Instructions to use BusRune/L3-70B-Nova-Fabula with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BusRune/L3-70B-Nova-Fabula with Transformers:

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

pipe = pipeline("text-generation", model="BusRune/L3-70B-Nova-Fabula")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BusRune/L3-70B-Nova-Fabula")
model = AutoModelForCausalLM.from_pretrained("BusRune/L3-70B-Nova-Fabula")
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 BusRune/L3-70B-Nova-Fabula with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BusRune/L3-70B-Nova-Fabula"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BusRune/L3-70B-Nova-Fabula",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BusRune/L3-70B-Nova-Fabula

SGLang

How to use BusRune/L3-70B-Nova-Fabula 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 "BusRune/L3-70B-Nova-Fabula" \
    --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": "BusRune/L3-70B-Nova-Fabula",
		"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 "BusRune/L3-70B-Nova-Fabula" \
        --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": "BusRune/L3-70B-Nova-Fabula",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BusRune/L3-70B-Nova-Fabula with Docker Model Runner:
```
docker model run hf.co/BusRune/L3-70B-Nova-Fabula
```

L3-70B-Nova-Fabula

L3-70B-Nova-Fabula is a fine-tuned version of Facebook's LLaMA 3 70B model, specifically optimized for roleplay and general knowledge tasks.
This is a test model for the “Fabula” series, as in the last deleted 2 models, “Qwen2.5-72B-Fabula”, and “L3.1-70B-Fabula” they apparently had a lot of problems.
So until I can find out what would be the best in parameters, datasets “Nova-Fabula” series will be my playground for it.

Human review (18/01/2024)

I finally managed to test the model out and so far, for the first test, it appears to be significantly better than the broken ones like “Qwen2.5-72B-Fabula”, and “L3.1-70B-Fabula.”
Though I must say from the experience I gathered while testing the old models, it really changes from where you host the model, like in one provider it might be really low quality that "just works" while in other, it might actually be high quality.
Anyways now to the actual model, starting with it's flaws:

Model being stuck on LLaMA3 template.
- From my testing it seems to be not entirelly following ChatML template, but LLaMA 3 template instead, though I still went with ChatML, just added a stop string as "<|eot_id|>" to ensure it doesn't go forever until it hits the token limit.
Model instruction following.
- On format following, it mostly appears to be fine.
  - (but it seems to require detailed instruction to do better, but even then, it seems to be copy the format used in examples, even when asked not to do so)

A further testing would be better as I didn't really go into detail on testing, but that's all I could see during testing.

Downloads last month: -

Safetensors

Model size

71B params

Tensor type

BF16

Model tree for BusRune/L3-70B-Nova-Fabula

Base model

meta-llama/Meta-Llama-3-70B

Finetuned

meta-llama/Meta-Llama-3-70B-Instruct

Finetuned

(48)

this model

BusRune
/

L3-70B-Nova-Fabula

L3-70B-Nova-Fabula

Human review (18/01/2024)

Model tree for BusRune/L3-70B-Nova-Fabula

Datasets used to train BusRune/L3-70B-Nova-Fabula