Instructions to use tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF", dtype="auto")

llama-cpp-python

How to use tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF",
	filename="tiny-random-LlamaForCausalLM-untied-Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF:Q2_K

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF:Q2_K
# Run inference directly in the terminal:
llama-cli -hf tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF:Q2_K

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 tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF:Q2_K
# Run inference directly in the terminal:
./llama-cli -hf tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF:Q2_K

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 tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF:Q2_K
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF:Q2_K

Use Docker

docker model run hf.co/tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF:Q2_K

LM Studio
Jan
Ollama
How to use tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF with Ollama:
```
ollama run hf.co/tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF:Q2_K
```

Unsloth Studio

How to use tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-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 tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-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 tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF to start chatting

Docker Model Runner
How to use tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF with Docker Model Runner:
```
docker model run hf.co/tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF:Q2_K
```

Lemonade

How to use tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tensorblock/onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF:Q2_K

Run and chat with the model

lemonade run user.onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF-Q2_K

List all available models

lemonade list

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1879a7fe7d65aa2537797832627e77dd16b2f229418997d4533486172d132418
-size 14501408

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:32864bbf0027cde027cf12cc18ccde8d80d80c1779f9f3738d11b7222401e981
-size 14500064

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1da6604d8871adf80523b9c52e88d19a8160fc7eb28ff2a25b1a63c81974e23a
-size 14500064

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a00a30a30ce75ae62208a444f66bdcb41e72e14e12cd87581776ca919ddabfb6
-size 15016352

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0c36cd15448eab9eeecde68e6433748ddae8221440490740d7e90c3316a54fba
-size 15015456

tensorblock
/

onnx-internal-testing_tiny-random-LlamaForCausalLM-untied-GGUF

Keep Q2_K/Q3_K_M gguf only