DeepSeek-Coder-V2-Lite-Instruct-GGUF

Instructions to use lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-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 lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-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 lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-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 lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-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 lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-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 lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-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": "lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q4_K_M

Ollama
How to use lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF with Ollama:
```
ollama run hf.co/lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lmstudio-community/DeepSeek-Coder-V2-Lite-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.DeepSeek-Coder-V2-Lite-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

LM studio Loading error

by Vezora - opened Jun 19, 2024

Discussion

Vezora

Jun 19, 2024

•

edited Jun 19, 2024

Does the latest release of LM studio 0.2.25 support this model? I just downloaded the model in LM Studio (latest release 0.2.25 on Windows) and when I hover over the model to load it says "this model architecture is not supported". And when i try to load it, it gives me an error.

"(Exit code: -1073740791). Unknown error. Try a different model and/or config."
{
"memory": {
"ram_capacity": "127.90 GB",
"ram_unused": "97.96 GB"
},
"gpu": {
"gpu_names": [
"NVIDIA GeForce RTX 3090"
],
"vram_recommended_capacity": "24.00 GB",
"vram_unused": "22.76 GB"
},
"os": {
"platform": "win32",
"version": "10.0.22631"
},
"app": {
"version": "0.2.25",
"downloadsDir": "C:\Users\bobni\.cache\lm-studio\models"
},
"model": {}
}

xavieranguera

Jun 19, 2024

Same here. I am getting the following error:
"llama.cpp error: 'error loading model architecture: unknown model architecture: 'deepseek2''"

and diagnostic info:
{
"memory": {
"ram_capacity": "96.00 GB",
"ram_unused": "10.00 GB"
},
"gpu": {
"gpu_names": [
"Apple Silicon"
],
"vram_recommended_capacity": "72.00 GB",
"vram_unused": "7.65 GB"
},
"os": {
"platform": "darwin",
"version": "14.4"
},
"app": {
"version": "0.2.24",
"downloadsDir": "/Users/xam/.cache/lm-studio/models"
},
"model": {}
}

bartowski

Jun 19, 2024

try disabling flash attention, i'm not sure why it's being listed as an unknown architecture

xavieranguera

Jun 19, 2024

Thanks for your support. In my case I might be missing something, but flash attention seems to already be disabled by default. See the image:

bartowski

Jun 19, 2024

oh @xavieranguera you might need an update as well to 0.2.25

xavieranguera

Jun 19, 2024

Ok, this solved the issue.
Note for others: while on the app the latest version available (when checking for updates) is 0.2.24, on the website the new version is already available.
Thanks @bartowski !

Vezora

Jun 20, 2024

Thank you this fixed the problem, and yeah it is strangely showing unsupported model, but with FA2 turned off it loads :) @bartowski

Vezora changed discussion status to closed Jun 20, 2024

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