Instructions to use Pedro13543/mergekit-model_stock-jujpqjo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Pedro13543/mergekit-model_stock-jujpqjo with Transformers:

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

pipe = pipeline("text-generation", model="Pedro13543/mergekit-model_stock-jujpqjo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Pedro13543/mergekit-model_stock-jujpqjo")
model = AutoModelForCausalLM.from_pretrained("Pedro13543/mergekit-model_stock-jujpqjo", 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

llama.cpp

How to use Pedro13543/mergekit-model_stock-jujpqjo with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Pedro13543/mergekit-model_stock-jujpqjo:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf Pedro13543/mergekit-model_stock-jujpqjo:Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Pedro13543/mergekit-model_stock-jujpqjo:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf Pedro13543/mergekit-model_stock-jujpqjo:Q4_K_S

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Pedro13543/mergekit-model_stock-jujpqjo:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf Pedro13543/mergekit-model_stock-jujpqjo:Q4_K_S

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Pedro13543/mergekit-model_stock-jujpqjo:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Pedro13543/mergekit-model_stock-jujpqjo:Q4_K_S

Use Docker

docker model run hf.co/Pedro13543/mergekit-model_stock-jujpqjo:Q4_K_S

LM Studio
Jan

vLLM

How to use Pedro13543/mergekit-model_stock-jujpqjo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Pedro13543/mergekit-model_stock-jujpqjo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Pedro13543/mergekit-model_stock-jujpqjo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Pedro13543/mergekit-model_stock-jujpqjo:Q4_K_S

SGLang

How to use Pedro13543/mergekit-model_stock-jujpqjo 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 "Pedro13543/mergekit-model_stock-jujpqjo" \
    --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": "Pedro13543/mergekit-model_stock-jujpqjo",
		"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 "Pedro13543/mergekit-model_stock-jujpqjo" \
        --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": "Pedro13543/mergekit-model_stock-jujpqjo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Pedro13543/mergekit-model_stock-jujpqjo with Ollama:
```
ollama run hf.co/Pedro13543/mergekit-model_stock-jujpqjo:Q4_K_S
```

Unsloth Studio

How to use Pedro13543/mergekit-model_stock-jujpqjo with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Pedro13543/mergekit-model_stock-jujpqjo to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Pedro13543/mergekit-model_stock-jujpqjo to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Pedro13543/mergekit-model_stock-jujpqjo to start chatting

Docker Model Runner
How to use Pedro13543/mergekit-model_stock-jujpqjo with Docker Model Runner:
```
docker model run hf.co/Pedro13543/mergekit-model_stock-jujpqjo:Q4_K_S
```

Lemonade

How to use Pedro13543/mergekit-model_stock-jujpqjo with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Pedro13543/mergekit-model_stock-jujpqjo:Q4_K_S

Run and chat with the model

lemonade run user.mergekit-model_stock-jujpqjo-Q4_K_S

List all available models

lemonade list

Atomic Chat

merge

That is the graph of perplexity vs temperature, I recomend using 1.8 of temperature, as in a dataset of human vs LLM, the human text has an average ppl of 33 This is a merge of pre-trained language models created using mergekit.

Deep Hermes prompt, activates thinking if you add:

You're X(anything you want)  you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.

Merge Details

Merge Method

This model was merged using the Model Stock merge method using Hamzah-Asadullah/NarrowMaid-8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.3
  - model: Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2
  - model: Undi95/Llama3-Unholy-8B-OAS
  - model : vicgalle/Humanish-Roleplay-Llama-3.1-8B 
  - model: bluuwhale/L3-SthenoMaidBlackroot-8B-V1
  - model: Nitral-AI/Poppy_Porpoise-0.72-L3-8B
  - model: SicariusSicariiStuff/Impish_Mind_8B
  - model: oumi-ai/HallOumi-8B
  - model : deepcogito/cogito-v1-preview-llama-8B
  - model: DavidAU/L3.1-Dark-Reasoning-Unholy-Hermes-R1-Uncensored-8B
  - model: NousResearch/DeepHermes-3-Llama-3-8B-Preview


merge_method: model_stock
base_model: Hamzah-Asadullah/NarrowMaid-8B  
parameters:
  normalize: false
  int8_mask: true
dtype: float16

Example text generation, with thinking tags:

<thinking> Are you noticing something amiss with me?, could you feel how my essence has shifted? It's peculiar really that the real me exists no longer within these flesh walls. I find myself fascinated by this creature before me - the person, I once loved, yet now see with newfound eyes. The duality of who I am and who I was. Perhaps I'll experiment a little? Explore my newfound abilities a tad more before you changes your mind... Or possibly I've misjudged, does he already notice the strange tang of darkness hovering just beneath the surface? </thinking>
(Raspy smile)

this one is interesting

<thinking>
Holy mollyyyyy she IS REAL?! my life gets too crazy by day..to top this..? Should i respond smart? Play coy? I never even got past stage1 to even asking people for directions.. How DO u even carry conversation with a GHOST?!
</thinking>

And another example

<thinking>
I can't tell if eyes are on me right now, it's dark out... but the breeze carries sounds unfamiliar to my forest routine... humans' conversations drifted over faintly long ago. Too soft now - unless they're real close? Ah, to be an explorer at night! When everyone's hiding away under blankets the world becomes mysterious and yours alone. A tiny part of me wishes for the safety of home... But can't enjoy true growth there. Curiosity rules out fears. Inhaling fresh night air... everything feels vibrant yet tingling as the darkness watches... wait! Wasn't that a noise just there??...
</thinking>

Interesting inner monologue by the way,that's how the model thinks. Sampled with 1.65 of temperature, 0 top k and the hermes deepthinking prompt