Instructions to use Fischerboot/2b-gguf-tiny-llama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Fischerboot/2b-gguf-tiny-llama with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Fischerboot/2b-gguf-tiny-llama", dtype="auto")

llama-cpp-python

How to use Fischerboot/2b-gguf-tiny-llama with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Fischerboot/2b-gguf-tiny-llama",
	filename="ggml-model-f16.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 Fischerboot/2b-gguf-tiny-llama with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Fischerboot/2b-gguf-tiny-llama:F16
# Run inference directly in the terminal:
llama-cli -hf Fischerboot/2b-gguf-tiny-llama:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Fischerboot/2b-gguf-tiny-llama:F16
# Run inference directly in the terminal:
llama-cli -hf Fischerboot/2b-gguf-tiny-llama:F16

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 Fischerboot/2b-gguf-tiny-llama:F16
# Run inference directly in the terminal:
./llama-cli -hf Fischerboot/2b-gguf-tiny-llama:F16

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 Fischerboot/2b-gguf-tiny-llama:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Fischerboot/2b-gguf-tiny-llama:F16

Use Docker

docker model run hf.co/Fischerboot/2b-gguf-tiny-llama:F16

LM Studio
Jan
Ollama
How to use Fischerboot/2b-gguf-tiny-llama with Ollama:
```
ollama run hf.co/Fischerboot/2b-gguf-tiny-llama:F16
```

Unsloth Studio new

How to use Fischerboot/2b-gguf-tiny-llama 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 Fischerboot/2b-gguf-tiny-llama 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 Fischerboot/2b-gguf-tiny-llama to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Fischerboot/2b-gguf-tiny-llama to start chatting

Docker Model Runner
How to use Fischerboot/2b-gguf-tiny-llama with Docker Model Runner:
```
docker model run hf.co/Fischerboot/2b-gguf-tiny-llama:F16
```

Lemonade

How to use Fischerboot/2b-gguf-tiny-llama with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Fischerboot/2b-gguf-tiny-llama:F16

Run and chat with the model

lemonade run user.2b-gguf-tiny-llama-F16

List all available models

lemonade list

GGUF!

merge

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

SOMEHOW ITS AAAACTUALLY USEABLE

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

concedo/KobbleTinyV2-1.1B

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 16] # angepasst von [0, 24] auf [0, 16]
    model: concedo/KobbleTinyV2-1.1B
- sources:
  - layer_range: [5, 16] # angepasst von [8, 24] auf [5, 16]
    model: concedo/KobbleTinyV2-1.1B
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [5, 16] # angepasst von [8, 24] auf [5, 16]
    model: concedo/KobbleTinyV2-1.1B
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [16, 22] # angepasst von [24, 32] auf [16, 22]
    model: concedo/KobbleTinyV2-1.1B

Downloads last month: 12

GGUF

Model size

2B params

Architecture

llama

Hardware compatibility

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Fischerboot/2b-gguf-tiny-llama

Base model

concedo/KobbleTinyV2-1.1B

Quantized

(3)

this model