Instructions to use basavyr/bitnet_b1_58-3B_quant_gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use basavyr/bitnet_b1_58-3B_quant_gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="basavyr/bitnet_b1_58-3B_quant_gguf",
	filename="model_f16.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 basavyr/bitnet_b1_58-3B_quant_gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf basavyr/bitnet_b1_58-3B_quant_gguf:F16
# Run inference directly in the terminal:
llama-cli -hf basavyr/bitnet_b1_58-3B_quant_gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf basavyr/bitnet_b1_58-3B_quant_gguf:F16
# Run inference directly in the terminal:
llama-cli -hf basavyr/bitnet_b1_58-3B_quant_gguf: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 basavyr/bitnet_b1_58-3B_quant_gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf basavyr/bitnet_b1_58-3B_quant_gguf: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 basavyr/bitnet_b1_58-3B_quant_gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf basavyr/bitnet_b1_58-3B_quant_gguf:F16

Use Docker

docker model run hf.co/basavyr/bitnet_b1_58-3B_quant_gguf:F16

LM Studio
Jan
Ollama
How to use basavyr/bitnet_b1_58-3B_quant_gguf with Ollama:
```
ollama run hf.co/basavyr/bitnet_b1_58-3B_quant_gguf:F16
```

Unsloth Studio

How to use basavyr/bitnet_b1_58-3B_quant_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 basavyr/bitnet_b1_58-3B_quant_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 basavyr/bitnet_b1_58-3B_quant_gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for basavyr/bitnet_b1_58-3B_quant_gguf to start chatting

Docker Model Runner
How to use basavyr/bitnet_b1_58-3B_quant_gguf with Docker Model Runner:
```
docker model run hf.co/basavyr/bitnet_b1_58-3B_quant_gguf:F16
```

Lemonade

How to use basavyr/bitnet_b1_58-3B_quant_gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull basavyr/bitnet_b1_58-3B_quant_gguf:F16

Run and chat with the model

lemonade run user.bitnet_b1_58-3B_quant_gguf-F16

List all available models

lemonade list

basavyr commited on Aug 21, 2024

Commit

c1d6b44

verified ·

1 Parent(s): fa3db3d

add full f16 gguf and quantized versions

Browse files

Adds the fully `f16` precision model converted to `.gguf` and the two quantized versions (i.e., the `Q1_3` and `Q2_2`).

Files changed (4) hide show

.gitattributes +3 -0
model_f16.gguf +3 -0
model_quant_Q1_3.gguf +3 -0
model_quant_Q2_2.gguf +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model_f16.gguf filter=lfs diff=lfs merge=lfs -text
+model_quant_Q1_3.gguf filter=lfs diff=lfs merge=lfs -text
+model_quant_Q2_2.gguf filter=lfs diff=lfs merge=lfs -text

model_f16.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7fc35e25de3315d5c5f7e2f8e4d09af4cfd84c66b12a9927c64d9640195d935c
+size 6650487168

model_quant_Q1_3.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:93397569b7562df531d823defc54749ba81046568f3ff29c3db87be41f9c81b4
+size 765841184

model_quant_Q2_2.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d0b04449fabec0ef2ce39fb311c4e203e50f06a2e81f3d6764f7c5869fb24a38
+size 916849184