Instructions to use deepforce/deepforce-coder-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepforce/deepforce-coder-v2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="deepforce/deepforce-coder-v2",
	filename="deepforce-coder-v2-q4_k_m.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use deepforce/deepforce-coder-v2 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 deepforce/deepforce-coder-v2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf deepforce/deepforce-coder-v2:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf deepforce/deepforce-coder-v2:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf deepforce/deepforce-coder-v2: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 deepforce/deepforce-coder-v2:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf deepforce/deepforce-coder-v2: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 deepforce/deepforce-coder-v2:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf deepforce/deepforce-coder-v2:Q4_K_M

Use Docker

docker model run hf.co/deepforce/deepforce-coder-v2:Q4_K_M

LM Studio
Jan

vLLM

How to use deepforce/deepforce-coder-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepforce/deepforce-coder-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepforce/deepforce-coder-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deepforce/deepforce-coder-v2:Q4_K_M

Ollama
How to use deepforce/deepforce-coder-v2 with Ollama:
```
ollama run hf.co/deepforce/deepforce-coder-v2:Q4_K_M
```

Unsloth Studio

How to use deepforce/deepforce-coder-v2 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 deepforce/deepforce-coder-v2 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 deepforce/deepforce-coder-v2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for deepforce/deepforce-coder-v2 to start chatting

How to use deepforce/deepforce-coder-v2 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf deepforce/deepforce-coder-v2:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "deepforce/deepforce-coder-v2:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use deepforce/deepforce-coder-v2 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf deepforce/deepforce-coder-v2:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default deepforce/deepforce-coder-v2:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use deepforce/deepforce-coder-v2 with Docker Model Runner:
```
docker model run hf.co/deepforce/deepforce-coder-v2:Q4_K_M
```

Lemonade

How to use deepforce/deepforce-coder-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull deepforce/deepforce-coder-v2:Q4_K_M

Run and chat with the model

lemonade run user.deepforce-coder-v2-Q4_K_M

List all available models

lemonade list

deepforce-coder-v2 / README.md

deepforce

Upload README.md with huggingface_hub

9ca1276 verified about 12 hours ago

preview code

Raw

History Blame Contribute Delete

4.67 kB

metadata

language:
  - en
license: apache-2.0
base_model: Qwen/Qwen2.5-Coder-3B-Instruct
tags:
  - salesforce
  - apex
  - lwc
  - lightning-web-components
  - code
  - fine-tuned
  - gguf
  - unsloth
pipeline_tag: text-generation

DeepForce Coder v2

A Salesforce-specialized AI coding assistant fine-tuned on Qwen 2.5 Coder 3B. Built specifically for Salesforce developers to generate, debug, review, and refactor Apex code and Lightning Web Components following enterprise best practices.

✅ v2 improvements over v1:

Fixed hallucinated Apex APIs

Simple requests now generate clean minimal code

Improved recursion guard patterns

Custom weighted adapter merge for better task balance

specialized adapters trained independently

Capabilities

Task	Description
Apex Generation	Write production-ready Apex classes, triggers, batch, scheduled, queueable
LWC Development	Create Lightning Web Components with SLDS conventions
Code Debug	Identify bugs with severity ratings and corrections
Code Review	Review code against Salesforce best practices
Refactoring	Simplify over-engineered code while preserving security
Test Classes	Generate comprehensive Apex test classes
Recursion Guards	Correct Apex recursion guard patterns
Simple Apex	Clean minimal Apex for simple requirements

Best Practices Enforced

with sharing on all classes
WITH USER_MODE on all SOQL queries
Security.stripInaccessible() before DML
try-catch on all DML and callouts
Database.update/insert(records, false) for bulk DML
No SOQL or DML inside loops
Bulkified trigger handlers with recursion guards
Static Set recursion guard pattern

Model Details

Base model: Qwen/Qwen2.5-Coder-3B-Instruct
Fine-tuning: specialized LoRA adapters with custom weights
Training data: curated Salesforce-specific examples generated via Claude API
Quantization: Q4_K_M GGUF (1.80 GB)
Context length: 6144 tokens

Quick Start

Ollama

ollama run hf.co/deepforce/deepforce-coder-v2:Q4_K_M

llama.cpp

llama serve -hf deepforce/deepforce-coder-v2:Q4_K_M

Python (llama-cpp-python)

from llama_cpp import Llama

llm = Llama.from_pretrained(
    repo_id  = "deepforce/deepforce-coder-v2",
    filename = "deepforce-coder-v2-q4_k_m.gguf",
)

response = llm.create_chat_completion(messages=[
    {"role": "system", "content": "You are DeepForce Coder, an expert Salesforce developer."},
    {"role": "user",   "content": "Write a simple Apex class that returns Accounts by industry."}
])
print(response["choices"][0]["message"]["content"])

Example Prompts

Generate Apex: Write a trigger handler for Opportunity that creates a follow-up Task

when StageName changes to Closed Won.

Debug Apex: Debug the following Apex code: [paste your code]

Review Apex: Review the following Apex code for best practices: [paste your code]

Generate LWC: Create an LWC component that displays a list of Accounts in a lightning-datatable.

Refactor Apex: Refactor the following Apex code to the minimum implementation: [paste your code]

Generate Test Class: Generate a comprehensive test class for the following Apex class: [paste your code]

Adapter Architecture

DeepForce Coder v2 uses a weighted combination of 9 independently trained LoRA adapters:

Adapter	Weight	Purpose
apex-main	18%	Complex Apex generation
apex-simple	18%	Simple clean Apex patterns
lwc	15%	Lightning Web Components
apex-testclass	12%	Test class generation
apex-refactor	10%	Code refactoring
apex-recursion	10%	Recursion guard patterns
apex-debug	8%	Bug identification
apex-review	5%	Code review
apex-basic	4%	Basic patterns

Known Limitations in v2

Test class generation occasionally uses System.assertEquals instead of Assert class
Recursion guard ID extraction needs improvement (fixed in v3)
These will be addressed in v3

Training

Fine-tuned using Unsloth on Google Colab L4 GPU. Training data generated using Anthropic Claude API. Each adapter trained independently with set_seed(42) for reproducibility.

Version History

Version	Status	Notes
v1	⚠️ Superseded	Hallucinated APIs, over-engineered simple requests
v2	✅ Current	Fixed hallucinations, custom weighted merge
v3	🔄 Planned	Assert class fix, better recursion guards

License

Apache 2.0 — free for commercial and personal use.