Not-For-All-Audiences

conversational

text-generation-inference

3-bit

exl2

Model card Files Files and versions

xet

Community

Instructions to use kim512/L3-70B-daybreak-storywriter-v0.4-3.0bpw-h6-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

Transformers

How to use kim512/L3-70B-daybreak-storywriter-v0.4-3.0bpw-h6-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="kim512/L3-70B-daybreak-storywriter-v0.4-3.0bpw-h6-exl2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kim512/L3-70B-daybreak-storywriter-v0.4-3.0bpw-h6-exl2")
model = AutoModelForCausalLM.from_pretrained("kim512/L3-70B-daybreak-storywriter-v0.4-3.0bpw-h6-exl2")
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 Settings

vLLM

How to use kim512/L3-70B-daybreak-storywriter-v0.4-3.0bpw-h6-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kim512/L3-70B-daybreak-storywriter-v0.4-3.0bpw-h6-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kim512/L3-70B-daybreak-storywriter-v0.4-3.0bpw-h6-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kim512/L3-70B-daybreak-storywriter-v0.4-3.0bpw-h6-exl2

SGLang

How to use kim512/L3-70B-daybreak-storywriter-v0.4-3.0bpw-h6-exl2 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 "kim512/L3-70B-daybreak-storywriter-v0.4-3.0bpw-h6-exl2" \
    --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": "kim512/L3-70B-daybreak-storywriter-v0.4-3.0bpw-h6-exl2",
		"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 "kim512/L3-70B-daybreak-storywriter-v0.4-3.0bpw-h6-exl2" \
        --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": "kim512/L3-70B-daybreak-storywriter-v0.4-3.0bpw-h6-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kim512/L3-70B-daybreak-storywriter-v0.4-3.0bpw-h6-exl2 with Docker Model Runner:
```
docker model run hf.co/kim512/L3-70B-daybreak-storywriter-v0.4-3.0bpw-h6-exl2
```

L3-70B-daybreak-storywriter-v0.4-3.0bpw-h6-exl2 / README.md

kim512

Upload folder using huggingface_hub

0177b23 verified about 2 years ago

2.04 kB

tags:
  - not-for-all-audiences

EXL2 quants of crestf411/L3-70B-daybreak-storywriter-v0.4

3.00 bits per weight
3.50 bits per weight
4.00 bits per weight
4.50 bits per weight
5.00 bits per weight
6.00 bits per weight
8.00 bits per weight

Created using the defaults from exllamav2 0.0.21 convert.py
3.0bpw to 6.0bpw head bits = 6
8.0bpw head bits = 8
length = 8192
dataset rows = 200
measurement rows = 32
measurement length = 8192

L3-70B-daybreak-storywriter-v0.4

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.