Instructions to use viplismism/deepseek-coder-6.7b-fim-reth-v1-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 viplismism/deepseek-coder-6.7b-fim-reth-v1-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 viplismism/deepseek-coder-6.7b-fim-reth-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf viplismism/deepseek-coder-6.7b-fim-reth-v1-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 viplismism/deepseek-coder-6.7b-fim-reth-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf viplismism/deepseek-coder-6.7b-fim-reth-v1-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 viplismism/deepseek-coder-6.7b-fim-reth-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf viplismism/deepseek-coder-6.7b-fim-reth-v1-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 viplismism/deepseek-coder-6.7b-fim-reth-v1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf viplismism/deepseek-coder-6.7b-fim-reth-v1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/viplismism/deepseek-coder-6.7b-fim-reth-v1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use viplismism/deepseek-coder-6.7b-fim-reth-v1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "viplismism/deepseek-coder-6.7b-fim-reth-v1-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "viplismism/deepseek-coder-6.7b-fim-reth-v1-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/viplismism/deepseek-coder-6.7b-fim-reth-v1-GGUF:Q4_K_M

Ollama
How to use viplismism/deepseek-coder-6.7b-fim-reth-v1-GGUF with Ollama:
```
ollama run hf.co/viplismism/deepseek-coder-6.7b-fim-reth-v1-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use viplismism/deepseek-coder-6.7b-fim-reth-v1-GGUF with Docker Model Runner:
```
docker model run hf.co/viplismism/deepseek-coder-6.7b-fim-reth-v1-GGUF:Q4_K_M
```

Lemonade

How to use viplismism/deepseek-coder-6.7b-fim-reth-v1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull viplismism/deepseek-coder-6.7b-fim-reth-v1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.deepseek-coder-6.7b-fim-reth-v1-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

deepseek-coder-6.7b-fim-reth-v1 — GGUF

GGUF quantizations of the deepseek-coder-6.7b-fim-reth-v1 LoRA adapter merged into DeepSeek-Coder-6.7B base. Fine-tuned for Fill-in-the-Middle (FIM) code completion on the reth Rust codebase.

Files

File	Quant	Size	Notes
`fim-deepseek-6.7b-reth-v1.q4_k_m.gguf`	Q4_K_M	4.08 GB	Fast, small — good default for laptops / Ollama
`fim-deepseek-6.7b-reth-v1.q8_0.gguf`	Q8_0	7.16 GB	Near-lossless quality

FIM prompt format

DeepSeek FIM tokens — completion is generated after <｜fim▁end｜>:

<｜fim▁begin｜>{prefix}<｜fim▁hole｜>{suffix}<｜fim▁end｜>

Usage

llama.cpp

llama-cli -m fim-deepseek-6.7b-reth-v1.q4_k_m.gguf \
  -p $'<｜fim▁begin｜>fn add(a: i32, b: i32) -> i32 {\n    <｜fim▁hole｜>\n}<｜fim▁end｜>' \
  -n 64 --temp 0.2 -no-cnv

Ollama

FROM ./fim-deepseek-6.7b-reth-v1.q4_k_m.gguf
TEMPLATE """{{ .Prompt }}"""
PARAMETER temperature 0.2
PARAMETER num_predict 128
PARAMETER num_ctx 4096
PARAMETER stop "<｜fim▁begin｜>"
PARAMETER stop "<｜fim▁hole｜>"
PARAMETER stop "<｜fim▁end｜>"
PARAMETER stop "<｜end▁of▁sentence｜>"

ollama create fim-deepseek-reth -f Modelfile

Evaluation (parent adapter, 200 held-out reth samples)

Metric	Tuned	Base	Δ
pass@1 (exact match)	31.0%	13.5%	+17.5 pts (2.3×)
Edit similarity	0.650	0.453	+0.197
BLEU	0.459	0.294	+0.165

GGUF-verified on real held-out reth code

These GGUF files were independently re-benchmarked via llama.cpp (greedy, temp 0) on 200 real held-out reth FIM samples — generated completion vs. the actual reth code:

Model	pass@1	edit-sim	size	speed (M4 Pro)
q8_0 (tuned)	18.0%	0.575	6.7 GB	~23 tok/s
q4_k_m (tuned)	16.0%	0.559	3.8 GB	~50 tok/s
base (q8_0)	7.5%	0.442	—	—

→ tuned is ~2.4× (q8) / ~2.1× (q4) the base model's pass@1 on reth — reproducing the adapter's reported lift end-to-end in GGUF. q4_k_m keeps ~90% of the gain at half the size; recommended default for laptops.

License

Governed by the DeepSeek License Agreement for the base model.

Downloads last month: 58

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

8-bit

Model tree for viplismism/deepseek-coder-6.7b-fim-reth-v1-GGUF

Base model

deepseek-ai/deepseek-coder-6.7b-base

Quantized

(31)

this model