Instructions to use roemmele/creative-help with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use roemmele/creative-help with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="roemmele/creative-help")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("roemmele/creative-help", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use roemmele/creative-help with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "roemmele/creative-help" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "roemmele/creative-help", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/roemmele/creative-help
- SGLang
How to use roemmele/creative-help 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 "roemmele/creative-help" \ --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": "roemmele/creative-help", "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 "roemmele/creative-help" \ --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": "roemmele/creative-help", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use roemmele/creative-help with Docker Model Runner:
docker model run hf.co/roemmele/creative-help
Fix GenerationMixin inheritance for transformers >= 4.50 (#3)
Browse files- Fix GenerationMixin inheritance for transformers >= 4.50 (6b1b70b14f47b7cefcbdec037b19316b907d46a6)
rnnlm_model/modeling_rnnlm.py
CHANGED
|
@@ -101,7 +101,7 @@ class GRUKerasCompat(nn.Module):
|
|
| 101 |
return output, h.unsqueeze(0)
|
| 102 |
|
| 103 |
|
| 104 |
-
class RNNLMForCausalLM(PreTrainedModel):
|
| 105 |
"""
|
| 106 |
RNN-based Causal Language Model for text generation.
|
| 107 |
Compatible with HuggingFace TextGenerationPipeline.
|
|
|
|
| 101 |
return output, h.unsqueeze(0)
|
| 102 |
|
| 103 |
|
| 104 |
+
class RNNLMForCausalLM(PreTrainedModel, GenerationMixin):
|
| 105 |
"""
|
| 106 |
RNN-based Causal Language Model for text generation.
|
| 107 |
Compatible with HuggingFace TextGenerationPipeline.
|