Instructions to use Corianas/llama-tiny-reactor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Corianas/llama-tiny-reactor with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Corianas/llama-tiny-reactor")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Corianas/llama-tiny-reactor")
model = AutoModelForCausalLM.from_pretrained("Corianas/llama-tiny-reactor")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Corianas/llama-tiny-reactor with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Corianas/llama-tiny-reactor"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Corianas/llama-tiny-reactor",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Corianas/llama-tiny-reactor

SGLang

How to use Corianas/llama-tiny-reactor 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 "Corianas/llama-tiny-reactor" \
    --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": "Corianas/llama-tiny-reactor",
		"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 "Corianas/llama-tiny-reactor" \
        --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": "Corianas/llama-tiny-reactor",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Corianas/llama-tiny-reactor with Docker Model Runner:
```
docker model run hf.co/Corianas/llama-tiny-reactor
```

Pad Token not uniquely defined?

by MartialTerran - opened Nov 23, 2024

Discussion

MartialTerran

Nov 23, 2024

Hi. Why is your "pad_token": "", the same as the "eos_token": {
"content": "",

Why the "pad_token": definition does not include a "content" key? Do these anomalies cancel each other out?

What did you actually use the "pad_token" for in developing your model?

{
"bos_token": {
"content": "",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "",
"unk_token": {
"content": "",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment