Instructions to use schonsense/70B_llama33_stock_unslop with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use schonsense/70B_llama33_stock_unslop with Transformers:

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

pipe = pipeline("text-generation", model="schonsense/70B_llama33_stock_unslop")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("schonsense/70B_llama33_stock_unslop")
model = AutoModelForCausalLM.from_pretrained("schonsense/70B_llama33_stock_unslop", 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 schonsense/70B_llama33_stock_unslop with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "schonsense/70B_llama33_stock_unslop"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "schonsense/70B_llama33_stock_unslop",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/schonsense/70B_llama33_stock_unslop

SGLang

How to use schonsense/70B_llama33_stock_unslop 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 "schonsense/70B_llama33_stock_unslop" \
    --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": "schonsense/70B_llama33_stock_unslop",
		"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 "schonsense/70B_llama33_stock_unslop" \
        --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": "schonsense/70B_llama33_stock_unslop",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use schonsense/70B_llama33_stock_unslop with Docker Model Runner:
```
docker model run hf.co/schonsense/70B_llama33_stock_unslop
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Geometric average of llama 3.3 instruct with it's abliterated version and a slop token suppressed version

An attempt at getting the best of all worlds. Still in testing.

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using meta-llama/Llama-3.1-70B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: model_stock

base_model: meta-llama/Llama-3.1-70B

models:
  - model: sam-paech/Llama-3.3-70B-Instruct-ftpo_1k
  - model: meta-llama/Llama-3.3-70B-Instruct
  - model: schonsense/llama33_inst_multivector_derestriction

parameters:
  normalize: false
  int8_mask: true

dtype: float32
out_dtype: bfloat16

tokenizer:
  source: meta-llama/Llama-3.3-70B-Instruct
  pad_to_multiple_of: 8