Not-For-All-Audiences

nsfw

trl

grpo

conversational

Model card Files Files and versions

xet

Community

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

Libraries

Transformers

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

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

pipe = pipeline("text-generation", model="icefog72/IceLemonMedovukhaRP-7b")
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("icefog72/IceLemonMedovukhaRP-7b")
model = AutoModelForCausalLM.from_pretrained("icefog72/IceLemonMedovukhaRP-7b", 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 icefog72/IceLemonMedovukhaRP-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "icefog72/IceLemonMedovukhaRP-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "icefog72/IceLemonMedovukhaRP-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use icefog72/IceLemonMedovukhaRP-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/IceLemonMedovukhaRP-7b" \
    --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": "icefog72/IceLemonMedovukhaRP-7b",
		"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 "icefog72/IceLemonMedovukhaRP-7b" \
        --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": "icefog72/IceLemonMedovukhaRP-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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

IceLemonMedovukhaRP-7b (Ice0.101-20.03-RP-GRPO-2)

mistral v0.2 base

The words mead and medovukha are closely related and go back to the Proto-Indo-European word médʰu (honey). Produced in Eastern Europe since pagan times, it remained popular well into the 19th century (unlike in Western Europe, where by the Middle Ages mead had already been mostly replaced by wine and beer).

Normal model IceMedovukhaRP-7b pls use it if you don't want to play with reasoning

ST settings, rules-lorebook look here

Use rules as examples and edit them as needed; it's not necessary to have my every rule.

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

Model slightly trained to use <reasoning>...</reasoning> To use it - import given ST settings preset(+-rules-lorebook)

AND PUT <reasoning> in to Miscellaneous -> Start Reply With. I moved prompt to rules-lorebook for proper <reasoning> setup. Use and edit it.

ko-fi To buy sweets for my cat :3

The model has a context limit of 32k tokens. However, the quality of responses from any model begins to decline after 16k tokens, with a more rapid degradation beyond 21k tokens. I recommend using 21k tokens as the maximum for optimal performance.

Exl2 Quants

4.2bpw-exl2

6.5bpw-exl2

8bpw-exl2

Thx mradermacher for GGUF

GGUF

i1-GGUF

All Quants

All Quants

Download

I recommend using the huggingface-hub Python library:

pip3 install huggingface-hub

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

mkdir IceLemonMedovukhaRP-7b
huggingface-cli download icefog72/IceLemonMedovukhaRP-7b --local-dir IceLemonMedovukhaRP-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.

Uploaded model

Developed by: icefog72
License: cc-by-nc-4.0
Finetuned from model : icefog72/Ice0.101-20.03-RP-GRPO-1

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 18

Safetensors

Model size

7B params

Tensor type

F16

Model tree for icefog72/IceLemonMedovukhaRP-7b

Base model

icefog72/IceMedovukhaRP-7b

Finetuned

icefog72/Ice0.101-20.03-RP-GRPO-1

Finetuned

(1)

this model

Quantizations

9 models

Collection including icefog72/IceLemonMedovukhaRP-7b

Final RP Mistral-v0.2 (32k context) Models

Collection

7 items • Updated Nov 29, 2025 • 3