_files),
1846 pretrained_model_name_or_path,
1847 copy.deepcopy(init_configuration),
1848 *init_inputs,
1849 use_auth_token=use_auth_token,
1850 cache_dir=cache_dir,
1851 local_files_only=local_files_only,
1852 _commit_hash=_commit_hash,
1853 **(copy.deepcopy(kwargs)),
1854 )
1855 else:
1856 slow_tokenizer = None

File H:\py310-venv\lib\site-packages\transformers\tokenization_utils_base.py:2031, in PreTrainedTokenizerBase._from_pretrained(cls, resolved_vocab_files, pretrained_model_name_or_path, init_configuration, use_auth_token, cache_dir, local_files_only, _commit_hash, _is_local, *init_inputs, **kwargs)
2024 raise ValueError(
2025 f"Wrong index found for {token}: should be {tokenizer.convert_tokens_to_ids(token)} but found "
2026 f"{index}."
2027 )
2028 elif not has_tokenizer_file and index != current_index:
2029 # Tokenizer slow: added token cannot already be in the vocabulary so its index needs to be the
2030 # current length of the tokenizer.
-> 2031 raise ValueError(
2032 f"Non-consecutive added token '{token}' found. "
2033 f"Should have index {current_index} but has index {index} in saved vocabulary."
2034 )
2036 is_special = bool(token in special_tokens)
2037 if is_last_special is None or is_last_special == is_special:

ValueError: Non-consecutive added token '' found. Should have index 32000 but has index 0 in saved vocabulary.

professor451451

Oct 27, 2023

I get this same error trying to deploy on hugginface endpoints

PsiPi

Nov 20, 2023

same

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