Text Generation
Transformers
English
encoder_decoder
code
natural language understanding
machine learning
research
introspection
self-reflection
conversational
Instructions to use Or4cl3-1/CSUMLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Or4cl3-1/CSUMLM with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Or4cl3-1/CSUMLM") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Or4cl3-1/CSUMLM", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Or4cl3-1/CSUMLM with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Or4cl3-1/CSUMLM" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Or4cl3-1/CSUMLM", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Or4cl3-1/CSUMLM
- SGLang
How to use Or4cl3-1/CSUMLM 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 "Or4cl3-1/CSUMLM" \ --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": "Or4cl3-1/CSUMLM", "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 "Or4cl3-1/CSUMLM" \ --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": "Or4cl3-1/CSUMLM", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Or4cl3-1/CSUMLM with Docker Model Runner:
docker model run hf.co/Or4cl3-1/CSUMLM
Update tokenizer_config.json
Browse files- tokenizer_config.json +5 -2
tokenizer_config.json
CHANGED
|
@@ -14,5 +14,8 @@
|
|
| 14 |
"mask_token": "<MASK>"
|
| 15 |
},
|
| 16 |
"tokenization_method": "Byte Pair Encoding (BPE)",
|
| 17 |
-
"training_data": "Custom 1500 Example Dataset"
|
| 18 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
"mask_token": "<MASK>"
|
| 15 |
},
|
| 16 |
"tokenization_method": "Byte Pair Encoding (BPE)",
|
| 17 |
+
"training_data": "Custom 1500 Example Dataset",
|
| 18 |
+
"chat_template": "[BOS] {context} {user_input} {response} [EOS]",
|
| 19 |
+
"pad_to_max_length": true,
|
| 20 |
+
"truncation_strategy": "only_second"
|
| 21 |
+
}
|