Instructions to use dvruette/gidd-unif-10b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dvruette/gidd-unif-10b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dvruette/gidd-unif-10b", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("dvruette/gidd-unif-10b", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use dvruette/gidd-unif-10b with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dvruette/gidd-unif-10b" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dvruette/gidd-unif-10b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/dvruette/gidd-unif-10b
- SGLang
How to use dvruette/gidd-unif-10b 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 "dvruette/gidd-unif-10b" \ --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": "dvruette/gidd-unif-10b", "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 "dvruette/gidd-unif-10b" \ --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": "dvruette/gidd-unif-10b", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use dvruette/gidd-unif-10b with Docker Model Runner:
docker model run hf.co/dvruette/gidd-unif-10b
Corrected model's name sample code
#1
by MaximoEduardoRulli - opened
README.md
CHANGED
|
@@ -41,7 +41,7 @@ import torch
|
|
| 41 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 42 |
|
| 43 |
device = "cuda" if torch.cuda.is_available() else "cpu"
|
| 44 |
-
model_name = "dvruette/gidd-
|
| 45 |
|
| 46 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 47 |
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.bfloat16)
|
|
|
|
| 41 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 42 |
|
| 43 |
device = "cuda" if torch.cuda.is_available() else "cpu"
|
| 44 |
+
model_name = "dvruette/gidd-unif-10b"
|
| 45 |
|
| 46 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 47 |
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, torch_dtype=torch.bfloat16)
|