Not-For-All-Audiences

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

Libraries

How to use crestf411/L3-70B-daybreak-abliterated-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-abliterated-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-abliterated-v0.4")
model = AutoModelForCausalLM.from_pretrained("crestf411/L3-70B-daybreak-abliterated-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-abliterated-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-abliterated-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-abliterated-v0.4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

Docker Model Runner
How to use crestf411/L3-70B-daybreak-abliterated-v0.4 with Docker Model Runner:
```
docker model run hf.co/crestf411/L3-70B-daybreak-abliterated-v0.4
```

crestf411 commited on May 27, 2024

Commit

4da59b6

verified ·

1 Parent(s): a7d2cf4

Create README.md

Browse files

Files changed (1) hide show

README.md +33 -0

README.md ADDED Viewed

	@@ -0,0 +1,33 @@

+---
+tags:
+- not-for-all-audiences
+---
+Daybreak (2024 May 24) v0.4 LoRA on top of https://huggingface.co/failspy/llama-3-70B-Instruct-abliterated
+Beware, depraved. Not suitable for any audience.
+Dataset curation to remove slop-perceived expressions continues. Unfortunately L3-Instruct (which this is merged on top of) is riddled with "barely audible"s and "couldn't help"s and "shivers down spines" etc.
+The below regexes return 0 matches, but as noted above, there are still frequent occurrences of these in the base instruct merge. **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.