Instructions to use QuantFactory/llama-3-sqlcoder-8b-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/llama-3-sqlcoder-8b-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/llama-3-sqlcoder-8b-GGUF",
	filename="llama-3-sqlcoder-8b.Q2_K.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use QuantFactory/llama-3-sqlcoder-8b-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/llama-3-sqlcoder-8b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/llama-3-sqlcoder-8b-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/llama-3-sqlcoder-8b-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/llama-3-sqlcoder-8b-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 QuantFactory/llama-3-sqlcoder-8b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/llama-3-sqlcoder-8b-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 QuantFactory/llama-3-sqlcoder-8b-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/llama-3-sqlcoder-8b-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/llama-3-sqlcoder-8b-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/llama-3-sqlcoder-8b-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantFactory/llama-3-sqlcoder-8b-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": "QuantFactory/llama-3-sqlcoder-8b-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantFactory/llama-3-sqlcoder-8b-GGUF:Q4_K_M

Ollama
How to use QuantFactory/llama-3-sqlcoder-8b-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/llama-3-sqlcoder-8b-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/llama-3-sqlcoder-8b-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 QuantFactory/llama-3-sqlcoder-8b-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 QuantFactory/llama-3-sqlcoder-8b-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/llama-3-sqlcoder-8b-GGUF to start chatting

Docker Model Runner
How to use QuantFactory/llama-3-sqlcoder-8b-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/llama-3-sqlcoder-8b-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/llama-3-sqlcoder-8b-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/llama-3-sqlcoder-8b-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.llama-3-sqlcoder-8b-GGUF-Q4_K_M

List all available models

lemonade list

Issue with safetensors and memory

by DevNCT - opened Nov 11, 2024

Discussion

DevNCT

Nov 11, 2024

AttributeError: 'NoneType' object has no attribute 'endswith'

I probably run out of memory or something is wrong with loading
the Q3_K_S model on my laptop with 16GB RAM and 6GB VRAM

model = AutoModelForCausalLM.from_pretrained(
        repo_id,
        gguf_file=filename,
        trust_remote_code=True,
        device_map="auto",
        use_cache=True,
        max_memory={"cpu": f"{ram:.2f}GiB", 0: f"{vram:.2f}GiB"},
        torch_dtype=torch.float
    )


File c:\Users\user\anaconda3\envs\llm\lib\site-packages\transformers\modeling_utils.py:4359, in PreTrainedModel._load_pretrained_model(cls, model, state_dict, loaded_keys, resolved_archive_file, pretrained_model_name_or_path, ignore_mismatched_sizes, sharded_metadata, _fast_init, low_cpu_mem_usage, device_map, offload_folder, offload_state_dict, dtype, hf_quantizer, keep_in_fp32_modules, gguf_path, weights_only)
   4355 if device_map is not None and "disk" in device_map.values():
   4356     archive_file = (
   4357         resolved_archive_file[0] if isinstance(resolved_archive_file, (list, tuple)) else resolved_archive_file
   4358     )
-> 4359     is_safetensors = archive_file.endswith(".safetensors")
   4360     if offload_folder is None and not is_safetensors:
   4361         raise ValueError(
   4362             "The current `device_map` had weights offloaded to the disk. Please provide an `offload_folder`"
   4363             " for them. Alternatively, make sure you have `safetensors` installed if the model you are using"
   4364             " offers the weights in this format."
   4365         )

AttributeError: 'NoneType' object has no attribute 'endswith'

Any idea?

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