Instructions to use Harshad2410/tinystarcoder-rlhf-model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Harshad2410/tinystarcoder-rlhf-model with Transformers:

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

pipe = pipeline("text-generation", model="Harshad2410/tinystarcoder-rlhf-model")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Harshad2410/tinystarcoder-rlhf-model")
model = AutoModelForCausalLM.from_pretrained("Harshad2410/tinystarcoder-rlhf-model")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Harshad2410/tinystarcoder-rlhf-model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Harshad2410/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": "Harshad2410/tinystarcoder-rlhf-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Harshad2410/tinystarcoder-rlhf-model

SGLang

How to use Harshad2410/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 "Harshad2410/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": "Harshad2410/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 "Harshad2410/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": "Harshad2410/tinystarcoder-rlhf-model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Harshad2410/tinystarcoder-rlhf-model with Docker Model Runner:
```
docker model run hf.co/Harshad2410/tinystarcoder-rlhf-model
```

Harshad2410 commited on Oct 16, 2023

Commit

a1d57c3

1 Parent(s): d9b3250

RLHF model of StarCoder 1

Browse files

Files changed (2) hide show

pytorch_model.bin +2 -2
training_args.bin +1 -1

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fca87056dcc775ae31c29d7846237bb28cb916acd50cbccc86a810035e2c15c
-size 656655965

 version https://git-lfs.github.com/spec/v1
+oid sha256:da6b9fc5a8e5138b76aa675714fd9764da6f11499d78cbc0429a6a198b6ead3f
+size 656652573

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cba4fc196a2652e280f90dde6a7c2176ff216c596bb491b4aa3f5c7dc161bd4
 size 4027

 version https://git-lfs.github.com/spec/v1
+oid sha256:5ae06367244e02fbd4ca9538c726f8f368218608a8bd78f90b83d63dc6161a6d
 size 4027