Instructions to use Elcaida/pretrainedtest with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Elcaida/pretrainedtest with Transformers:

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

pipe = pipeline("text-generation", model="Elcaida/pretrainedtest")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Elcaida/pretrainedtest")
model = AutoModelForCausalLM.from_pretrained("Elcaida/pretrainedtest", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Elcaida/pretrainedtest with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Elcaida/pretrainedtest

SGLang

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

Docker Model Runner
How to use Elcaida/pretrainedtest with Docker Model Runner:
```
docker model run hf.co/Elcaida/pretrainedtest
```

Elcaida commited on Feb 26, 2025

Commit

822f95d

verified ·

1 Parent(s): 53cca86

Training in progress, step 2496

Browse files

Files changed (2) hide show

model.safetensors +1 -1
runs/Feb26_14-26-06_ip-10-192-12-95/events.out.tfevents.1740580065.ip-10-192-12-95.1627.0 +2 -2

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7fa189370fe0e5dfca6ee8e0383ced51b872234ae4a2d249886ef74567d2167
 size 4943274328

 version https://git-lfs.github.com/spec/v1
+oid sha256:434d12295bc9e06ae7f06761b10e9e4722cf4a1f8b9ec158e4a1caae96c74730
 size 4943274328

runs/Feb26_14-26-06_ip-10-192-12-95/events.out.tfevents.1740580065.ip-10-192-12-95.1627.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:092c2e2f73c84a39a70d62c84fef892ab1224a24be9452446266414bfebb635a
-size 9586

 version https://git-lfs.github.com/spec/v1
+oid sha256:a0826237ca6f8dd4f610a5ada6f24ba9bbe2e94b0fe8e638913223a68a7fb470
+size 10784