Instructions to use OEvortex/HelpingAI-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OEvortex/HelpingAI-3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="OEvortex/HelpingAI-3B", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("OEvortex/HelpingAI-3B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use OEvortex/HelpingAI-3B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OEvortex/HelpingAI-3B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OEvortex/HelpingAI-3B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/OEvortex/HelpingAI-3B
- SGLang
How to use OEvortex/HelpingAI-3B 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 "OEvortex/HelpingAI-3B" \ --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": "OEvortex/HelpingAI-3B", "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 "OEvortex/HelpingAI-3B" \ --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": "OEvortex/HelpingAI-3B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use OEvortex/HelpingAI-3B with Docker Model Runner:
docker model run hf.co/OEvortex/HelpingAI-3B
Update configuration_HelpingAI.py
Browse files
configuration_HelpingAI.py
CHANGED
|
@@ -34,6 +34,7 @@ class HelpingAIConfig(PretrainedConfig):
|
|
| 34 |
use_cache=True,
|
| 35 |
hidden_activation=None,
|
| 36 |
rope_theta=10000,
|
|
|
|
| 37 |
attention_bias=False,
|
| 38 |
attention_dropout=0.0,
|
| 39 |
num_experts_per_tok=2,
|
|
@@ -63,5 +64,5 @@ class HelpingAIConfig(PretrainedConfig):
|
|
| 63 |
self.num_local_experts = num_local_experts
|
| 64 |
self.router_aux_loss_coef = router_aux_loss_coef
|
| 65 |
self.output_router_logits = output_router_logits
|
| 66 |
-
self.rope_pct = rope_pct
|
| 67 |
super().__init__(**kwargs)
|
|
|
|
| 34 |
use_cache=True,
|
| 35 |
hidden_activation=None,
|
| 36 |
rope_theta=10000,
|
| 37 |
+
rope_pct=0.25
|
| 38 |
attention_bias=False,
|
| 39 |
attention_dropout=0.0,
|
| 40 |
num_experts_per_tok=2,
|
|
|
|
| 64 |
self.num_local_experts = num_local_experts
|
| 65 |
self.router_aux_loss_coef = router_aux_loss_coef
|
| 66 |
self.output_router_logits = output_router_logits
|
| 67 |
+
self.rope_pct = rope_pct
|
| 68 |
super().__init__(**kwargs)
|