Instructions to use scowen/deepseek-coder-6.7b-vala with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use scowen/deepseek-coder-6.7b-vala with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="scowen/deepseek-coder-6.7b-vala",
	filename="deepseekcoder-6.7B-vala.q8_0.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use scowen/deepseek-coder-6.7b-vala with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf scowen/deepseek-coder-6.7b-vala:Q8_0
# Run inference directly in the terminal:
llama-cli -hf scowen/deepseek-coder-6.7b-vala:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf scowen/deepseek-coder-6.7b-vala:Q8_0
# Run inference directly in the terminal:
llama-cli -hf scowen/deepseek-coder-6.7b-vala:Q8_0

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 scowen/deepseek-coder-6.7b-vala:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf scowen/deepseek-coder-6.7b-vala:Q8_0

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 scowen/deepseek-coder-6.7b-vala:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf scowen/deepseek-coder-6.7b-vala:Q8_0

Use Docker

docker model run hf.co/scowen/deepseek-coder-6.7b-vala:Q8_0

LM Studio
Jan
Ollama
How to use scowen/deepseek-coder-6.7b-vala with Ollama:
```
ollama run hf.co/scowen/deepseek-coder-6.7b-vala:Q8_0
```

Unsloth Studio new

How to use scowen/deepseek-coder-6.7b-vala 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 scowen/deepseek-coder-6.7b-vala 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 scowen/deepseek-coder-6.7b-vala to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for scowen/deepseek-coder-6.7b-vala to start chatting

Docker Model Runner
How to use scowen/deepseek-coder-6.7b-vala with Docker Model Runner:
```
docker model run hf.co/scowen/deepseek-coder-6.7b-vala:Q8_0
```

Lemonade

How to use scowen/deepseek-coder-6.7b-vala with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull scowen/deepseek-coder-6.7b-vala:Q8_0

Run and chat with the model

lemonade run user.deepseek-coder-6.7b-vala-Q8_0

List all available models

lemonade list

deepseek-coder-6.7b-vala

Commit History

Upload deepseekcoder-6.7B-vala5.q8_0.gguf

b7ff02e
verified

scowen commited on Oct 9, 2024

Upload qwen2.5-coder-7B-vala.q8_0.gguf

f50cbae
verified

scowen commited on Oct 1, 2024

Upload deepseekcoder-6.7B-vala4.q8_0.gguf

b7f32a7
verified

scowen commited on May 14, 2024

Upload deepseekcoder-6.7B-vala3.q8_0.gguf

68ba11d
verified

scowen commited on May 7, 2024

added second model, trained on slightly cleaned up data & for an extra epoch

e6baf89

Sam Cowen commited on Apr 30, 2024

new model

c676ac7

Sam Cowen commited on Apr 29, 2024

updated the gguf

0ea208c

Sam Cowen commited on Apr 29, 2024

new version to test

c1b959d

Sam Cowen commited on Apr 28, 2024

new gguf, might fix breakage

7e4c478

Sam Cowen commited on Apr 28, 2024

added v0.1 gguf

7f03f21

Sam Cowen commited on Apr 28, 2024

initial commit

5b62cbc
verified

scowen commited on Apr 28, 2024

Commit History

Upload deepseekcoder-6.7B-vala5.q8_0.gguf b7ff02e verified

Upload qwen2.5-coder-7B-vala.q8_0.gguf f50cbae verified

Upload deepseekcoder-6.7B-vala4.q8_0.gguf b7f32a7 verified

Upload deepseekcoder-6.7B-vala3.q8_0.gguf 68ba11d verified

added second model, trained on slightly cleaned up data & for an extra epoch e6baf89

new model c676ac7

updated the gguf 0ea208c

new version to test c1b959d

new gguf, might fix breakage 7e4c478

added v0.1 gguf 7f03f21

initial commit 5b62cbc verified

Upload deepseekcoder-6.7B-vala5.q8_0.gguf

b7ff02e
verified

Upload qwen2.5-coder-7B-vala.q8_0.gguf

f50cbae
verified

Upload deepseekcoder-6.7B-vala4.q8_0.gguf

b7f32a7
verified

Upload deepseekcoder-6.7B-vala3.q8_0.gguf

68ba11d
verified

added second model, trained on slightly cleaned up data & for an extra epoch

e6baf89

new model

c676ac7

updated the gguf

0ea208c

new version to test

c1b959d

new gguf, might fix breakage

7e4c478

added v0.1 gguf

7f03f21

initial commit

5b62cbc
verified