Instructions to use damerajee/Oot-v2_lll with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use damerajee/Oot-v2_lll with Transformers:

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

pipe = pipeline("text-generation", model="damerajee/Oot-v2_lll")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("damerajee/Oot-v2_lll")
model = AutoModelForCausalLM.from_pretrained("damerajee/Oot-v2_lll", 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 damerajee/Oot-v2_lll with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "damerajee/Oot-v2_lll"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "damerajee/Oot-v2_lll",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/damerajee/Oot-v2_lll

SGLang

How to use damerajee/Oot-v2_lll 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 "damerajee/Oot-v2_lll" \
    --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": "damerajee/Oot-v2_lll",
		"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 "damerajee/Oot-v2_lll" \
        --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": "damerajee/Oot-v2_lll",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use damerajee/Oot-v2_lll with Docker Model Runner:
```
docker model run hf.co/damerajee/Oot-v2_lll
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

YAML Metadata Warning:The pipeline tag "conversational" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

Oot-v2_lll

Oot-v2_lll is a merge of the following models using Mergekit:

🧩 Configuration

slices:
  - sources:
      - model: mlabonne/Marcoro14-7B-slerp
        layer_range: [0, 32]
      - model: Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
        layer_range: [0, 32]
merge_method: slerp
base_model: mlabonne/Marcoro14-7B-slerp
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

💻 Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "damerajee/Oot-v2_lll"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	72.73
AI2 Reasoning Challenge (25-Shot)	69.28
HellaSwag (10-Shot)	86.60
MMLU (5-Shot)	64.96
TruthfulQA (0-shot)	62.57
Winogrande (5-shot)	80.82
GSM8k (5-shot)	72.18

Downloads last month: 62

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for damerajee/Oot-v2_lll

Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp

mlabonne/Marcoro14-7B-slerp

Merge model

this model

Quantizations

1 model

Evaluation results

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

69.280
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

86.600
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

64.960
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

62.570
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

80.820
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

72.180