Instructions to use Saini-Manisha/tinystarcoder-rlhf-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Saini-Manisha/tinystarcoder-rlhf-model with Transformers:

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

pipe = pipeline("text-generation", model="Saini-Manisha/tinystarcoder-rlhf-model")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Saini-Manisha/tinystarcoder-rlhf-model")
model = AutoModelForCausalLM.from_pretrained("Saini-Manisha/tinystarcoder-rlhf-model", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Saini-Manisha/tinystarcoder-rlhf-model with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Saini-Manisha/tinystarcoder-rlhf-model

SGLang

How to use Saini-Manisha/tinystarcoder-rlhf-model 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 "Saini-Manisha/tinystarcoder-rlhf-model" \
    --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": "Saini-Manisha/tinystarcoder-rlhf-model",
		"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 "Saini-Manisha/tinystarcoder-rlhf-model" \
        --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": "Saini-Manisha/tinystarcoder-rlhf-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Saini-Manisha/tinystarcoder-rlhf-model with Docker Model Runner:
```
docker model run hf.co/Saini-Manisha/tinystarcoder-rlhf-model
```

tinystarcoder-rlhf-model / emissions.csv

Saini-Manisha

RLHF model of StarCoder

5a94e4e verified over 2 years ago

Raw

History Blame Contribute Delete

1.26 kB

	timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
	2024-02-05T14:15:02,codecarbon,3c3a7e90-f65c-4746-97e9-aeb99599778b,5.3008997440338135,8.260499544757351e-07,1.5583202746014168e-07,140.0,48.984,47.14897298812867,0.0002061253322495,7.203342609882355e-05,6.932713929557594e-05,0.0003474858976439,Canada,CAN,quebec,,,Linux-5.4.0-166-generic-x86_64-with-glibc2.31,3.11.4,2.2.3,48,AMD Ryzen Threadripper 3960X 24-Core Processor,2,2 x NVIDIA GeForce RTX 3090,-71.2,46.8,125.73059463500977,machine,N,1.0
	2024-02-05T16:20:19,codecarbon,b337ca15-eccd-4931-9747-8166d80924f4,5.204237222671509,8.131744881465295e-07,1.5625238692119032e-07,140.0,49.61900000000001,47.14897298812867,0.00020236685540941026,7.163956382115683e-05,6.80632890524862e-05,0.00034206970828305327,Canada,CAN,quebec,,,Linux-5.4.0-166-generic-x86_64-with-glibc2.31,3.11.4,2.2.3,48,AMD Ryzen Threadripper 3960X 24-Core Processor,2,2 x NVIDIA GeForce RTX 3090,-71.2,46.8,125.73059463500977,machine,N,1.0