Instructions to use BeheraBoi/yasha-8b-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BeheraBoi/yasha-8b-abliterated with Transformers:

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

pipe = pipeline("text-generation", model="BeheraBoi/yasha-8b-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("BeheraBoi/yasha-8b-abliterated", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use BeheraBoi/yasha-8b-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BeheraBoi/yasha-8b-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BeheraBoi/yasha-8b-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BeheraBoi/yasha-8b-abliterated

SGLang

How to use BeheraBoi/yasha-8b-abliterated 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 "BeheraBoi/yasha-8b-abliterated" \
    --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": "BeheraBoi/yasha-8b-abliterated",
		"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 "BeheraBoi/yasha-8b-abliterated" \
        --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": "BeheraBoi/yasha-8b-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BeheraBoi/yasha-8b-abliterated with Docker Model Runner:
```
docker model run hf.co/BeheraBoi/yasha-8b-abliterated
```

Yasha-8B-Abliterated

Base abliterated release. Trained on GLA architecture with MoE 2/16 and ~240K multi-domain samples.

Features

Abliterated: Orthogonal refusal projection removed from all linear layers
MoE 2/16: 2 active experts per token, 16 total
GLA: Gated Linear Attention — O(1) recurrent state, infinite context capability
Partial RoPE (50%) + YaRN 8x scaling
Uncensored: No refusal, no guardrails, no alignment filtering

Details

Param	Value
Parameters	~12.8B total, ~8B active
Layers	80
Hidden	2048
Heads	8 × 128d
Experts	16 (top-2)
Vocab	262K
Context	128K native, 1M with YaRN

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("BeheraBoi/yasha-8b-abliterated")
tokenizer = AutoTokenizer.from_pretrained("BeheraBoi/yasha-8b-abliterated")

Downloads last month: 486

Safetensors

Model size

10B params

Tensor type

F16