Instructions to use v000000/L3.1-Niitorm-8B-t0.0001 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use v000000/L3.1-Niitorm-8B-t0.0001 with Transformers:

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

pipe = pipeline("text-generation", model="v000000/L3.1-Niitorm-8B-t0.0001")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("v000000/L3.1-Niitorm-8B-t0.0001")
model = AutoModelForCausalLM.from_pretrained("v000000/L3.1-Niitorm-8B-t0.0001", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use v000000/L3.1-Niitorm-8B-t0.0001 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "v000000/L3.1-Niitorm-8B-t0.0001"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "v000000/L3.1-Niitorm-8B-t0.0001",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/v000000/L3.1-Niitorm-8B-t0.0001

SGLang

How to use v000000/L3.1-Niitorm-8B-t0.0001 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 "v000000/L3.1-Niitorm-8B-t0.0001" \
    --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": "v000000/L3.1-Niitorm-8B-t0.0001",
		"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 "v000000/L3.1-Niitorm-8B-t0.0001" \
        --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": "v000000/L3.1-Niitorm-8B-t0.0001",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use v000000/L3.1-Niitorm-8B-t0.0001 with Docker Model Runner:
```
docker model run hf.co/v000000/L3.1-Niitorm-8B-t0.0001
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-3.1-Niitorm-8B

RP model, Niitama 1.1 as a base, nearswapped with one of the smartest 3.1 models "Storm", mostly abliterated.

Thank you mradermacher for the quants!

Thank you QuantFactory for the quants!

GGUF

merge

This is a merge of pre-trained language models.

Merge Details

Merge Method

This model was merged using the NEARSWAP t0.0001 merge algorithm.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Sao10K/L3.1-8B-Niitama-v1.1+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
        layer_range: [0, 32]
      - model: akjindal53244/Llama-3.1-Storm-8B
        layer_range: [0, 32]
merge_method: nearswap
base_model: Sao10K/L3.1-8B-Niitama-v1.1+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
parameters:
  t:
    - value: 0.0001
dtype: bfloat16
out_type: float16 #oops

Prompt Template:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>

Credit to Alchemonaut.

Credit to woofwolfy for the idea.