Instructions to use Flexan/Blake-XTM-Arc-T0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Flexan/Blake-XTM-Arc-T0-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Flexan/Blake-XTM-Arc-T0-GGUF",
	filename="Blake-XTM-Arc-T0.IQ3_M.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 Flexan/Blake-XTM-Arc-T0-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 Flexan/Blake-XTM-Arc-T0-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Flexan/Blake-XTM-Arc-T0-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 Flexan/Blake-XTM-Arc-T0-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Flexan/Blake-XTM-Arc-T0-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 Flexan/Blake-XTM-Arc-T0-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Flexan/Blake-XTM-Arc-T0-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 Flexan/Blake-XTM-Arc-T0-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Flexan/Blake-XTM-Arc-T0-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Flexan/Blake-XTM-Arc-T0-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Flexan/Blake-XTM-Arc-T0-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Flexan/Blake-XTM-Arc-T0-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Flexan/Blake-XTM-Arc-T0-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Flexan/Blake-XTM-Arc-T0-GGUF:Q4_K_M

Ollama
How to use Flexan/Blake-XTM-Arc-T0-GGUF with Ollama:
```
ollama run hf.co/Flexan/Blake-XTM-Arc-T0-GGUF:Q4_K_M
```

Unsloth Studio

How to use Flexan/Blake-XTM-Arc-T0-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 Flexan/Blake-XTM-Arc-T0-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 Flexan/Blake-XTM-Arc-T0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Flexan/Blake-XTM-Arc-T0-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use Flexan/Blake-XTM-Arc-T0-GGUF with Docker Model Runner:
```
docker model run hf.co/Flexan/Blake-XTM-Arc-T0-GGUF:Q4_K_M
```

Lemonade

How to use Flexan/Blake-XTM-Arc-T0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Flexan/Blake-XTM-Arc-T0-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Blake-XTM-Arc-T0-GGUF-Q4_K_M

List all available models

lemonade list

Blake-XTM-Arc-T0-GGUF / README.md

Flexan

Fix README

b20ce19 verified about 1 year ago

preview code

Raw

History Blame

5.58 kB

	---
	license: cc-by-sa-4.0
	datasets:
	- PJMixers-Dev/dolphin-deepseek-1k-think-1k-response-filtered-ShareGPT
	- Jofthomas/hermes-function-calling-thinking-V1
	language:
	- en
	base_model:
	- arlineka/CatNyanster-7b
	pipeline_tag: text-generation
	---
	# GGUF Files for Blake-XTM-Arc-T0

	These are the GGUF files for [Flexan/Blake-XTM-Arc-T0](https://huggingface.co/Flexan/Blake-XTM-Arc-T0).

	\| GGUF Link \| Quantization \| Description \|
	\| ---- \| ----- \| ----------- \|
	\| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-T0-GGUF/resolve/main/Blake-XTM-Arc-T0.Q2_K.gguf) \| Q2_K \| Lowest quality \|
	\| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-T0-GGUF/resolve/main/Blake-XTM-Arc-T0.IQ3_XS.gguf) \| IQ3_XS \| Integer quant \|
	\| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-T0-GGUF/resolve/main/Blake-XTM-Arc-T0.Q3_K_S.gguf) \| Q3_K_S \| \|
	\| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-T0-GGUF/resolve/main/Blake-XTM-Arc-T0.IQ3_S.gguf) \| IQ3_S \| Integer quant, preferable over Q3_K_S \|
	\| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-T0-GGUF/resolve/main/Blake-XTM-Arc-T0.IQ3_M.gguf) \| IQ3_M \| Integer quant \|
	\| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-T0-GGUF/resolve/main/Blake-XTM-Arc-T0.Q3_K_M.gguf) \| Q3_K_M \| \|
	\| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-T0-GGUF/resolve/main/Blake-XTM-Arc-T0.Q3_K_L.gguf) \| Q3_K_L \| \|
	\| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-T0-GGUF/resolve/main/Blake-XTM-Arc-T0.IQ4_XS.gguf) \| IQ4_XS \| Integer quant \|
	\| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-T0-GGUF/resolve/main/Blake-XTM-Arc-T0.Q4_K_S.gguf) \| Q4_K_S \| Fast with good performance \|
	\| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-T0-GGUF/resolve/main/Blake-XTM-Arc-T0.Q4_K_M.gguf) \| Q4_K_M \| Recommended: Perfect mix of speed and performance \|
	\| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-T0-GGUF/resolve/main/Blake-XTM-Arc-T0.Q5_K_S.gguf) \| Q5_K_S \| \|
	\| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-T0-GGUF/resolve/main/Blake-XTM-Arc-T0.Q5_K_M.gguf) \| Q5_K_M \| \|
	\| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-T0-GGUF/resolve/main/Blake-XTM-Arc-T0.Q6_K.gguf) \| Q6_K \| Very good quality \|
	\| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-T0-GGUF/resolve/main/Blake-XTM-Arc-T0.Q8_0.gguf) \| Q8_0 \| Best quality \|
	\| [Download](https://huggingface.co/Flexan/Blake-XTM-Arc-T0-GGUF/resolve/main/Blake-XTM-Arc-T0.f16.gguf) \| f16 \| Full precision, don't bother; use a quant \|

	# Model Card for Blake-XTM Arc T0

	Blake-XTM Arc T0 is a 7B large language model used for text generation.
	It was trained as a (tool-calling) assistant. This model is a variation of [Blake-XTM-Arc](https://huggingface.co/Flexan/Blake-XTM-Arc) without reasoning.

	## Model Details

	### Model Description

	Blake-XTM Arc T0 is a 7B parameter instruct LLM trained to assist and optionally call a tool. It only supports using one tool per assistant message (no parallel tool calling).
	The model was LoRA fine-tuned with [CatNyanster-7B](https://huggingface.co/arlineka/CatNyanster-7b) as base model, which was fine-tuned on [Mistral-7B](https://huggingface.co/mistralai/Mistral-7B-v0.1).

	### Chat Format

	Blake-XTM Arc T0 uses the ChatML format, e.g.:
	```text
	<\|im_start\|>system
	System message<\|im_end\|>
	<\|im_start\|>user
	User prompt<\|im_end\|>
	<\|im_start\|>assistant
	Assistant response<\|im_end\|>
	```

	### Model Usage

	The assistant response can have the following two formats (the contents are examples and were not generated from the model):
	1. Response:
	```text
	<\|im_start\|>assistant
	Hello! How may I assist you today?<\|im_end\|>
	```
	2. Tool call:
	```text
	<\|im_start\|>assistant
	<\|tool_start\|>{'name': 'find_restaurants', 'arguments': {'city': 'Paris', 'country': 'France'}}<\|tool_end\|><\|im_end\|>
	```

	We recommend using the following system prompts for your situation:
	- Only thought process:
	```text
	You are an advanced AI model.
	```
	- Thought process and tool calling:
	```text
	You are an advanced AI model with tool-calling capabilities.

	If the user asks something and it requires a tool then you should call the tool with the arguments.

	# Tools
	You have access to the following tools:
	[{'type': 'function', 'function': {'name': 'convert_currency', 'description': 'Convert currency from one type to another', 'parameters': {'type': 'object', 'properties': {'amount': {'type': 'number', 'description': 'The amount to be converted'}, 'from_currency': {'type': 'string', 'description': 'The currency to convert from'}, 'to_currency': {'type': 'string', 'description': 'The currency to convert to'}}, 'required': ['amount', 'from_currency', 'to_currency']}}}, {'type': 'function', 'function': {'name': 'get_random_joke', 'description': 'Get a random joke', 'parameters': {'type': 'object', 'properties': {}, 'required': []}}}] <\/tools>Use the following pydantic model json schema for each tool call you will make: {'title': 'FunctionCall', 'type': 'object', 'properties': {'arguments': {'title': 'Arguments', 'type': 'object'}, 'name': {'title': 'Name', 'type': 'string'}}, 'required': ['arguments', 'name']}

	To call a tool, write a JSON object with the name and arguments inside <\|tool_start\|>...<\|tool_end\|>.
	```

	For responding with a tool response, you can send a message as the `tool` user:
	```
	<\|im_start\|>assistant
	<\|tool_start\|>{'name': 'find_restaurants', 'arguments': {'city': 'Paris', 'country': 'France'}}<\|tool_end\|><\|im_end\|>
	<\|im_start\|>tool
	{'restaurants': [{'name': 'A Restaurant Name', 'rating': 4.5}]}<\|im_end\|>
	```