Instructions to use Malcolmdenis/Pillar-3-Knox-9625 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Malcolmdenis/Pillar-3-Knox-9625 with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Malcolmdenis/Pillar-3-Knox-9625", dtype="auto")

llama-cpp-python

How to use Malcolmdenis/Pillar-3-Knox-9625 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Malcolmdenis/Pillar-3-Knox-9625",
	filename="unsloth.Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Malcolmdenis/Pillar-3-Knox-9625 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 Malcolmdenis/Pillar-3-Knox-9625:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Malcolmdenis/Pillar-3-Knox-9625:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Malcolmdenis/Pillar-3-Knox-9625:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Malcolmdenis/Pillar-3-Knox-9625:Q4_K_M

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 Malcolmdenis/Pillar-3-Knox-9625:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Malcolmdenis/Pillar-3-Knox-9625:Q4_K_M

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 Malcolmdenis/Pillar-3-Knox-9625:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Malcolmdenis/Pillar-3-Knox-9625:Q4_K_M

Use Docker

docker model run hf.co/Malcolmdenis/Pillar-3-Knox-9625:Q4_K_M

LM Studio
Jan
Ollama
How to use Malcolmdenis/Pillar-3-Knox-9625 with Ollama:
```
ollama run hf.co/Malcolmdenis/Pillar-3-Knox-9625:Q4_K_M
```

Unsloth Studio

How to use Malcolmdenis/Pillar-3-Knox-9625 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 Malcolmdenis/Pillar-3-Knox-9625 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 Malcolmdenis/Pillar-3-Knox-9625 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Malcolmdenis/Pillar-3-Knox-9625 to start chatting

Atomic Chat new
Docker Model Runner
How to use Malcolmdenis/Pillar-3-Knox-9625 with Docker Model Runner:
```
docker model run hf.co/Malcolmdenis/Pillar-3-Knox-9625:Q4_K_M
```

Lemonade

How to use Malcolmdenis/Pillar-3-Knox-9625 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Malcolmdenis/Pillar-3-Knox-9625:Q4_K_M

Run and chat with the model

lemonade run user.Pillar-3-Knox-9625-Q4_K_M

List all available models

lemonade list

Pillar-3-Knox-9625 / config.json

Malcolmdenis

(Trained with Unsloth)

b893a16 about 1 year ago

Raw

History Blame

1.24 kB

	{
	"architectures": [
	"MistralForCausalLM"
	],
	"attention_dropout": 0.0,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 5120,
	"initializer_range": 0.02,
	"intermediate_size": 32768,
	"max_position_embeddings": 32768,
	"model_type": "mistral",
	"num_attention_heads": 32,
	"num_hidden_layers": 40,
	"num_key_value_heads": 8,
	"pad_token_id": 11,
	"quantization_config": {
	"bnb_4bit_compute_dtype": "bfloat16",
	"bnb_4bit_quant_type": "nf4",
	"bnb_4bit_use_double_quant": true,
	"llm_int8_enable_fp32_cpu_offload": false,
	"llm_int8_has_fp16_weight": false,
	"llm_int8_skip_modules": [
	"model.layers.2.mlp.gate_proj",
	"model.layers.2.mlp.up_proj",
	"model.layers.2.mlp.down_proj",
	"lm_head"
	],
	"llm_int8_threshold": 6.0,
	"load_in_4bit": true,
	"load_in_8bit": false,
	"quant_method": "bitsandbytes"
	},
	"rms_norm_eps": 1e-05,
	"rope_scaling": null,
	"rope_theta": 100000000.0,
	"sliding_window": null,
	"tie_word_embeddings": false,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.51.3",
	"unsloth_fixed": true,
	"unsloth_version": "2025.6.1",
	"use_cache": true,
	"vocab_size": 131072
	}