Instructions to use NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 with Transformers:

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

pipe = pipeline("text-generation", model="NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3")
model = AutoModelForCausalLM.from_pretrained("NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3"
# 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/Noromaid-v0.1-mixtral-8x7b-Instruct-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3

SGLang

How to use NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 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/Noromaid-v0.1-mixtral-8x7b-Instruct-v3" \
    --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/Noromaid-v0.1-mixtral-8x7b-Instruct-v3",
		"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/Noromaid-v0.1-mixtral-8x7b-Instruct-v3" \
        --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/Noromaid-v0.1-mixtral-8x7b-Instruct-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3 with Docker Model Runner:
```
docker model run hf.co/NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3
```

IkariDev commited on Dec 25, 2023

Commit

15ec057

1 Parent(s): c818dfc

Create README.md

Browse files

Files changed (1) hide show

README.md +92 -0

README.md ADDED Viewed

	@@ -0,0 +1,92 @@

+---
+license: cc-by-nc-4.0
+---
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/630dfb008df86f1e5becadc3/vwcJfOnL-2QDJ0ShfxRJ5.png)
+---
+# Disclaimer:
+## This model is experimental, do not expect everything to work.
+This model uses the Alpaca **prompting format**(or just directly download the SillyTavern instruct preset [here](https://files.catbox.moe/0ohmco.json))
+---
+Beeg noromaid on ***steroids***. Suitable for RP, ERP.
+This time based on Mixtral Instruct, seems to do wonders!
+This model was trained for 8h(v1) + 8h(v2) + 12h(v3) on customized modified datasets, focusing on RP, uncensoring, and a modified version of the Alpaca prompting (that was already used in LimaRP), which should be at the same conversational level as ChatLM or Llama2-Chat without adding any additional special tokens.
+If you wanna have more infos about this model(and v1 + v2) you can check out [my blog post](https://ikaridevgit.github.io/index.html?p=7&blog=blogid-6&bo=true)
+[Recommended settings - Settings 1](https://huggingface.co/NeverSleep/Noromaid-v0.1-mixtral-8x7b-v3/discussions/1)
+[Recommended settings - Settings 2 (idk if they are any good)](https://files.catbox.moe/fv4xhu.json)
+## Credits:
+- Undi
+- IkariDev
+<!-- description start -->
+## Description
+<!-- [Recommended settings - contributed by localfultonextractor](https://files.catbox.moe/ue0tja.json) -->
+This repo contains FP16 files of Noromaid-v0.1-mixtral-8x7b-Instruct-v3.
+[FP16 - by IkariDev and Undi](https://huggingface.co/NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3)
+<!-- [GGUF - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GGUF)-->
+<!-- [GPTQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-GPTQ)-->
+<!-- [exl2[8bpw-8h] - by AzureBlack](https://huggingface.co/AzureBlack/Echidna-13b-v0.3-8bpw-8h-exl2)-->
+<!-- [AWQ - By TheBloke](https://huggingface.co/TheBloke/Athena-v4-AWQ)-->
+<!-- [fp16 - by IkariDev+Undi95](https://huggingface.co/IkariDev/Athena-v4)-->
+[GGUF - by IkariDev and Undi](https://huggingface.co/NeverSleep/Noromaid-v0.1-mixtral-8x7b-Instruct-v3-GGUF)
+<!-- [OLD(GGUF - by IkariDev+Undi95)](https://huggingface.co/IkariDev/Athena-v4-GGUF)-->
+## Ratings:
+Note: We have permission of all users to upload their ratings, we DONT screenshot random reviews without asking if we can put them here!
+No ratings yet!
+If you want your rating to be here, send us a message over on DC and we'll put up a screenshot of it here. DC name is "ikaridev" and "undi".
+<!-- description end -->
+<!-- prompt-template start -->
+### Custom format:
+```
+### Instruction:
+{system prompt}
+### Input:
+{input}
+### Response:
+{reply}
+```
+## Datasets used:
+- Aesir 1 and 2 ([MinervaAI](https://huggingface.co/MinervaAI) / [Gryphe](https://huggingface.co/Gryphe))
+- [LimaRP-20231109](https://huggingface.co/datasets/lemonilia/LimaRP) ([Lemonilia](https://huggingface.co/lemonilia))
+- [ToxicDPO-NoWarning](https://huggingface.co/datasets/Undi95/toxic-dpo-v0.1-sharegpt) ([unalignment orga repo](https://huggingface.co/unalignment) + [Undi](https://huggingface.co/Undi95))
+- [No-robots-ShareGPT](https://huggingface.co/datasets/Doctor-Shotgun/no-robots-sharegpt) ([Doctor-Shotgun](https://huggingface.co/Doctor-Shotgu))
+## Others
+Undi: If you want to support me, you can [here](https://ko-fi.com/undiai).
+IkariDev: Visit my [retro/neocities style website](https://ikaridevgit.github.io/) please kek