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

Libraries

How to use valine/OpenTolkien with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("valine/OpenTolkien")
model = AutoModelForCausalLM.from_pretrained("valine/OpenTolkien")
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 valine/OpenTolkien with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/valine/OpenTolkien

SGLang

How to use valine/OpenTolkien 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 "valine/OpenTolkien" \
    --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": "valine/OpenTolkien",
		"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 "valine/OpenTolkien" \
        --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": "valine/OpenTolkien",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

OpenTolkien / transformers_inference.py

valine

Update model

81d31de over 2 years ago

raw

history blame contribute delete

1.42 kB

	# Code to inference Open Hermes 2.5 with HF Transformers
	# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages

	import torch
	from transformers import AutoTokenizer, AutoModelForCausalLM
	from transformers import LlamaTokenizer, LlamaForCausalLM, MistralForCausalLM
	import bitsandbytes, flash_attn

	tokenizer = LlamaTokenizer.from_pretrained('teknium/OpenHermes-2.5-Mistral-7B', trust_remote_code=True)
	model = MistralForCausalLM.from_pretrained(
	"teknium/OpenHermes-2.5-Mistral-7B",
	torch_dtype=torch.float16,
	device_map="auto",#{'': 'cuda:0'},
	load_in_8bit=False,
	load_in_4bit=True,
	use_flash_attention_2=True
	)

	prompts = [
	"""<\|im_start\|>system
	You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<\|im_end\|>
	<\|im_start\|>user
	Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<\|im_end\|>
	<\|im_start\|>assistant""",
	]

	for chat in prompts:
	print(chat)
	input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
	generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
	response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
	print(f"Response: {response}")