Instructions to use Klevin/PRIME2-openai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Klevin/PRIME2-openai with Transformers:

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

pipe = pipeline("text-generation", model="Klevin/PRIME2-openai")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Klevin/PRIME2-openai")
model = AutoModelForCausalLM.from_pretrained("Klevin/PRIME2-openai")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Klevin/PRIME2-openai with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Klevin/PRIME2-openai"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Klevin/PRIME2-openai",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Klevin/PRIME2-openai

SGLang

How to use Klevin/PRIME2-openai 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 "Klevin/PRIME2-openai" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Klevin/PRIME2-openai",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Klevin/PRIME2-openai" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Klevin/PRIME2-openai",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Klevin/PRIME2-openai with Docker Model Runner:
```
docker model run hf.co/Klevin/PRIME2-openai
```

PRIME2-openai / config.json

Klevin

Upload GPTNeoForCausalLM

a127f7b verified almost 2 years ago

raw

history blame contribute delete

1.58 kB

	{
	"_name_or_path": "EleutherAI/gpt-neo-2.7B",
	"activation_function": "gelu_new",
	"architectures": [
	"GPTNeoForCausalLM"
	],
	"attention_dropout": 0,
	"attention_layers": [
	"global",
	"local",
	"global",
	"local",
	"global",
	"local",
	"global",
	"local",
	"global",
	"local",
	"global",
	"local",
	"global",
	"local",
	"global",
	"local",
	"global",
	"local",
	"global",
	"local",
	"global",
	"local",
	"global",
	"local",
	"global",
	"local",
	"global",
	"local",
	"global",
	"local",
	"global",
	"local"
	],
	"attention_types": [
	[
	[
	"global",
	"local"
	],
	16
	]
	],
	"bos_token_id": 50257,
	"classifier_dropout": 0.1,
	"embed_dropout": 0,
	"eos_token_id": 50258,
	"gradient_checkpointing": false,
	"hidden_size": 2560,
	"initializer_range": 0.02,
	"intermediate_size": null,
	"layer_norm_epsilon": 1e-05,
	"max_position_embeddings": 2048,
	"model_type": "gpt_neo",
	"num_heads": 20,
	"num_layers": 32,
	"pad_token_id": 50258,
	"resid_dropout": 0,
	"summary_activation": null,
	"summary_first_dropout": 0.1,
	"summary_proj_to_labels": true,
	"summary_type": "cls_index",
	"summary_use_proj": true,
	"task_specific_params": {
	"text-generation": {
	"do_sample": true,
	"max_length": 50,
	"temperature": 0.9
	}
	},
	"tokenizer_class": "GPT2Tokenizer",
	"torch_dtype": "float16",
	"transformers_version": "4.41.2",
	"use_cache": true,
	"vocab_size": 50259,
	"window_size": 256
	}