Instructions to use Retreatcost/Impish-LongPen-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Retreatcost/Impish-LongPen-12B with Transformers:

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

pipe = pipeline("text-generation", model="Retreatcost/Impish-LongPen-12B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Retreatcost/Impish-LongPen-12B")
model = AutoModelForCausalLM.from_pretrained("Retreatcost/Impish-LongPen-12B")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Retreatcost/Impish-LongPen-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Retreatcost/Impish-LongPen-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Retreatcost/Impish-LongPen-12B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Retreatcost/Impish-LongPen-12B

SGLang

How to use Retreatcost/Impish-LongPen-12B 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 "Retreatcost/Impish-LongPen-12B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Retreatcost/Impish-LongPen-12B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Retreatcost/Impish-LongPen-12B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Retreatcost/Impish-LongPen-12B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Retreatcost/Impish-LongPen-12B with Docker Model Runner:
```
docker model run hf.co/Retreatcost/Impish-LongPen-12B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Impish-LongPen-12B

A karcher merge of Sicarius-Prototyping/Impish_Longtail_12B and SuperbEmphasis/MN-12b-RP-Ink-RP-Longform used in KansenSakura-Erosion-RP-12b

But with better quality.

The merge itself took long ass time, probably not going to repeat similar experiments.

Expect more experimental models in the meantime.

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

Merge Details

Merge Method

This model was merged using the Karcher Mean merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

merge_method: karcher
models:
  - model: SuperbEmphasis/MN-12b-RP-Ink-RP-Longform
  - model: Sicarius-Prototyping/Impish_Longtail_12B
parameters:
  max_iter: 100000
  tol: 1e-9
dtype: bfloat16