Instructions to use LostCow/cowshed-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LostCow/cowshed-mini with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="LostCow/cowshed-mini")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("LostCow/cowshed-mini") model = AutoModelForCausalLM.from_pretrained("LostCow/cowshed-mini") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use LostCow/cowshed-mini with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "LostCow/cowshed-mini" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "LostCow/cowshed-mini", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/LostCow/cowshed-mini
- SGLang
How to use LostCow/cowshed-mini 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 "LostCow/cowshed-mini" \ --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": "LostCow/cowshed-mini", "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 "LostCow/cowshed-mini" \ --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": "LostCow/cowshed-mini", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use LostCow/cowshed-mini with Docker Model Runner:
docker model run hf.co/LostCow/cowshed-mini
padding_side="left"
Browse files- tokenizer_config.json +1 -0
tokenizer_config.json
CHANGED
|
@@ -532,6 +532,7 @@
|
|
| 532 |
"errors": "replace",
|
| 533 |
"model_max_length": 4096,
|
| 534 |
"pad_token": "<|pad|>",
|
|
|
|
| 535 |
"tokenizer_class": "GPT2Tokenizer",
|
| 536 |
"unk_token": "<|unk|>"
|
| 537 |
}
|
|
|
|
| 532 |
"errors": "replace",
|
| 533 |
"model_max_length": 4096,
|
| 534 |
"pad_token": "<|pad|>",
|
| 535 |
+
"padding_side": "left",
|
| 536 |
"tokenizer_class": "GPT2Tokenizer",
|
| 537 |
"unk_token": "<|unk|>"
|
| 538 |
}
|