Instructions to use NeverSleepHistorical/Noromaid-7B-0.4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NeverSleepHistorical/Noromaid-7B-0.4 with Transformers:

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

pipe = pipeline("text-generation", model="NeverSleepHistorical/Noromaid-7B-0.4")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NeverSleepHistorical/Noromaid-7B-0.4")
model = AutoModelForCausalLM.from_pretrained("NeverSleepHistorical/Noromaid-7B-0.4")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use NeverSleepHistorical/Noromaid-7B-0.4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NeverSleepHistorical/Noromaid-7B-0.4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeverSleepHistorical/Noromaid-7B-0.4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NeverSleepHistorical/Noromaid-7B-0.4

SGLang

How to use NeverSleepHistorical/Noromaid-7B-0.4 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 "NeverSleepHistorical/Noromaid-7B-0.4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeverSleepHistorical/Noromaid-7B-0.4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "NeverSleepHistorical/Noromaid-7B-0.4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeverSleepHistorical/Noromaid-7B-0.4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NeverSleepHistorical/Noromaid-7B-0.4 with Docker Model Runner:
```
docker model run hf.co/NeverSleepHistorical/Noromaid-7B-0.4
```

This model is a collab between IkariDev and Undi!

Description

This repo contains fp16 files of Noromaid-7b-v0.4. DPO version was choosen over this one, and are available here:

FP16 - by IkariDev and Undi

GGUF - by IkariDev and Undi

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".

Prompt format: Chatml

<|im_start|>system
{sysprompt}<|im_end|>
<|im_start|>user
{input}<|im_end|>
<|im_start|>assistant
{output}<|im_end|>

Training data used:

no_robots dataset let the model have more human behavior, enhances the output.
[Aesir Private RP dataset] New data from a new and never used before dataset, add fresh data, no LimaRP spam, this is 100% new. Thanks to the MinvervaAI Team and, in particular, Gryphe for letting us use it!
[Another private Aesir dataset]
[Another private Aesir dataset]
limarp

This is a full finetune. Trained until 2 epoch, trained on mistral 0.1 7b base.

Others

Undi: If you want to support me, you can here.

IkariDev: Visit my retro/neocities style website please kek

Downloads last month: 7