Instructions to use GabSo/santacoder-finetuned-robot4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GabSo/santacoder-finetuned-robot4 with Transformers:

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

pipe = pipeline("text-generation", model="GabSo/santacoder-finetuned-robot4", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GabSo/santacoder-finetuned-robot4", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("GabSo/santacoder-finetuned-robot4", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use GabSo/santacoder-finetuned-robot4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GabSo/santacoder-finetuned-robot4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GabSo/santacoder-finetuned-robot4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/GabSo/santacoder-finetuned-robot4

SGLang

How to use GabSo/santacoder-finetuned-robot4 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 "GabSo/santacoder-finetuned-robot4" \
    --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": "GabSo/santacoder-finetuned-robot4",
		"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 "GabSo/santacoder-finetuned-robot4" \
        --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": "GabSo/santacoder-finetuned-robot4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use GabSo/santacoder-finetuned-robot4 with Docker Model Runner:
```
docker model run hf.co/GabSo/santacoder-finetuned-robot4
```

GabSo commited on Nov 9, 2023

Commit

3cc46f1

1 Parent(s): df93aa2

Training in progress, step 20

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Nov09_18-07-40_007b771cd18b/events.out.tfevents.1699553271.007b771cd18b.5358.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ec45dd4657127fd1ac592d5da6ebb56b2b2c0d102bb440cf072ed2dca49c3d8
 size 4600250264

 version https://git-lfs.github.com/spec/v1
+oid sha256:eba70fcab036edd30a5b97f7ba470d60bcc42e7ddac254fb49ac28010c9910bf
 size 4600250264

runs/Nov09_18-07-40_007b771cd18b/events.out.tfevents.1699553271.007b771cd18b.5358.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cec7d37573d9f5cd4239ba8c5bde9206b61e15dd3371e8357c869daffc78aa7
-size 7967

 version https://git-lfs.github.com/spec/v1
+oid sha256:fb1ad5ba0c115d4b84b30c98e2954fec50d304623ea702105c0daf4a2f7ab0f8
+size 10597