Instructions to use JuliaKreutzerCohere/tiny-aya-global-prompt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JuliaKreutzerCohere/tiny-aya-global-prompt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="JuliaKreutzerCohere/tiny-aya-global-prompt") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("JuliaKreutzerCohere/tiny-aya-global-prompt") model = AutoModelForCausalLM.from_pretrained("JuliaKreutzerCohere/tiny-aya-global-prompt", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use JuliaKreutzerCohere/tiny-aya-global-prompt with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "JuliaKreutzerCohere/tiny-aya-global-prompt" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JuliaKreutzerCohere/tiny-aya-global-prompt", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/JuliaKreutzerCohere/tiny-aya-global-prompt
- SGLang
How to use JuliaKreutzerCohere/tiny-aya-global-prompt 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 "JuliaKreutzerCohere/tiny-aya-global-prompt" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JuliaKreutzerCohere/tiny-aya-global-prompt", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "JuliaKreutzerCohere/tiny-aya-global-prompt" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "JuliaKreutzerCohere/tiny-aya-global-prompt", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use JuliaKreutzerCohere/tiny-aya-global-prompt with Docker Model Runner:
docker model run hf.co/JuliaKreutzerCohere/tiny-aya-global-prompt
Upload script.py with huggingface_hub
Browse files
script.py
CHANGED
|
@@ -1,4 +1,30 @@
|
|
| 1 |
import os
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
import re
|
| 3 |
import csv
|
| 4 |
import json
|
|
|
|
| 1 |
import os
|
| 2 |
+
import subprocess
|
| 3 |
+
import sys
|
| 4 |
+
|
| 5 |
+
|
| 6 |
+
def _install_bundled_deps() -> None:
|
| 7 |
+
"""Install transformers from bundled wheels (eval sandbox has no PyPI access)."""
|
| 8 |
+
wheels_dir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "wheels")
|
| 9 |
+
if not os.path.isdir(wheels_dir):
|
| 10 |
+
return
|
| 11 |
+
subprocess.run(
|
| 12 |
+
[
|
| 13 |
+
sys.executable,
|
| 14 |
+
"-m",
|
| 15 |
+
"pip",
|
| 16 |
+
"install",
|
| 17 |
+
"-q",
|
| 18 |
+
"--no-index",
|
| 19 |
+
f"--find-links={wheels_dir}",
|
| 20 |
+
"transformers==4.56.2",
|
| 21 |
+
],
|
| 22 |
+
check=True,
|
| 23 |
+
)
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
_install_bundled_deps()
|
| 27 |
+
|
| 28 |
import re
|
| 29 |
import csv
|
| 30 |
import json
|