Instructions to use bartowski/35b-beta-long-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/35b-beta-long-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bartowski/35b-beta-long-GGUF",
	filename="35b-beta-long-IQ1_M.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 bartowski/35b-beta-long-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 bartowski/35b-beta-long-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/35b-beta-long-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 bartowski/35b-beta-long-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/35b-beta-long-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 bartowski/35b-beta-long-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartowski/35b-beta-long-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 bartowski/35b-beta-long-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartowski/35b-beta-long-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/35b-beta-long-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bartowski/35b-beta-long-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/35b-beta-long-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": "bartowski/35b-beta-long-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bartowski/35b-beta-long-GGUF:Q4_K_M

Ollama
How to use bartowski/35b-beta-long-GGUF with Ollama:
```
ollama run hf.co/bartowski/35b-beta-long-GGUF:Q4_K_M
```

Unsloth Studio

How to use bartowski/35b-beta-long-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 bartowski/35b-beta-long-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 bartowski/35b-beta-long-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bartowski/35b-beta-long-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use bartowski/35b-beta-long-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/35b-beta-long-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/35b-beta-long-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/35b-beta-long-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.35b-beta-long-GGUF-Q4_K_M

List all available models

lemonade list

Anyone able to get this working on koboldcpp?

by lemon07r - opened May 7, 2024

Discussion

lemon07r

May 7, 2024

Crashes when I try to load the model, same issue with quantfactory's quant of this model too. Maybe koboldcpp doesnt have the required upstream merges from llamacpp yet? Wondering if someone can confirm. I tested lost ruins koboldcpp with openblas and vulkan both, and yellowroses hipblas fork, neither can load this model. Tested with Q4k_M

Elfrino

May 7, 2024

Yes, I'm getting the same crash. We'll have to wait until KoboldCPP updates this change:

https://github.com/LostRuins/koboldcpp/commit/889bdd76866ea31a7625ec2dcea63ff469f3e981

lejunzhu

May 7, 2024

If you build it from source code, you can use the "concedo_experimental" branch. As of now, it has PR #7063 from upstream which is the new tokenizer.

bartowski

Owner May 7, 2024

Thanks for looking into this, yeah another one of those "update your backend" changes

Elfrino

May 11, 2024

Crashes when I try to load the model, same issue with quantfactory's quant of this model too. Maybe koboldcpp doesnt have the required upstream merges from llamacpp yet? Wondering if someone can confirm. I tested lost ruins koboldcpp with openblas and vulkan both, and yellowroses hipblas fork, neither can load this model. Tested with Q4k_M

Hey just tested with the latest Kobold release, working great!:

https://github.com/LostRuins/koboldcpp/releases

lemon07r

May 12, 2024

•

edited May 12, 2024

Thanks for looking into this, yeah another one of those "update your backend" changes

Working great in the latest kcpp release. The iquant versions will work for cpu only inference but wont work for me when I do any sort of gpu offloading, clblas. vulkan or otherwise on my 6900 xt. I tried iq4 and iq3 quants, they work with clblast but not vulkan when I try to offload any amount.

EDIT - Here's the last message I see on screen before it crashes:

GGML_ASSERT: ggml-vulkan.cpp:2940: !qx_needs_dequant || to_fp16_vk_0 != nullptr

bartowski

Owner May 12, 2024

That's expected, you can see the support table here:

https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix

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