Instructions to use Nitral-Archive/Mika-Lelantacles-7b-Longtext with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nitral-Archive/Mika-Lelantacles-7b-Longtext with Transformers:

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

pipe = pipeline("text-generation", model="Nitral-Archive/Mika-Lelantacles-7b-Longtext", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nitral-Archive/Mika-Lelantacles-7b-Longtext", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Nitral-Archive/Mika-Lelantacles-7b-Longtext", trust_remote_code=True)
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

vLLM

How to use Nitral-Archive/Mika-Lelantacles-7b-Longtext with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nitral-Archive/Mika-Lelantacles-7b-Longtext"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nitral-Archive/Mika-Lelantacles-7b-Longtext",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nitral-Archive/Mika-Lelantacles-7b-Longtext

SGLang

How to use Nitral-Archive/Mika-Lelantacles-7b-Longtext 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 "Nitral-Archive/Mika-Lelantacles-7b-Longtext" \
    --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": "Nitral-Archive/Mika-Lelantacles-7b-Longtext",
		"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 "Nitral-Archive/Mika-Lelantacles-7b-Longtext" \
        --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": "Nitral-Archive/Mika-Lelantacles-7b-Longtext",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nitral-Archive/Mika-Lelantacles-7b-Longtext with Docker Model Runner:
```
docker model run hf.co/Nitral-Archive/Mika-Lelantacles-7b-Longtext
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Nitral-AI/Mika-Longtext-7b
        layer_range: [0, 32]
      - model: ChaoticNeutrals/Prima-LelantaclesV7-experimental-7b
        layer_range: [0, 32]
merge_method: slerp
base_model: Nitral-AI/Mika-Longtext-7b
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

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	70.86
AI2 Reasoning Challenge (25-Shot)	67.66
HellaSwag (10-Shot)	86.34
MMLU (5-Shot)	63.29
TruthfulQA (0-shot)	70.15
Winogrande (5-shot)	79.79
GSM8k (5-shot)	57.92

Downloads last month: 43

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for Nitral-Archive/Mika-Lelantacles-7b-Longtext

Base model

ChaoticNeutrals/Prima-LelantaclesV6.69-7b

Finetuned

ChaoticNeutrals/Prima-LelantaclesV7-experimental-7b

Finetuned

(1)

this model

Quantizations

2 models

Evaluation results

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

67.660
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

86.340
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

63.290
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

70.150
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

79.790
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

57.920