Instructions to use TheBloke/tulu-30B-GPTQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TheBloke/tulu-30B-GPTQ with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="TheBloke/tulu-30B-GPTQ")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("TheBloke/tulu-30B-GPTQ") model = AutoModelForCausalLM.from_pretrained("TheBloke/tulu-30B-GPTQ") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use TheBloke/tulu-30B-GPTQ with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "TheBloke/tulu-30B-GPTQ" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TheBloke/tulu-30B-GPTQ", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/TheBloke/tulu-30B-GPTQ
- SGLang
How to use TheBloke/tulu-30B-GPTQ 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 "TheBloke/tulu-30B-GPTQ" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TheBloke/tulu-30B-GPTQ", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "TheBloke/tulu-30B-GPTQ" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "TheBloke/tulu-30B-GPTQ", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use TheBloke/tulu-30B-GPTQ with Docker Model Runner:
docker model run hf.co/TheBloke/tulu-30B-GPTQ
Error loading in text-generation-webui
Traceback (most recent call last): File “E:\llmRunner\textV2\oobabooga-windows\text-generation-webui\server.py”, line 69, in load_model_wrapper shared.model, shared.tokenizer = load_model(shared.model_name) File “E:\llmRunner\textV2\oobabooga-windows\text-generation-webui\modules\models.py”, line 102, in load_model tokenizer = load_tokenizer(model_name, model) File “E:\llmRunner\textV2\oobabooga-windows\text-generation-webui\modules\models.py”, line 127, in load_tokenizer tokenizer = LlamaTokenizer.from_pretrained(Path(f"{shared.args.model_dir}/{model_name}/“), clean_up_tokenization_spaces=True) File “E:\llmRunner\textV2\oobabooga-windows\installer_files\env\lib\site-packages\transformers\tokenization_utils_base.py”, line 1812, in from_pretrained return cls.from_pretrained( File “E:\llmRunner\textV2\oobabooga-windows\installer_files\env\lib\site-packages\transformers\tokenization_utils_base.py”, line 1975, in from_pretrained tokenizer = cls(*init_inputs, **init_kwargs) File “E:\llmRunner\textV2\oobabooga-windows\installer_files\env\lib\site-packages\transformers\models\llama\tokenization_llama.py”, line 96, in init self.sp_model.Load(vocab_file) File "E:\llmRunner\textV2\oobabooga-windows\installer_files\env\lib\site-packages\sentencepiece_init.py", line 905, in Load return self.LoadFromFile(model_file) File "E:\llmRunner\textV2\oobabooga-windows\installer_files\env\lib\site-packages\sentencepiece_init.py”, line 310, in LoadFromFile return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg) TypeError: not a string
Can anyone help?
Thanks
I get (IndexError: list index out of range)
Try updating your text-generation-webui to the latest version.