Instructions to use trl-internal-testing/tiny-OPTForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trl-internal-testing/tiny-OPTForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="trl-internal-testing/tiny-OPTForCausalLM")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("trl-internal-testing/tiny-OPTForCausalLM")
model = AutoModelForCausalLM.from_pretrained("trl-internal-testing/tiny-OPTForCausalLM", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use trl-internal-testing/tiny-OPTForCausalLM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/trl-internal-testing/tiny-OPTForCausalLM

SGLang

How to use trl-internal-testing/tiny-OPTForCausalLM 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 "trl-internal-testing/tiny-OPTForCausalLM" \
    --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": "trl-internal-testing/tiny-OPTForCausalLM",
		"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 "trl-internal-testing/tiny-OPTForCausalLM" \
        --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": "trl-internal-testing/tiny-OPTForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use trl-internal-testing/tiny-OPTForCausalLM with Docker Model Runner:
```
docker model run hf.co/trl-internal-testing/tiny-OPTForCausalLM
```

Upload OPTForCausalLM

by albertvillanova HF Staff - opened 4 days ago

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

-1

Files changed (2) hide show

config.json +2 -0
model.safetensors +1 -1

config.json CHANGED Viewed

@@ -1,5 +1,6 @@
 {
   "_remove_final_layer_norm": false,
   "activation_function": "relu",
   "architectures": [
     "OPTForCausalLM"
@@ -21,6 +22,7 @@
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
   "pad_token_id": 1,
   "transformers_version": "4.56.2",
   "use_cache": true,
   "vocab_size": 50272,

 {
   "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
   "activation_function": "relu",
   "architectures": [
     "OPTForCausalLM"
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
   "pad_token_id": 1,
+  "prefix": "</s>",
   "transformers_version": "4.56.2",
   "use_cache": true,
   "vocab_size": 50272,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1feacb109f53317ea274284e332372b7fcef91f85f092c67af1dbfcaaa91808
 size 844480

 version https://git-lfs.github.com/spec/v1
+oid sha256:a34fb0c80127d7b78877beeafbe98cd4555a821bf48352c0da0456337aa8b1ad
 size 844480