Instructions to use microsoft/bitnet-b1.58-2B-4T-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/bitnet-b1.58-2B-4T-gguf with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="microsoft/bitnet-b1.58-2B-4T-gguf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("microsoft/bitnet-b1.58-2B-4T-gguf", dtype="auto")

llama-cpp-python

How to use microsoft/bitnet-b1.58-2B-4T-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="microsoft/bitnet-b1.58-2B-4T-gguf",
	filename="ggml-model-i2_s.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use microsoft/bitnet-b1.58-2B-4T-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf microsoft/bitnet-b1.58-2B-4T-gguf
# Run inference directly in the terminal:
llama-cli -hf microsoft/bitnet-b1.58-2B-4T-gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf microsoft/bitnet-b1.58-2B-4T-gguf
# Run inference directly in the terminal:
llama-cli -hf microsoft/bitnet-b1.58-2B-4T-gguf

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 microsoft/bitnet-b1.58-2B-4T-gguf
# Run inference directly in the terminal:
./llama-cli -hf microsoft/bitnet-b1.58-2B-4T-gguf

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 microsoft/bitnet-b1.58-2B-4T-gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf microsoft/bitnet-b1.58-2B-4T-gguf

Use Docker

docker model run hf.co/microsoft/bitnet-b1.58-2B-4T-gguf

LM Studio
Jan

vLLM

How to use microsoft/bitnet-b1.58-2B-4T-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/bitnet-b1.58-2B-4T-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/bitnet-b1.58-2B-4T-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/microsoft/bitnet-b1.58-2B-4T-gguf

SGLang

How to use microsoft/bitnet-b1.58-2B-4T-gguf with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "microsoft/bitnet-b1.58-2B-4T-gguf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/bitnet-b1.58-2B-4T-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "microsoft/bitnet-b1.58-2B-4T-gguf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "microsoft/bitnet-b1.58-2B-4T-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use microsoft/bitnet-b1.58-2B-4T-gguf with Ollama:
```
ollama run hf.co/microsoft/bitnet-b1.58-2B-4T-gguf
```

Unsloth Studio

How to use microsoft/bitnet-b1.58-2B-4T-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 microsoft/bitnet-b1.58-2B-4T-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 microsoft/bitnet-b1.58-2B-4T-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for microsoft/bitnet-b1.58-2B-4T-gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use microsoft/bitnet-b1.58-2B-4T-gguf with Docker Model Runner:
```
docker model run hf.co/microsoft/bitnet-b1.58-2B-4T-gguf
```

Lemonade

How to use microsoft/bitnet-b1.58-2B-4T-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull microsoft/bitnet-b1.58-2B-4T-gguf

Run and chat with the model

lemonade run user.bitnet-b1.58-2B-4T-gguf-{{QUANT_TAG}}

List all available models

lemonade list

llama_cpp_python: gguf_init_from_file_impl: failed to read tensor info

#14

by miscw - opened Apr 29, 2025

Discussion

miscw

Apr 29, 2025

.../Python/ai_test $ python main.py                                       gguf_init_from_file_impl: tensor 'blk.0.ffn_down.weight' of type 36 (TYPE_IQ4_NL_4_4 REMOVED, use IQ4_NL with runtime repacking) has 6912 elements per row, not a multiple of block size (0)                                  gguf_init_from_file_impl: failed to read tensor info                      llama_model_load: error loading model: llama_model_loader: failed to load model from /data/data/com.termux/files/home/.cache/huggingface/hub/models--microsoft--bitnet-b1.58-2B-4T-gguf/snapshots/0f9a32c738e25e05b399303a54e59c9826a35b36/./ggml-model-i2_s.gguf                                                                                                                 llama_model_load_from_file_impl: failed to load model                     Traceback (most recent call last):                                          File "/storage/emulated/0/Python/ai_test/main.py", line 4, in <module>      llm = Llama.from_pretrained(                                                    ^^^^^^^^^^^^^^^^^^^^^^                                            File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/llama_cpp/llama.py", line 2357, in from_pretrained                                 return cls(                                                                      ^^^^                                                             File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/llama_cpp/llama.py", line 372, in __init__                                         internals.LlamaModel(                                                   File "/data/data/com.termux/files/usr/lib/python3.12/site-packages/llama_cpp/_internals.py", line 56, in __init__                                     raise ValueError(f"Failed to load model from file: {path_model}")     ValueError: Failed to load model from file: /data/data/com.termux/files/home/.cache/huggingface/hub/models--microsoft--bitnet-b1.58-2B-4T-gguf/snapshots/0f9a32c738e25e05b399303a54e59c9826a35b36/./ggml-model-i2_s.gguf      .../Python/ai_test $

Python snippet:

from llama_cpp import Llama

# Load the model from Hugging Face repo (auto-downloads .gguf)
llm = Llama.from_pretrained(
    repo_id="microsoft/bitnet-b1.58-2B-4T-gguf",
    filename="ggml-model-i2_s.gguf",
    n_ctx=512,
    verbose=False,
)

# ANSI styles
GREEN = "\033[92m"
MAGENTA = "\033[95m"
RESET = "\033[0m"

# Chat loop
print(f"{MAGENTA}BitNet 2B ChatBot Ready. Type 'exit' to quit.{RESET}")
while True:
    try:
        user_input = input(f"{GREEN}You > {RESET}").strip()
        if user_input.lower() in ["exit", "quit"]: break

        output = llm(f"User: {user_input}\nAssistant:", max_tokens=200)
        reply = output["choices"][0]["text"].strip()
        print(f"{MAGENTA}Bot > {reply}{RESET}\n")

    except KeyboardInterrupt:
        break

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment