Not-For-All-Audiences

nsfw

Instructions to use NeverSleep/Lumimaid-v0.2-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NeverSleep/Lumimaid-v0.2-70B with Transformers:

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

pipe = pipeline("text-generation", model="NeverSleep/Lumimaid-v0.2-70B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NeverSleep/Lumimaid-v0.2-70B")
model = AutoModelForCausalLM.from_pretrained("NeverSleep/Lumimaid-v0.2-70B", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NeverSleep/Lumimaid-v0.2-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NeverSleep/Lumimaid-v0.2-70B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeverSleep/Lumimaid-v0.2-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NeverSleep/Lumimaid-v0.2-70B

SGLang

How to use NeverSleep/Lumimaid-v0.2-70B 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 "NeverSleep/Lumimaid-v0.2-70B" \
    --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": "NeverSleep/Lumimaid-v0.2-70B",
		"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 "NeverSleep/Lumimaid-v0.2-70B" \
        --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": "NeverSleep/Lumimaid-v0.2-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NeverSleep/Lumimaid-v0.2-70B with Docker Model Runner:
```
docker model run hf.co/NeverSleep/Lumimaid-v0.2-70B
```

Undi95 commited on Jul 26, 2024

Commit

146d042

verified ·

1 Parent(s): 1220186

Update README.md

Browse files

Files changed (1) hide show

README.md +45 -9

README.md CHANGED Viewed

@@ -22,15 +22,6 @@ As some people have told us our models are sloppy, Ikari decided to say fuck it
 Our dataset stayed the same since day one, we added data over time, cleaned them, and repeat. After not releasing model for a while because we were never satisfied, we think it's time to come back!
-## Credits:
-- Undi
-- IkariDev
-## Training data used:
-We will point out all dataset we used here, please be patient the time we get them all back kek.
-Temporary credit for the following madlads, who contributed to the datasets we have build over time: Gryphe, Caitlyn, Kalomaze, Gifted Gummy Bee, Sao [...]
 ## Prompt template: Llama-3-Instruct
 ```
@@ -43,6 +34,51 @@ Temporary credit for the following madlads, who contributed to the datasets we h
 {output}<|eot_id|>
 ```
 ## Others
 Undi: If you want to support us, you can [here](https://ko-fi.com/undiai).

 Our dataset stayed the same since day one, we added data over time, cleaned them, and repeat. After not releasing model for a while because we were never satisfied, we think it's time to come back!
 ## Prompt template: Llama-3-Instruct
 ```
 {output}<|eot_id|>
 ```
+## Credits:
+- Undi
+- IkariDev
+## Training data we used to make our dataset:
+- [Epiculous/Gnosis](https://huggingface.co/Epiculous/Gnosis)
+- [ChaoticNeutrals/Luminous_Opus](https://huggingface.co/datasets/ChaoticNeutrals/Luminous_Opus)
+- [ChaoticNeutrals/Synthetic-Dark-RP](https://huggingface.co/datasets/ChaoticNeutrals/Synthetic-Dark-RP)
+- [ChaoticNeutrals/Synthetic-RP](https://huggingface.co/datasets/ChaoticNeutrals/Synthetic-RP)
+- [Gryphe/Sonnet3.5-SlimOrcaDedupCleaned](https://huggingface.co/datasets/Gryphe/Sonnet3.5-SlimOrcaDedupCleaned)
+- [Gryphe/Opus-WritingPrompts](https://huggingface.co/datasets/Gryphe/Opus-WritingPrompts)
+- [meseca/writing-opus-6k](https://huggingface.co/datasets/meseca/writing-opus-6k)
+- [meseca/opus-instruct-9k](https://huggingface.co/datasets/meseca/opus-instruct-9k)
+- [PJMixers/grimulkan_theory-of-mind-ShareGPT](https://huggingface.co/datasets/PJMixers/grimulkan_theory-of-mind-ShareGPT)
+- [NobodyExistsOnTheInternet/ToxicQAFinal](https://huggingface.co/datasets/NobodyExistsOnTheInternet/ToxicQAFinal)
+- [Undi95/toxic-dpo-v0.1-sharegpt](https://huggingface.co/datasets/Undi95/toxic-dpo-v0.1-sharegpt)
+- [cgato/SlimOrcaDedupCleaned](https://huggingface.co/datasets/cgato/SlimOrcaDedupCleaned)
+- [kalomaze/Opus_Instruct_25k](https://huggingface.co/datasets/kalomaze/Opus_Instruct_25k)
+- [Doctor-Shotgun/no-robots-sharegpt](https://huggingface.co/datasets/Doctor-Shotgun/no-robots-sharegpt)
+- [Norquinal/claude_multiround_chat_30k](https://huggingface.co/datasets/Norquinal/claude_multiround_chat_30k)
+- [nothingiisreal/Claude-3-Opus-Instruct-15K](https://huggingface.co/datasets/nothingiisreal/Claude-3-Opus-Instruct-15K)
+- All the Aesirs dataset, cleaned, unslopped
+- All le luminae dataset, cleaned, unslopped
+- Small part of Airoboros reduced
+We sadly didn't find the sources of the following, DM us if you recognize your set !
+- Opus_Instruct-v2-6.5K-Filtered-v2-sharegpt
+- claude_sharegpt_trimmed
+- CapybaraPure_Decontaminated-ShareGPT_reduced
+## Datasets credits:
+- Epiculous
+- ChaoticNeutrals
+- Gryphe
+- meseca
+- PJMixers
+- NobodyExistsOnTheInternet
+- cgato
+- kalomaze
+- Doctor-Shotgun
+- Norquinal
+- nothingiisreal
 ## Others
 Undi: If you want to support us, you can [here](https://ko-fi.com/undiai).