Instructions to use alchemonaut/BoreanGale-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alchemonaut/BoreanGale-70B with Transformers:

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

pipe = pipeline("text-generation", model="alchemonaut/BoreanGale-70B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alchemonaut/BoreanGale-70B")
model = AutoModelForCausalLM.from_pretrained("alchemonaut/BoreanGale-70B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alchemonaut/BoreanGale-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alchemonaut/BoreanGale-70B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alchemonaut/BoreanGale-70B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/alchemonaut/BoreanGale-70B

SGLang

How to use alchemonaut/BoreanGale-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 "alchemonaut/BoreanGale-70B" \
    --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": "alchemonaut/BoreanGale-70B",
		"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 "alchemonaut/BoreanGale-70B" \
        --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": "alchemonaut/BoreanGale-70B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use alchemonaut/BoreanGale-70B with Docker Model Runner:
```
docker model run hf.co/alchemonaut/BoreanGale-70B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

BoreanGale-70B

A merge using a custom algorithm (NearSwap) of:

Quants

Several quants are available thanks to community efforts.

Type	Misc	Author
GGUF	iMat Q3	Nexesenex
GGUF	iMat	mradermacher
GGUF	Full Set	mradermacher
GGUF	Misc	LoneStriker
exl2	2.4 bpw	LoneStriker
exl2	3.5 bpw	LoneStriker
exl2	4.0 bpw	LoneStriker
exl2	4.65 bpw	LoneStriker

NearSwap Algorithm

NearSwap retains most of the weights of the base model (Miqu), but when a weight is similar between the two, it is interpolated to the secondary model (WinterGoddess) value. A parameter t specifies the sameness threshold. When the distance between two values is below t, the weight from the secondary model (WinterGoddess) is used.

This version of the model uses t = 0.001. At this t, about 10% of weights are fully switched to WinterGoddess. Model quality rapidly degrades above t = 0.0025:

t = 0.0001 (~0.8% full swap): QuartetAnemoi-70B-t0.0001
t = 0.0003 (~2% full swap)
t = 0.001 (~10% full swap): This model
t = 0.0025 (~18% full swap): Generates one paragraph okay, but then reverts to garbage
t = 0.005 (~35% full swap): Garbage; semi-related word lists
t = 0.01 (~55% full swap): Garbage; pseudorandom tokens output

NearSwap implementation:

    t: Union[float, np.ndarray],
    v0: Union[np.ndarray, torch.Tensor],
    v1: Union[np.ndarray, torch.Tensor],
...
    lweight = numpy.absolute(v0-v1)
    lweight = t / lweight
    lweight = numpy.nan_to_num(lweight, nan=1.0, posinf=1.0, neginf=1.0)
    numpy.clip(lweight, a_min=0.0, a_max=1.0, out=lweight)
    res = lerp(lweight,v0,v1)

License and Use

Since the ultimate origin of Miqu is at this time unknown beyond speculation, this model is for noncommercial research use only.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	76.48
AI2 Reasoning Challenge (25-Shot)	73.89
HellaSwag (10-Shot)	89.37
MMLU (5-Shot)	75.19
TruthfulQA (0-shot)	68.6
Winogrande (5-shot)	84.53
GSM8k (5-shot)	67.32

Downloads last month: 77

Safetensors

Model size

69B params

Tensor type

F16

Model tree for alchemonaut/BoreanGale-70B

Merges

1 model

Quantizations

2 models

Spaces using alchemonaut/BoreanGale-70B 16

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

73.890
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

89.370
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

75.190
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

68.600
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

84.530
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

67.320