Instructions to use OpenOpenAI/ppo_iter_14 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenOpenAI/ppo_iter_14 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="OpenOpenAI/ppo_iter_14")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("OpenOpenAI/ppo_iter_14") model = AutoModelForCausalLM.from_pretrained("OpenOpenAI/ppo_iter_14") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use OpenOpenAI/ppo_iter_14 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "OpenOpenAI/ppo_iter_14" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "OpenOpenAI/ppo_iter_14", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/OpenOpenAI/ppo_iter_14
- SGLang
How to use OpenOpenAI/ppo_iter_14 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 "OpenOpenAI/ppo_iter_14" \ --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": "OpenOpenAI/ppo_iter_14", "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 "OpenOpenAI/ppo_iter_14" \ --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": "OpenOpenAI/ppo_iter_14", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use OpenOpenAI/ppo_iter_14 with Docker Model Runner:
docker model run hf.co/OpenOpenAI/ppo_iter_14
Upload config
Browse files- config.json +2 -2
config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "/workspace/OpenRLHF3/checkpoint/llama-3-8b-rlhf/iter_14",
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": null,
|
|
@@ -23,7 +23,7 @@
|
|
| 23 |
"rope_scaling": null,
|
| 24 |
"rope_theta": 10000.0,
|
| 25 |
"tie_word_embeddings": false,
|
| 26 |
-
"torch_dtype": "
|
| 27 |
"transformers_version": "4.43.1",
|
| 28 |
"use_cache": false,
|
| 29 |
"vocab_size": 51200
|
|
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "/workspace/OpenRLHF3/checkpoint/llama-3-8b-rlhf/iter_14",
|
| 3 |
"architectures": [
|
| 4 |
+
"PhiForCausalLM"
|
| 5 |
],
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": null,
|
|
|
|
| 23 |
"rope_scaling": null,
|
| 24 |
"rope_theta": 10000.0,
|
| 25 |
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "bfloat16",
|
| 27 |
"transformers_version": "4.43.1",
|
| 28 |
"use_cache": false,
|
| 29 |
"vocab_size": 51200
|