Not-For-All-Audiences

nsfw

Instructions to use icefog72/IceNalyvkaRP-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use icefog72/IceNalyvkaRP-7b with Transformers:

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

pipe = pipeline("text-generation", model="icefog72/IceNalyvkaRP-7b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("icefog72/IceNalyvkaRP-7b")
model = AutoModelForCausalLM.from_pretrained("icefog72/IceNalyvkaRP-7b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use icefog72/IceNalyvkaRP-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "icefog72/IceNalyvkaRP-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "icefog72/IceNalyvkaRP-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/icefog72/IceNalyvkaRP-7b

SGLang

How to use icefog72/IceNalyvkaRP-7b 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 "icefog72/IceNalyvkaRP-7b" \
    --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": "icefog72/IceNalyvkaRP-7b",
		"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 "icefog72/IceNalyvkaRP-7b" \
        --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": "icefog72/IceNalyvkaRP-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use icefog72/IceNalyvkaRP-7b with Docker Model Runner:
```
docker model run hf.co/icefog72/IceNalyvkaRP-7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

IceNalyvkaRP-7b (Ice0.70-25.01-RP)

Nalyvka is a delightful gem from Eastern European tradition—a homemade liqueur that captures the essence of ripe fruits and the warmth of shared moments. Originating primarily in Ukraine and also cherished in Poland

ST settings, rules-lorebook look here

Get last version of rules, or ask me a questions you can here. on my new AI related discord server for feedback, questions and other stuff.

In general Alpaca format will work.

ko-fi To buy sweets for my cat :3

It shoud handle 16-25k context window, maybe 32k.

Exl2 Quants

4.2bpw-exl2

6.5bpw-exl2

8bpw-exl2

Thx mradermacher for GGUF

GGUF

i1-GGUF

Download

I recommend using the huggingface-hub Python library:

pip3 install huggingface-hub

To download the main branch to a folder called IceNalyvkaRP-7b:

mkdir IceNalyvkaRP-7b
huggingface-cli download icefog72/IceNalyvkaRP-7b --local-dir IceNalyvkaRP-7b --local-dir-use-symlinks False

More advanced huggingface-cli download usage

If you remove the --local-dir-use-symlinks False parameter, the files will instead be stored in the central Hugging Face cache directory (default location on Linux is: ~/.cache/huggingface), and symlinks will be added to the specified --local-dir, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.

The cache location can be changed with the HF_HOME environment variable, and/or the --cache-dir parameter to huggingface-cli.

For more documentation on downloading with huggingface-cli, please see: HF -> Hub Python Library -> Download files -> Download from the CLI.

To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer:

pip3 install hf_transfer

And set environment variable HF_HUB_ENABLE_HF_TRANSFER to 1:

mkdir FOLDERNAME
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download MODEL --local-dir FOLDERNAME --local-dir-use-symlinks False

Windows Command Line users: You can set the environment variable by running set HF_HUB_ENABLE_HF_TRANSFER=1 before the download command.

Merge Method

This is a merge of pre-trained language models created using mergekit. This model was merged using the SLERP merge method.

Models Merged

The following models were included in the merge:

Ice0.69-25.01-RP
Ice0.68-25.01-RP

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: Ice0.69-25.01-RP
        layer_range: [0, 32]
      - model: Ice0.68-25.01-RP
        layer_range: [0, 32]

merge_method: slerp
base_model: Ice0.68-25.01-RP
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 # fallback for rest of tensors
dtype: bfloat16