Instructions to use appvoid/cortex with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use appvoid/cortex with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="appvoid/cortex", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("appvoid/cortex", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use appvoid/cortex with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "appvoid/cortex" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "appvoid/cortex", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/appvoid/cortex
- SGLang
How to use appvoid/cortex 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 "appvoid/cortex" \ --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": "appvoid/cortex", "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 "appvoid/cortex" \ --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": "appvoid/cortex", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use appvoid/cortex with Docker Model Runner:
docker model run hf.co/appvoid/cortex
Update bet_model.py
Browse files- bet_model.py +1 -1
bet_model.py
CHANGED
|
@@ -451,7 +451,7 @@ def verify_architecture(model, rank=0):
|
|
| 451 |
vocab_size=259, hidden_size=324, intermediate_size=864,
|
| 452 |
prelude_layers=1, body_blocks=6, coda_layers=1,
|
| 453 |
num_heads=6, num_kv_heads=2, head_dim=54,
|
| 454 |
-
lora_rank=16, hyper_lanes=2, max_seq_len=1024, max_loops=
|
| 455 |
rope_theta=10_000.0, rms_eps=1e-6,
|
| 456 |
ddl_beta_init=1.0, ddl_k_eps=1e-2, ddl_v_sigmoid_scale=4.0,
|
| 457 |
)
|
|
|
|
| 451 |
vocab_size=259, hidden_size=324, intermediate_size=864,
|
| 452 |
prelude_layers=1, body_blocks=6, coda_layers=1,
|
| 453 |
num_heads=6, num_kv_heads=2, head_dim=54,
|
| 454 |
+
lora_rank=16, hyper_lanes=2, max_seq_len=1024, max_loops=10,
|
| 455 |
rope_theta=10_000.0, rms_eps=1e-6,
|
| 456 |
ddl_beta_init=1.0, ddl_k_eps=1e-2, ddl_v_sigmoid_scale=4.0,
|
| 457 |
)
|