Text Generation
Transformers
PyTorch
English
crystalcoder
llm
code
custom_code
Eval Results (legacy)
Instructions to use LLM360/CrystalChat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LLM360/CrystalChat with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LLM360/CrystalChat", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("LLM360/CrystalChat", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use LLM360/CrystalChat with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LLM360/CrystalChat" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LLM360/CrystalChat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/LLM360/CrystalChat
- SGLang
How to use LLM360/CrystalChat 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 "LLM360/CrystalChat" \ --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": "LLM360/CrystalChat", "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 "LLM360/CrystalChat" \ --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": "LLM360/CrystalChat", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use LLM360/CrystalChat with Docker Model Runner:
docker model run hf.co/LLM360/CrystalChat
Getting "'NoneType' object has no attribute 'size'" error when trying to run model
#3
by Bandeze - opened
I'm trying to run the provided example of using the model, but I keep getting this error:
Traceback (most recent call last):
File "/home/bandeze/Ethical_AI_Stuff/./crystal_chat.py", line 12, in <module>
gen_tokens = model.generate(input_ids, do_sample=True, max_length=400)
File "/home/bandeze/Ethical_AI_Stuff/ai_venv/lib/python3.13/site-packages/torch/utils/_contextlib.py", line 124, in decorate_context
return func(*args, **kwargs)
File "/home/bandeze/Ethical_AI_Stuff/ai_venv/lib/python3.13/site-packages/transformers/generation/utils.py", line 2566, in generate
result = decoding_method(
self,
...<5 lines>...
**model_kwargs,
)
File "/home/bandeze/Ethical_AI_Stuff/ai_venv/lib/python3.13/site-packages/transformers/generation/utils.py", line 2786, in _sample
outputs = self(**model_inputs, return_dict=True)
File "/home/bandeze/Ethical_AI_Stuff/ai_venv/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "/home/bandeze/Ethical_AI_Stuff/ai_venv/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
return forward_call(*args, **kwargs)
File "/home/bandeze/.cache/huggingface/modules/transformers_modules/LLM360/CrystalChat/18091ea1d89f8c6c18d3a90eb86c8324bb09a6f6/modeling_crystalcoder.py", line 1271, in forward
transformer_outputs = self.transformer(
input_ids,
...<11 lines>...
return_dict=return_dict,
)
File "/home/bandeze/Ethical_AI_Stuff/ai_venv/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^
File "/home/bandeze/Ethical_AI_Stuff/ai_venv/lib/python3.13/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
return forward_call(*args, **kwargs)
File "/home/bandeze/.cache/huggingface/modules/transformers_modules/LLM360/CrystalChat/18091ea1d89f8c6c18d3a90eb86c8324bb09a6f6/modeling_crystalcoder.py", line 981, in forward
past_length = past_key_values[0][0].size(-2)
^^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'size'
I'm very new to this, so I don't know how to fix this.
I'm using Python 3.13.7, and the only change I made to the script is forcing it to use the CPU, since my NVIDIA card doesn't have enough VRAM (I have a good amount of DRAM, thankfully).
What do I do?