Text Generation
Transformers
Safetensors
English
seqcond
hybrid
reasoning
spectral
trickstr
custom_code
Instructions to use trickstr-ai/nautile-370m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use trickstr-ai/nautile-370m with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="trickstr-ai/nautile-370m", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("trickstr-ai/nautile-370m", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use trickstr-ai/nautile-370m with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "trickstr-ai/nautile-370m" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "trickstr-ai/nautile-370m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/trickstr-ai/nautile-370m
- SGLang
How to use trickstr-ai/nautile-370m 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 "trickstr-ai/nautile-370m" \ --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": "trickstr-ai/nautile-370m", "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 "trickstr-ai/nautile-370m" \ --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": "trickstr-ai/nautile-370m", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use trickstr-ai/nautile-370m with Docker Model Runner:
docker model run hf.co/trickstr-ai/nautile-370m
Upload config.json with huggingface_hub
Browse files- config.json +1 -4
config.json
CHANGED
|
@@ -6,10 +6,7 @@
|
|
| 6 |
"auto_map": {
|
| 7 |
"AutoConfig": "configuration_seqcond.SeqCondConfig",
|
| 8 |
"AutoModelForCausalLM": "modeling_seqcond.SeqCondForCausalLM",
|
| 9 |
-
"AutoTokenizer":
|
| 10 |
-
"tokenization_seqcond.SeqCondTokenizer",
|
| 11 |
-
null
|
| 12 |
-
]
|
| 13 |
},
|
| 14 |
"transformers_version": "5.3.0",
|
| 15 |
"d_model": 1024,
|
|
|
|
| 6 |
"auto_map": {
|
| 7 |
"AutoConfig": "configuration_seqcond.SeqCondConfig",
|
| 8 |
"AutoModelForCausalLM": "modeling_seqcond.SeqCondForCausalLM",
|
| 9 |
+
"AutoTokenizer": "tokenization_seqcond.SeqCondTokenizer"
|
|
|
|
|
|
|
|
|
|
| 10 |
},
|
| 11 |
"transformers_version": "5.3.0",
|
| 12 |
"d_model": 1024,
|