Instructions to use Hob-forge/BAR-5x7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Hob-forge/BAR-5x7B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Hob-forge/BAR-5x7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Hob-forge/BAR-5x7B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Hob-forge/BAR-5x7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Hob-forge/BAR-5x7B-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 Hob-forge/BAR-5x7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Hob-forge/BAR-5x7B-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 Hob-forge/BAR-5x7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Hob-forge/BAR-5x7B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Hob-forge/BAR-5x7B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Hob-forge/BAR-5x7B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hob-forge/BAR-5x7B-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": "Hob-forge/BAR-5x7B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Hob-forge/BAR-5x7B-GGUF:Q4_K_M

Ollama
How to use Hob-forge/BAR-5x7B-GGUF with Ollama:
```
ollama run hf.co/Hob-forge/BAR-5x7B-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use Hob-forge/BAR-5x7B-GGUF with Docker Model Runner:
```
docker model run hf.co/Hob-forge/BAR-5x7B-GGUF:Q4_K_M
```

Lemonade

How to use Hob-forge/BAR-5x7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Hob-forge/BAR-5x7B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.BAR-5x7B-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

RhinoWithAcape commited on Apr 30

Commit

729c660

verified ·

1 Parent(s): 1b3441b

Update build instructions

Browse files

Files changed (1) hide show

README.md +2 -5

README.md CHANGED Viewed

@@ -25,12 +25,11 @@ This is the **first GGUF conversion** of [`allenai/BAR-5x7B`](https://huggingfac
 ## ⚠ Requires patched llama.cpp
-The FlexOlmo architecture is **not yet supported in upstream `llama.cpp`**. The support PR is open at:
-- **PR:** https://github.com/ggml-org/llama.cpp (search for "FlexOlmo")
 - **Fork:** https://github.com/Seraphiel102/llama.cpp/tree/flex-olmo-pr-clean
-**Build from the support branch:**
 ```bash
 git clone https://github.com/Seraphiel102/llama.cpp.git
@@ -40,8 +39,6 @@ cmake -B build -DGGML_CUDA=OFF
 cmake --build build -j --target llama-cli llama-quantize llama-completion
 ```
-Once upstream PR lands, any standard llama.cpp / Ollama install will work directly.
 ## What FlexOlmo is
 Per [`transformers.models.flex_olmo`](https://github.com/huggingface/transformers/tree/main/src/transformers/models/flex_olmo), FlexOlmoDecoderLayer is **Olmo2's hybrid post-norm decoder layer with the dense FFN swapped for OlmoE-style top-k MoE routing**. Specifically:

 ## ⚠ Requires patched llama.cpp
+The FlexOlmo architecture is **not yet supported in upstream `llama.cpp`**. To run this GGUF use the FlexOlmo support fork:
 - **Fork:** https://github.com/Seraphiel102/llama.cpp/tree/flex-olmo-pr-clean
+**Build from the fork:**
 ```bash
 git clone https://github.com/Seraphiel102/llama.cpp.git
 cmake --build build -j --target llama-cli llama-quantize llama-completion
 ```
 ## What FlexOlmo is
 Per [`transformers.models.flex_olmo`](https://github.com/huggingface/transformers/tree/main/src/transformers/models/flex_olmo), FlexOlmoDecoderLayer is **Olmo2's hybrid post-norm decoder layer with the dense FFN swapped for OlmoE-style top-k MoE routing**. Specifically: