Instructions to use QuantFactory/Loki-v2.6-8b-1024k-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/Loki-v2.6-8b-1024k-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("QuantFactory/Loki-v2.6-8b-1024k-GGUF", dtype="auto")

llama-cpp-python

How to use QuantFactory/Loki-v2.6-8b-1024k-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/Loki-v2.6-8b-1024k-GGUF",
	filename="Loki-v2.6-8b-1024k.Q2_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use QuantFactory/Loki-v2.6-8b-1024k-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/Loki-v2.6-8b-1024k-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/Loki-v2.6-8b-1024k-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/Loki-v2.6-8b-1024k-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/Loki-v2.6-8b-1024k-GGUF: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 QuantFactory/Loki-v2.6-8b-1024k-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/Loki-v2.6-8b-1024k-GGUF: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 QuantFactory/Loki-v2.6-8b-1024k-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/Loki-v2.6-8b-1024k-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/Loki-v2.6-8b-1024k-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use QuantFactory/Loki-v2.6-8b-1024k-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/Loki-v2.6-8b-1024k-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/Loki-v2.6-8b-1024k-GGUF 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 QuantFactory/Loki-v2.6-8b-1024k-GGUF 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 QuantFactory/Loki-v2.6-8b-1024k-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/Loki-v2.6-8b-1024k-GGUF to start chatting

Docker Model Runner
How to use QuantFactory/Loki-v2.6-8b-1024k-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/Loki-v2.6-8b-1024k-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/Loki-v2.6-8b-1024k-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/Loki-v2.6-8b-1024k-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Loki-v2.6-8b-1024k-GGUF-Q4_K_M

List all available models

lemonade list

QuantFactory/Loki-v2.6-8b-1024k-GGUF

This is quantized version of MrRobotoAI/Loki-v2.6-8b-1024k created using llama.cpp

Original Model Card

merge

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using aifeifei798/llama3-8B-DarkIdol-2.2-Uncensored-1048K as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model: MrRobotoAI/Unaligned-RP-Base-8b-1024k

models:

  - model: Casual-Autopsy/L3-Luna-8B
  - model: Casual-Autopsy/L3-Super-Nova-RP-8B
  - model: Casual-Autopsy/L3-Umbral-Mind-RP-v3.0-8B
  - model: Casual-Autopsy/Halu-L3-Stheno-BlackOasis-8B
  - model: Undi95/Llama-3-Unholy-8B
  - model: Undi95/Llama-3-LewdPlay-8B
  - model: Undi95/Llama-3-LewdPlay-8B-evo
  - model: ChaoticNeutrals/Hathor_RP-v.01-L3-8B
  - model: ChaoticNeutrals/Sekhmet_Gimmel-L3.1-8B-v0.3
  - model: ChaoticNeutrals/Hathor_Tahsin-L3-8B-v0.9
  - model: ChaoticNeutrals/Hathor_Respawn-L3-8B-v0.8
  - model: ChaoticNeutrals/Domain-Fusion-L3-8B
  - model: ChaoticNeutrals/T-900-8B
  - model: ChaoticNeutrals/Templar_v1_8B
  - model: ChaoticNeutrals/Poppy_Porpoise-1.4-L3-8B
  - model: tannedbum/L3-Nymeria-Maid-8B
  - model: saishf/SOVLish-Maid-L3-8B
  - model: vicgalle/Humanish-Roleplay-Llama-3.1-8B
  - model: Nekochu/Luminia-8B-RP
  - model: Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP
  - model: jeiku/Chaos_RP_l3_8B
  - model: tohur/natsumura-storytelling-rp-1.0-llama-3.1-8b
  - model: zeroblu3/LewdPoppy-8B-RP
  - model: maldv/badger-mu-llama-3-8b
  - model: maldv/badger-lambda-llama-3-8b
  - model: maldv/badger-writer-llama-3-8b
  - model: maldv/llama-3-fantasy-writer-8b
  - model: maldv/badger-kappa-llama-3-8b
  - model: maldv/badger-lambda-0-llama-3-8b
  - model: maldv/badger-iota-llama-3-8b
  - model: mlabonne/Daredevil-8B-abliterated
  - model: mlabonne/NeuralDaredevil-8B-abliterated
  - model: Magpie-Align/MagpieLM-8B-Chat-v0.1
  - model: Magpie-Align/MagpieLM-8B-SFT-v0.1
  - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1
  - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
  - model: nbeerbower/llama-3-gutenberg-8B
  - model: nbeerbower/llama-3-spicy-abliterated-stella-8B  
  - model: nothingiisreal/L3-8B-Instruct-Abliterated-DWP
  - model: nothingiisreal/L3-8B-Stheno-Horny-v3.3-32K
  - model: abacusai/Llama-3-Smaug-8B
  - model: ajibawa-2023/Scarlett-Llama-3-8B-v1.0
  - model: ajibawa-2023/SlimOrca-Llama-3-8B
  - model: ajibawa-2023/Uncensored-Frank-Llama-3-8B
  - model: Blackroot/Llama-3-Gamma-Twist
  - model: Blackroot/Llama-3-LongStory
  - model: ChaoticNeutrals/Templar_v1_8B
  - model: ChaoticNeutrals/Sekhmet_Gimmel-L3.1-8B-v0.3
  - model: ChaoticNeutrals/Hathor_Tahsin-L3-8B-v0.9
  - model: FPHam/L3-8B-Everything-COT
  - model: ResplendentAI/Nymph_8B
  - model: NousResearch/Hermes-2-Theta-Llama-3-8B
  - model: openchat/openchat-3.6-8b-20240522
  - model: OwenArli/Awanllm-Llama-3-8B-Cumulus-v1.0
  - model: refuelai/Llama-3-Refueled
  - model: SicariusSicariiStuff/LLAMA-3_8B_Unaligned_Alpha
  - model: TIGER-Lab/MAmmoTH2-8B-Plus
  - model: turboderp/llama3-turbcat-instruct-8b
  - model: UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3
  - model: Undi95/Llama-3-LewdPlay-8B
  - model: ChaoticNeutrals/Hathor_RP-v.01-L3-8B
  - model: flammenai/Mahou-1.3b-llama3-8B
  - model: grimjim/Llama-3-Oasis-v1-OAS-8B
  - model: grimjim/llama-3-Nephilim-v2.1-8B
  - model: grimjim/Llama-3.1-SuperNova-Lite-lorabilterated-8B  
  - model: grimjim/Llama-Nephilim-Metamorphosis-v2-8B
  - model: grimjim/Llama-3-Perky-Pat-Instruct-8B
  - model: lemon07r/Llama-3-RedMagic4-8B
  - model: lemon07r/Lllama-3-RedElixir-8B
  - model: ChaoticNeutrals/Hathor_Respawn-L3-8B-v0.8
  - model: failspy/Meta-Llama-3-8B-Instruct-abliterated-v3
  - model: HaitameLaf/Llama-3-8B-StoryGenerator
  - model: Locutusque/Llama-3-Hercules-5.0-8B
  - model: HPAI-BSC/Llama3-Aloe-8B-Alpha
  - model: iRyanBell/ARC1-II
  - model: migtissera/Llama-3-8B-Synthia-v3.5
  - model: Undi95/Llama-3-Unholy-8B
  - model: VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
  - model: WhiteRabbitNeo/Llama-3-WhiteRabbitNeo-8B-v2.0
  - model: aifeifei798/llama3-8B-DarkIdol-2.2-Uncensored-1048K
  - model: Khetterman/CursedMatrix-8B-v9

merge_method: model_stock
base_model: aifeifei798/llama3-8B-DarkIdol-2.2-Uncensored-1048K
normalize: true
dtype: float16

The following YAML configuration was used to produce this model: MrRobotoAI/Loki-8b-1024k-v2

models:

  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+surya-narayanan/formal_logic
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+surya-narayanan/conceptual_physics
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+surya-narayanan/college_physics
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+surya-narayanan/electrical_engineering
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+surya-narayanan/college_chemistry
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+surya-narayanan/college_computer_science
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+surya-narayanan/psychology_non_masked
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+surya-narayanan/physics_non_masked
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+surya-narayanan/philosophy_non_masked
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+surya-narayanan/philosophy_100
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+surya-narayanan/psychology
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+surya-narayanan/philosophy
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+surya-narayanan/world_religions
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+surya-narayanan/sociology
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+surya-narayanan/human_sexuality
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+surya-narayanan/high_school_european_history
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+surya-narayanan/electrical_engineering
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+Azazelle/Llama-3-LimaRP-Instruct-LoRA-8B 
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+Azazelle/Llama-3-8B-Abomination-LORA
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+nothingiisreal/llama3-8B-DWP-lora
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+Blackroot/Llama3-RP-Lora
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+Azazelle/Llama-3-LimaRP-Instruct-LoRA-8B
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+Azazelle/Llama-3-LongStory-LORA
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+ResplendentAI/Theory_of_Mind_Llama3
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+ResplendentAI/Aura_Llama3
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+ResplendentAI/Luna_Llama3
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+ResplendentAI/BlueMoon_Llama3
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+ResplendentAI/NoWarning_Llama3
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+Azazelle/L3-Daybreak-8b-lora
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+Blackroot/Llama-3-LongStory-LORA
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+Azazelle/Smarts_Llama3
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+Azazelle/Nimue-8B
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+Azazelle/Llama-3-LongStory-LORA
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+vincentyandex/lora_llama3_chunked_novel_bs128
  - model: MrRobotoAI/Unaligned-RP-Base-8b-1024k+nicce/story-mixtral-8x7b-lora

merge_method: model_stock
base_model: aifeifei798/llama3-8B-DarkIdol-2.2-Uncensored-1048K
normalize: true
dtype: float16