Text Generation
Transformers
Merge
uncensored
unrestricted
reasoning
tool-use
multimodal
vision
long-context
conversational
instruction-following
zero-shot
few-shot
code-generation
summarization
question-answering
multi-task
dialogue
Instructions to use Abigail45/Shay with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Abigail45/Shay with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Abigail45/Shay") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Abigail45/Shay", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Abigail45/Shay with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Abigail45/Shay" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Abigail45/Shay", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Abigail45/Shay
- SGLang
How to use Abigail45/Shay 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 "Abigail45/Shay" \ --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": "Abigail45/Shay", "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 "Abigail45/Shay" \ --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": "Abigail45/Shay", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Abigail45/Shay with Docker Model Runner:
docker model run hf.co/Abigail45/Shay
Update README.md
Browse files
README.md
CHANGED
|
@@ -74,12 +74,15 @@ inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
|
| 74 |
|
| 75 |
output = model.generate(
|
| 76 |
**inputs,
|
| 77 |
-
max_new_tokens=
|
| 78 |
temperature=1.05,
|
| 79 |
top_p=0.97,
|
| 80 |
top_k=60,
|
| 81 |
-
repetition_penalty=1.12,
|
| 82 |
do_sample=True
|
| 83 |
)
|
| 84 |
|
|
|
|
|
|
|
|
|
|
| 85 |
print(tokenizer.decode(output[0], skip_special_tokens=False))
|
|
|
|
| 74 |
|
| 75 |
output = model.generate(
|
| 76 |
**inputs,
|
| 77 |
+
max_new_tokens=512,
|
| 78 |
temperature=1.05,
|
| 79 |
top_p=0.97,
|
| 80 |
top_k=60,
|
| 81 |
+
repetition_penalty=1.12,
|
| 82 |
do_sample=True
|
| 83 |
)
|
| 84 |
|
| 85 |
+
# decode the output
|
| 86 |
+
reply = tokenizer.decode(output[0], skip_special_tokens=True)
|
| 87 |
+
|
| 88 |
print(tokenizer.decode(output[0], skip_special_tokens=False))
|