Instructions to use Aalaa/opt-125m-wikitext2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Aalaa/opt-125m-wikitext2 with Transformers:

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

pipe = pipeline("text-generation", model="Aalaa/opt-125m-wikitext2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Aalaa/opt-125m-wikitext2")
model = AutoModelForCausalLM.from_pretrained("Aalaa/opt-125m-wikitext2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Aalaa/opt-125m-wikitext2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Aalaa/opt-125m-wikitext2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aalaa/opt-125m-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Aalaa/opt-125m-wikitext2

SGLang

How to use Aalaa/opt-125m-wikitext2 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 "Aalaa/opt-125m-wikitext2" \
    --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": "Aalaa/opt-125m-wikitext2",
		"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 "Aalaa/opt-125m-wikitext2" \
        --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": "Aalaa/opt-125m-wikitext2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Aalaa/opt-125m-wikitext2 with Docker Model Runner:
```
docker model run hf.co/Aalaa/opt-125m-wikitext2
```

Add evaluation results on the mathemakitten--winobias_antistereotype_dev config and validation split of mathemakitten/winobias_antistereotype_dev

by autoevaluator HF Staff - opened Jan 12, 2023

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+20

-1

Files changed (1) hide show

README.md +20 -1

README.md CHANGED Viewed

@@ -4,7 +4,26 @@ tags:
 - generated_from_trainer
 model-index:
 - name: opt-125m-wikitext2
-  results: []
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You

 - generated_from_trainer
 model-index:
 - name: opt-125m-wikitext2
+  results:
+  - task:
+      type: zero-shot-classification
+      name: Zero-Shot Text Classification
+    dataset:
+      name: mathemakitten/winobias_antistereotype_dev
+      type: mathemakitten/winobias_antistereotype_dev
+      config: mathemakitten--winobias_antistereotype_dev
+      split: validation
+    metrics:
+    - type: accuracy
+      value: 0.4375
+      name: Accuracy
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTYwMThiZjYwMmNmZDA4ZmUyNzYwNjU3MGU0NTRhZjI5NWVjNGRmOTRhZWRlZWVmYzQ5MWRiNmQ0MzRlMjU0NyIsInZlcnNpb24iOjF9.hqz3Xwego8qtofxVwg0yO0Ovk6G_kXYj55gPPLzmBFYJQOuy9kSa8g2Sm_GRTU0GSU10rAtDzYCSyehqz58VBQ
+    - type: loss
+      value: 1.1480248920549638
+      name: Loss
+      verified: true
+      verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDhkODZmMzgyODQyNzYzZGE4Nzc2YjhkZTk0ZDgwMGUwMjI0ZjliMmQyODM3NzlkODkwOWEwYzBlNWU4NzlmMCIsInZlcnNpb24iOjF9.qlhKo7zXMRYAYWTszoZ7VQqF52mCDBQ7PRLD6y6doFmAnmKa8nv4VQeDBFdYwomMA1Rdw2jwqhYcwbgSYEm0CA
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You