Instructions to use nelson-pawait/checkpoints_3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nelson-pawait/checkpoints_3 with Transformers:

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

pipe = pipeline("text-generation", model="nelson-pawait/checkpoints_3")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("nelson-pawait/checkpoints_3")
model = AutoModelForCausalLM.from_pretrained("nelson-pawait/checkpoints_3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nelson-pawait/checkpoints_3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nelson-pawait/checkpoints_3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nelson-pawait/checkpoints_3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nelson-pawait/checkpoints_3

SGLang

How to use nelson-pawait/checkpoints_3 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 "nelson-pawait/checkpoints_3" \
    --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": "nelson-pawait/checkpoints_3",
		"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 "nelson-pawait/checkpoints_3" \
        --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": "nelson-pawait/checkpoints_3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nelson-pawait/checkpoints_3 with Docker Model Runner:
```
docker model run hf.co/nelson-pawait/checkpoints_3
```

nelson-pawait commited on May 4, 2024

Commit

e54dac4

verified ·

1 Parent(s): 538c6f6

Training in progress, step 3000

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/May04_08-53-30_ccai-deeplearning-vm/events.out.tfevents.1714812865.ccai-deeplearning-vm.1535325.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71452950f562ab98aa8235ff94b9fc0f504c3bfc06bc3f2d7b5d96425b757b57
 size 1826635576

 version https://git-lfs.github.com/spec/v1
+oid sha256:901a665d4ff83e86ad57d9d878b15b3a240dbefebe43c59950d276b6e3bc74e7
 size 1826635576

runs/May04_08-53-30_ccai-deeplearning-vm/events.out.tfevents.1714812865.ccai-deeplearning-vm.1535325.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c58dfdd675abce47a73d47be946f51c0b35db4413390eb6584cdd887ec4ee24e
-size 8200

 version https://git-lfs.github.com/spec/v1
+oid sha256:adb454da76c34e8de87a52d4d0aff677e1e70c6ff18efc6ae7d8ac33d6cdf77c
+size 8729