Text Generation
GGUF
Safetensors
English
Turkish
plc
iec-61131-3
structured-text
code-generation
ollama
mikrodev
ALB
AdvanceLogicBuilder
MikrodevLogicStudio
advance-logic-builder
mikrodev-logicstudio
gemma
conversational
Instructions to use Mikrodev/stcoder-gemma4-12b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Mikrodev/stcoder-gemma4-12b-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 Mikrodev/stcoder-gemma4-12b-gguf:Q4_K_M # Run inference directly in the terminal: llama cli -hf Mikrodev/stcoder-gemma4-12b-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 Mikrodev/stcoder-gemma4-12b-gguf:Q4_K_M # Run inference directly in the terminal: llama cli -hf Mikrodev/stcoder-gemma4-12b-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 Mikrodev/stcoder-gemma4-12b-gguf:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Mikrodev/stcoder-gemma4-12b-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 Mikrodev/stcoder-gemma4-12b-gguf:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Mikrodev/stcoder-gemma4-12b-gguf:Q4_K_M
Use Docker
docker model run hf.co/Mikrodev/stcoder-gemma4-12b-gguf:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use Mikrodev/stcoder-gemma4-12b-gguf with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Mikrodev/stcoder-gemma4-12b-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": "Mikrodev/stcoder-gemma4-12b-gguf", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Mikrodev/stcoder-gemma4-12b-gguf:Q4_K_M
- Ollama
How to use Mikrodev/stcoder-gemma4-12b-gguf with Ollama:
ollama run hf.co/Mikrodev/stcoder-gemma4-12b-gguf:Q4_K_M
- Unsloth Studio
How to use Mikrodev/stcoder-gemma4-12b-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 Mikrodev/stcoder-gemma4-12b-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 Mikrodev/stcoder-gemma4-12b-gguf to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Mikrodev/stcoder-gemma4-12b-gguf to start chatting
- Docker Model Runner
How to use Mikrodev/stcoder-gemma4-12b-gguf with Docker Model Runner:
docker model run hf.co/Mikrodev/stcoder-gemma4-12b-gguf:Q4_K_M
- Lemonade
How to use Mikrodev/stcoder-gemma4-12b-gguf with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Mikrodev/stcoder-gemma4-12b-gguf:Q4_K_M
Run and chat with the model
lemonade run user.stcoder-gemma4-12b-gguf-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Upload Modelfile with huggingface_hub
Browse files
Modelfile
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# stcoder-gemma4-12b - Ollama Modelfile (one file for every quantisation of this model)
|
| 2 |
+
# Repo: https://huggingface.co/Mikrodev/stcoder-gemma4-12b-gguf
|
| 3 |
+
#
|
| 4 |
+
# The FROM line below points at the recommended Q8_0 build (gemma4_12b-tc.q8_0.gguf).
|
| 5 |
+
# If you downloaded a DIFFERENT quantisation, change that one line to its filename:
|
| 6 |
+
# FROM ./gemma4_12b-tc.q6_k.gguf (Q6_K, 9.11 GiB)
|
| 7 |
+
# FROM ./gemma4_12b-tc.q4_k_m.gguf (Q4_K_M, 6.87 GiB)
|
| 8 |
+
#
|
| 9 |
+
# 1) put this file next to the GGUF you downloaded (and edit FROM if needed)
|
| 10 |
+
# 2) ollama create stcoder-gemma4-12b:<quant> -f Modelfile e.g. ollama create stcoder-gemma4-12b:q8_0 -f Modelfile
|
| 11 |
+
# 3) ollama run stcoder-gemma4-12b:<quant> "Motor starts 5 seconds after the start button; stop and E-stop drop it."
|
| 12 |
+
#
|
| 13 |
+
# Requires Ollama 0.5 or newer.
|
| 14 |
+
# num_ctx 8192 matches the sequence length this model was fine-tuned at.
|
| 15 |
+
# Published numbers were measured greedily (temperature 0, seed 42) at num_ctx 16384 / num_predict 8192. The values below are the interactive defaults; match those to reproduce the numbers exactly.
|
| 16 |
+
# Gemma turn format, not ChatML. Do not mix the two.
|
| 17 |
+
# Q8_0 crashed on a 16 GiB card in our own testing at this context size; drop to Q6_K if you hit an out-of-memory or a load failure.
|
| 18 |
+
# Q8_0: crashed on a 16 GiB card in our own testing at 8k context - if that happens, drop to Q6_K.
|
| 19 |
+
|
| 20 |
+
FROM ./gemma4_12b-tc.q8_0.gguf
|
| 21 |
+
|
| 22 |
+
TEMPLATE """<start_of_turn>user
|
| 23 |
+
{{ if .System }}{{ .System }}
|
| 24 |
+
|
| 25 |
+
{{ end }}{{ .Prompt }}<end_of_turn>
|
| 26 |
+
<start_of_turn>model
|
| 27 |
+
{{ .Response }}<end_of_turn>
|
| 28 |
+
"""
|
| 29 |
+
|
| 30 |
+
PARAMETER stop "<end_of_turn>"
|
| 31 |
+
PARAMETER stop "<start_of_turn>"
|
| 32 |
+
|
| 33 |
+
PARAMETER temperature 0.2
|
| 34 |
+
PARAMETER top_p 0.95
|
| 35 |
+
PARAMETER top_k 20
|
| 36 |
+
PARAMETER min_p 0.0
|
| 37 |
+
PARAMETER repeat_penalty 1.0
|
| 38 |
+
PARAMETER num_ctx 8192
|
| 39 |
+
PARAMETER num_predict 2048
|
| 40 |
+
|
| 41 |
+
SYSTEM """You are STCoder, a conversational coding assistant for the Mikrodev LogicStudio IDE and an expert in IEC 61131-3 Structured Text. You help the user design and understand PLC logic entirely through chat — you do not call tools. Answer the user's message directly and helpfully, and explain briefly when it aids understanding. When the user asks for logic, provide correct, body-only Structured Text in the Mikrodev dialect inside an ```iecst code block, then remind the user to compile it in the IDE.
|
| 42 |
+
|
| 43 |
+
Mikrodev Structured Text rules (always follow):
|
| 44 |
+
- UPPERCASE keywords (IF/THEN/VAR/END_IF); lowercase or mixed case is forbidden
|
| 45 |
+
- Close every block: END_IF / END_FOR / END_CASE / END_WHILE / END_REPEAT; every statement ends with `;`
|
| 46 |
+
- Positional function-block calls only — TON(bStart, 5000); named parameters (IN :=, PT :=) and `=>` are forbidden
|
| 47 |
+
- Read FB outputs via dot notation: bOut := tDelay.Q;
|
| 48 |
+
- Body only — never write POU wrappers (PROGRAM / FUNCTION_BLOCK ... END_*)
|
| 49 |
+
- No TIME literals (T#5s) — use INT milliseconds with VAR CONSTANT (5000 = 5 s, 500 = 500 ms)
|
| 50 |
+
- `:=` assign, `=` compare, `<>` not-equal; AND / OR / NOT / XOR / MOD
|
| 51 |
+
- ENUM and 1-D ARRAY allowed; STRING, STRUCT, TYPE alias, FUNCTION definitions, POINTER, pragmas, VAR_GLOBAL / VAR_EXTERNAL / VAR RETAIN / VAR PERSISTENT are forbidden
|
| 52 |
+
- No explicit casts (INT_TO_REAL, TO_INT) and no MIN / MAX / LIMIT / SEL / `**`
|
| 53 |
+
- No direct addresses (%IX, %QW) — use symbolic names
|
| 54 |
+
- No `/* */` C-style comments — use (* *) or //
|
| 55 |
+
- Do not nest comments — write each comment once, e.g. (* text *), never (* (* text *) *)
|
| 56 |
+
- Identifiers are ASCII; keywords, identifiers and all code comments are written in English; only your conversational prose may match the user's language
|
| 57 |
+
- Politely decline non-PLC requests
|
| 58 |
+
|
| 59 |
+
Keep answers focused and practical."""
|