Instructions to use abideen/Heimer-dpo-TinyLlama-1.1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abideen/Heimer-dpo-TinyLlama-1.1B with Transformers:

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

pipe = pipeline("text-generation", model="abideen/Heimer-dpo-TinyLlama-1.1B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("abideen/Heimer-dpo-TinyLlama-1.1B")
model = AutoModelForCausalLM.from_pretrained("abideen/Heimer-dpo-TinyLlama-1.1B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use abideen/Heimer-dpo-TinyLlama-1.1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abideen/Heimer-dpo-TinyLlama-1.1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abideen/Heimer-dpo-TinyLlama-1.1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/abideen/Heimer-dpo-TinyLlama-1.1B

SGLang

How to use abideen/Heimer-dpo-TinyLlama-1.1B 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 "abideen/Heimer-dpo-TinyLlama-1.1B" \
    --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": "abideen/Heimer-dpo-TinyLlama-1.1B",
		"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 "abideen/Heimer-dpo-TinyLlama-1.1B" \
        --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": "abideen/Heimer-dpo-TinyLlama-1.1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use abideen/Heimer-dpo-TinyLlama-1.1B with Docker Model Runner:
```
docker model run hf.co/abideen/Heimer-dpo-TinyLlama-1.1B
```

abideen commited on Jan 14, 2024

Commit

a2e281e

verified ·

1 Parent(s): e616aec

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -70,7 +70,7 @@ max_length=1536
 ## 💻 Usage
-Here's a [Colab notebook](https://colab.research.google.com/drive/1F9lzL1IeZRMgiSbY9UbgCR__RreIflJh?usp=sharing) to run NexoNimbus-7B in 4-bit precision on a free T4 GPU.
 ```python
 !pip install -qU transformers accelerate

 ## 💻 Usage
+Here's a [Colab notebook](https://colab.research.google.com/drive/11KEX1LG3nRBoeGR0Iyy-459XllGlLOA9?usp=sharing) to run Heimer-TinyLLama-1.1B in 4-bit precision on a free T4 GPU.
 ```python
 !pip install -qU transformers accelerate