Not-For-All-Audiences

Instructions to use crestf411/L3-70B-daybreak-storywriter-v0.4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use crestf411/L3-70B-daybreak-storywriter-v0.4 with Transformers:

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

pipe = pipeline("text-generation", model="crestf411/L3-70B-daybreak-storywriter-v0.4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("crestf411/L3-70B-daybreak-storywriter-v0.4")
model = AutoModelForCausalLM.from_pretrained("crestf411/L3-70B-daybreak-storywriter-v0.4")
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]:]))

Inference
Local Apps Settings

vLLM

How to use crestf411/L3-70B-daybreak-storywriter-v0.4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "crestf411/L3-70B-daybreak-storywriter-v0.4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "crestf411/L3-70B-daybreak-storywriter-v0.4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/crestf411/L3-70B-daybreak-storywriter-v0.4

SGLang

How to use crestf411/L3-70B-daybreak-storywriter-v0.4 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 "crestf411/L3-70B-daybreak-storywriter-v0.4" \
    --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": "crestf411/L3-70B-daybreak-storywriter-v0.4",
		"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 "crestf411/L3-70B-daybreak-storywriter-v0.4" \
        --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": "crestf411/L3-70B-daybreak-storywriter-v0.4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use crestf411/L3-70B-daybreak-storywriter-v0.4 with Docker Model Runner:
```
docker model run hf.co/crestf411/L3-70B-daybreak-storywriter-v0.4
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Daybreak (2024 May 24) v0.4 LoRA on top of https://huggingface.co/tdrussell/Llama-3-70B-Instruct-Storywriter

Dataset curation to remove slop-perceived expressions continues.

The below regexes return 0 matches. Bold entries are new since v0.3.

'barely above a whisper',
'barely audible',
'shiver([s]?) down',
' ministration',
'audible (["'"]?)p[l]?op',
'can't help but',
'buck([s]?) my ',
'buck([s]?) h[ei][rs] ',
'[Dd]espite h[ie][mr]self',
'slick slit',
'whatever it takes',
'unlike anything (s?)he',
'a mix([a-z]*) of',
'wave after wave',
'reckless abandon',
'[Mm]aybe, just maybe',
'eyes gleaming',
'mischievously',
"couldn't help but",

From testing so far, it feels like temperature 0.8-0.9 is a good starting point. I have mostly tested with everything neutralized. Please give feedback on which parameters work good for you.

EXL2 quants made by kim512 be found in (scroll to bottom for updated quants) https://huggingface.co/crestf411/L3-70B-daybreak-storywriter-v0.4/discussions/2 including the settings used to make them.

Downloads last month: 17

Safetensors

Model size

71B params

Tensor type

BF16

Model tree for crestf411/L3-70B-daybreak-storywriter-v0.4

Quantizations

3 models

Collection including crestf411/L3-70B-daybreak-storywriter-v0.4

Daybreak

Collection

Daybreak • 2 items • Updated Mar 2 • 2