Instructions to use Minata/reduced_ast_method2test-codegen-350M_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Minata/reduced_ast_method2test-codegen-350M_v1 with Transformers:

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

pipe = pipeline("text-generation", model="Minata/reduced_ast_method2test-codegen-350M_v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Minata/reduced_ast_method2test-codegen-350M_v1")
model = AutoModelForCausalLM.from_pretrained("Minata/reduced_ast_method2test-codegen-350M_v1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Minata/reduced_ast_method2test-codegen-350M_v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Minata/reduced_ast_method2test-codegen-350M_v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Minata/reduced_ast_method2test-codegen-350M_v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Minata/reduced_ast_method2test-codegen-350M_v1

SGLang

How to use Minata/reduced_ast_method2test-codegen-350M_v1 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 "Minata/reduced_ast_method2test-codegen-350M_v1" \
    --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": "Minata/reduced_ast_method2test-codegen-350M_v1",
		"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 "Minata/reduced_ast_method2test-codegen-350M_v1" \
        --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": "Minata/reduced_ast_method2test-codegen-350M_v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Minata/reduced_ast_method2test-codegen-350M_v1 with Docker Model Runner:
```
docker model run hf.co/Minata/reduced_ast_method2test-codegen-350M_v1
```

Minata commited on Jan 6, 2024

Commit

0d3c98e

1 Parent(s): 6d0d784

Training in progress, epoch 2

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Jan06_21-01-00_0c1a461767f5/events.out.tfevents.1704574872.0c1a461767f5.1916.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:260aa9e7ecff2df2d9f10c9accac439b15d651d99c540a849a2e6cc9f20392a4
 size 1426867192

 version https://git-lfs.github.com/spec/v1
+oid sha256:4369768f93eefe2396dcd9ad5ebc3729c649895c156ef6c61d3727d8b2e7e43a
 size 1426867192

runs/Jan06_21-01-00_0c1a461767f5/events.out.tfevents.1704574872.0c1a461767f5.1916.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:066fcccfa01bd4596a06d460b0f3444e78117ab91bbde545556deac117aa06be
-size 5088

 version https://git-lfs.github.com/spec/v1
+oid sha256:b0e4716b5fcb70981b9eb4c76fa1b12615d9693c730f9d664f1c36c214012988
+size 5870