Instructions to use winglian/omega-platy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use winglian/omega-platy with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="winglian/omega-platy", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("winglian/omega-platy", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use winglian/omega-platy with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "winglian/omega-platy" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "winglian/omega-platy", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/winglian/omega-platy
- SGLang
How to use winglian/omega-platy 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 "winglian/omega-platy" \ --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": "winglian/omega-platy", "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 "winglian/omega-platy" \ --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": "winglian/omega-platy", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use winglian/omega-platy with Docker Model Runner:
docker model run hf.co/winglian/omega-platy
Training in progress, step 310
Browse files- adapter_config.json +3 -3
- adapter_model.bin +1 -1
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -14,11 +14,11 @@
|
|
| 14 |
"r": 128,
|
| 15 |
"revision": null,
|
| 16 |
"target_modules": [
|
| 17 |
-
"linear",
|
| 18 |
"out_proj",
|
| 19 |
-
"
|
| 20 |
"Wqkv",
|
| 21 |
-
"
|
|
|
|
| 22 |
],
|
| 23 |
"task_type": "CAUSAL_LM"
|
| 24 |
}
|
|
|
|
| 14 |
"r": 128,
|
| 15 |
"revision": null,
|
| 16 |
"target_modules": [
|
|
|
|
| 17 |
"out_proj",
|
| 18 |
+
"fc2",
|
| 19 |
"Wqkv",
|
| 20 |
+
"linear",
|
| 21 |
+
"fc1"
|
| 22 |
],
|
| 23 |
"task_type": "CAUSAL_LM"
|
| 24 |
}
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 416184853
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85fa468df06e3f3148c370cf8dc7c8fdf2290699a2e34d981f23ea76e9dfdf4e
|
| 3 |
size 416184853
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5755
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d043430afb517c876e4e445c78f62ebf3deac78bba7d192352c8559e7b4f2677
|
| 3 |
size 5755
|