Instructions to use crumb/GLORT2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use crumb/GLORT2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="crumb/GLORT2", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("crumb/GLORT2", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use crumb/GLORT2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "crumb/GLORT2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "crumb/GLORT2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/crumb/GLORT2
- SGLang
How to use crumb/GLORT2 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 "crumb/GLORT2" \ --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": "crumb/GLORT2", "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 "crumb/GLORT2" \ --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": "crumb/GLORT2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use crumb/GLORT2 with Docker Model Runner:
docker model run hf.co/crumb/GLORT2
;)
Browse files- modeling_t2.py +2 -0
modeling_t2.py
CHANGED
|
@@ -149,6 +149,8 @@ class TransformerAttention(nn.Module):
|
|
| 149 |
super().__init__()
|
| 150 |
self.config = config
|
| 151 |
self.stage = stage
|
|
|
|
|
|
|
| 152 |
self.head_dim = config.hidden_size // config.num_attention_heads
|
| 153 |
assert (
|
| 154 |
self.head_dim * config.num_attention_heads == config.hidden_size
|
|
|
|
| 149 |
super().__init__()
|
| 150 |
self.config = config
|
| 151 |
self.stage = stage
|
| 152 |
+
self.max_position_embeddings = config.max_position_embeddings
|
| 153 |
+
self.rope_theta = config.rope_theta
|
| 154 |
self.head_dim = config.hidden_size // config.num_attention_heads
|
| 155 |
assert (
|
| 156 |
self.head_dim * config.num_attention_heads == config.hidden_size
|