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
```

Great model!

by cosmicdread - opened 12 days ago

Discussion

cosmicdread

12 days ago

Thanks for your work! I've mainly been using Hemingway in openwebui with thinking enabled to chat with. From a more RP perspective, I find it to be great at helping me brainstorm character identities, backstories etc. It's also good at rewriting sloppy responses from other models.It's not as strong at keeping details straight narratively, which is why the use-case I'm settling on is having it rewrite other models' output.

I've thrown it markdown and json structures, and it's been able to create output based on those without issue, but I haven't tested it's coding/agentic use further yet.

I'm looking forward to seeing further work with this approach, whatever you're doing is working and this model is different than any other one I've run locally so far. Thanks again!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment