Instructions to use Gnonymous/EVOKE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Gnonymous/EVOKE with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Gnonymous/EVOKE")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Gnonymous/EVOKE", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Gnonymous/EVOKE with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Gnonymous/EVOKE" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Gnonymous/EVOKE", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Gnonymous/EVOKE
- SGLang
How to use Gnonymous/EVOKE 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 "Gnonymous/EVOKE" \ --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": "Gnonymous/EVOKE", "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 "Gnonymous/EVOKE" \ --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": "Gnonymous/EVOKE", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Gnonymous/EVOKE with Docker Model Runner:
docker model run hf.co/Gnonymous/EVOKE
Add `pipeline_tag` and `library_name` metadata
Browse filesThis PR adds the missing `pipeline_tag: text-generation` and `library_name: transformers` to the model card's YAML metadata. The `pipeline_tag` ensures the model appears under the correct category on the Hub, and the `library_name` enables the automatic "Use in Transformers" code snippet. The model is a causal language model that loads directly with `transformers`, as shown in the official GitHub README.
README.md
CHANGED
|
@@ -1,7 +1,9 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
language:
|
| 4 |
- en
|
|
|
|
|
|
|
|
|
|
| 5 |
tags:
|
| 6 |
- agents
|
| 7 |
- llm-agents
|
|
@@ -36,4 +38,4 @@ Both repositories contain full models, each with its own license. Evaluation cod
|
|
| 36 |
journal={arXiv preprint arXiv:2609.38334},
|
| 37 |
year={2026}
|
| 38 |
}
|
| 39 |
-
```
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
library_name: transformers
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
tags:
|
| 8 |
- agents
|
| 9 |
- llm-agents
|
|
|
|
| 38 |
journal={arXiv preprint arXiv:2609.38334},
|
| 39 |
year={2026}
|
| 40 |
}
|
| 41 |
+
```
|