Instructions to use Altworld/Hemmingway-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Altworld/Hemmingway-1 with Transformers:

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

pipe = pipeline("text-generation", model="Altworld/Hemmingway-1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Altworld/Hemmingway-1")
model = AutoModelForCausalLM.from_pretrained("Altworld/Hemmingway-1", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Altworld/Hemmingway-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Altworld/Hemmingway-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Altworld/Hemmingway-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Altworld/Hemmingway-1

SGLang

How to use Altworld/Hemmingway-1 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 "Altworld/Hemmingway-1" \
    --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": "Altworld/Hemmingway-1",
		"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 "Altworld/Hemmingway-1" \
        --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": "Altworld/Hemmingway-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Altworld/Hemmingway-1 with Docker Model Runner:
```
docker model run hf.co/Altworld/Hemmingway-1
```

How to turn a top-tier model into an intellectual invalid

by Qozimo - opened 11 days ago

Discussion

Qozimo

11 days ago

I’ve spent some time hands-on with this "masterpiece" of engineering, and here is my verdict: if your IQ is somewhere around 40, this model is built perfectly for you.However, if you actually care about quality and are capable of reading anything more complex than children's literature, this is an absolute pile of garbage. Even a standard 4B model feels like a hyper-intelligence compared to this half-baked creation.Huge thanks to the authors for reinforcing my belief that 99% of people in the AI industry are talentless grifters hiding behind holy benchmark charts.