Not-For-All-Audiences

nsfw

Instructions to use Undi95/Borealis-10.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Undi95/Borealis-10.7B with Transformers:

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

pipe = pipeline("text-generation", model="Undi95/Borealis-10.7B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Undi95/Borealis-10.7B")
model = AutoModelForCausalLM.from_pretrained("Undi95/Borealis-10.7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Undi95/Borealis-10.7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Undi95/Borealis-10.7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Undi95/Borealis-10.7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Undi95/Borealis-10.7B

SGLang

How to use Undi95/Borealis-10.7B 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 "Undi95/Borealis-10.7B" \
    --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": "Undi95/Borealis-10.7B",
		"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 "Undi95/Borealis-10.7B" \
        --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": "Undi95/Borealis-10.7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Undi95/Borealis-10.7B with Docker Model Runner:
```
docker model run hf.co/Undi95/Borealis-10.7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Borealis

Borealis-10.7B is a 10.7B model made of 48 Mistral 7B layers, finetuned for +70h on 2xA6000 on a big RP and Conversational dataset with llama2 configuration of Axolotl, like SOLAR.

Next step would be to do a DPO train on top, but I don't know if it would be benefical.

Description

This repo contains fp16 files of Borealis-10.7B, a conversational model.

The goal of this model isn't to break all benchmark, but to have a better RP/ERP/Conversational model.

It was trained on multiple basic dataset to make it intelligent, but majority of the dataset was basic conversations.

Dataset used

NobodyExistsOnTheInternet/ToxicQAFinal
teknium/openhermes
unalignment/spicy-3.1
Doctor-Shotgun/no-robots-sharegpt
Undi95/toxic-dpo-v0.1-sharegpt
Aesir [1], [2], [3-SFW], [3-NSFW]
lemonilia/LimaRP
Squish42/bluemoon-fandom-1-1-rp-cleaned
Undi95/ConversationChronicles-sharegpt-SHARDED (2 sets, modified)

Prompt format: NsChatml

<|im_system|>
{sysprompt}<|im_end|>
<|im_user|>
{input}<|im_end|>
<|im_bot|>
{output}<|im_end|>

Others

If you want to support me, you can here.

Downloads last month: 15

Model tree for Undi95/Borealis-10.7B

Quantizations

2 models

Collection including Undi95/Borealis-10.7B

Honorable mentions

Collection

Some models I've made and I liked but isn't part of a serie. • 10 items • Updated Feb 4, 2024 • 6