Instructions to use SpaceGhost/SpaceCode-E2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use SpaceGhost/SpaceCode-E2B 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 SpaceGhost/SpaceCode-E2B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SpaceGhost/SpaceCode-E2B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SpaceGhost/SpaceCode-E2B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf SpaceGhost/SpaceCode-E2B:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf SpaceGhost/SpaceCode-E2B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf SpaceGhost/SpaceCode-E2B:Q4_K_M

Use Docker

docker model run hf.co/SpaceGhost/SpaceCode-E2B:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use SpaceGhost/SpaceCode-E2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SpaceGhost/SpaceCode-E2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SpaceGhost/SpaceCode-E2B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/SpaceGhost/SpaceCode-E2B:Q4_K_M

Ollama
How to use SpaceGhost/SpaceCode-E2B with Ollama:
```
ollama run hf.co/SpaceGhost/SpaceCode-E2B:Q4_K_M
```
Unsloth Desktop

How to use SpaceGhost/SpaceCode-E2B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SpaceGhost/SpaceCode-E2B:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "SpaceGhost/SpaceCode-E2B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use SpaceGhost/SpaceCode-E2B with Docker Model Runner:
```
docker model run hf.co/SpaceGhost/SpaceCode-E2B:Q4_K_M
```

Lemonade

How to use SpaceGhost/SpaceCode-E2B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SpaceGhost/SpaceCode-E2B:Q4_K_M

Run and chat with the model

lemonade run user.SpaceCode-E2B-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use SpaceGhost/SpaceCode-E2B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SpaceGhost/SpaceCode-E2B: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 SpaceGhost/SpaceCode-E2B:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SpaceGhost/SpaceCode-E2B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SpaceGhost/SpaceCode-E2B:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "SpaceGhost/SpaceCode-E2B:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

SpaceGhost commited on 5 days ago

Commit

1383452

verified ·

1 Parent(s): dbc5242

docs: sync official SpaceCode 131-example Model Card and lineage

Browse files

Files changed (1) hide show

README.md +111 -13

README.md CHANGED Viewed

@@ -1,21 +1,119 @@
 ---
-base_model: unsloth/gemma-4-E2B-it-unsloth-bnb-4bit
 tags:
-- text-generation-inference
-- transformers
-- unsloth
-- gemma4
-license: apache-2.0
 language:
-- en
 ---
-# Uploaded finetuned  model
-- **Developed by:** SpaceGhost
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/gemma-4-E2B-it-unsloth-bnb-4bit
-This gemma4 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

 ---
+license: gemma
+base_model:
+  - google/gemma-4-E2B-it
+  - unsloth/gemma-4-E2B-it
+datasets:
+  - SpaceGhost/space-dataset
 tags:
+  - code
+  - vision
+  - multimodal
+  - gguf
+  - llama.cpp
+  - ollama
+  - unsloth
+  - causal-software-engineering
+  - react
+  - flutter
+  - typescript
+  - python
+  - rust
+  - go
 language:
+  - pt
+  - en
+pipeline_tag: image-text-to-text
 ---
+# SpaceCode-E2B-it (`SpaceGhost/SpaceCode-E2B-it`)
+**SpaceCode-E2B-it** é um modelo de Engenharia de Software e Reparo Visual Causal derivado do **Google Gemma 4 E2B (`google/gemma-4-E2B-it`)**, treinado via QLoRA SFT com [Unsloth](https://github.com/unslothai/unsloth) e quantizado em formato **GGUF (`Q4_K_M`)** pela **SpaceGhost** através do projeto `dataset-treina`.
+---
+## 📌 Visão Geral do Modelo
+- **Nome Oficial**: `SpaceCode-E2B-it`
+- **Repositório Hugging Face**: [`SpaceGhost/SpaceCode-E2B-it`](https://huggingface.co/SpaceGhost/SpaceCode-E2B-it)
+- **Dataset Oficial**: [`SpaceGhost/space-dataset`](https://huggingface.co/datasets/SpaceGhost/space-dataset) (`data/gemma4/train_131.jsonl`)
+- **Modelo Base**: `google/gemma-4-E2B-it` (`unsloth/gemma-4-E2B-it`)
+- **Formato / Quantização**: `GGUF` (`gemma-4-E2B-it.Q4_K_M.gguf`) + `Modelfile` oficial para Ollama
+- **Janela de Contexto**: 128K tokens (treinado com `max_seq_length=4096`)
+---
+## 📊 Corpus de Treinamento Consolidado (131 Exemplos Auditados)
+O modelo foi ajustado sobre o corpus **`train_131.jsonl`** (SHA-256: `f4382467afa2a41e832c01d79489fdb17e9c561e6b5ec26545bdc937a74c1009`), combinando reparo visual causal e engenharia de software políglota com **zero vazamento (0% data leakage)** contra os conjuntos de validação, holdout de teste e benchmark de ambiguidade:
+1. **C08 — Diagnóstico Causal e Reparo Visual Dual-Image (31 exemplos)**:
+   - Pares multimodais (`expected_ui` vs. `actual_ui` + código quebrado) cobrindo regressões de CSS/Tailwind e Flutter (`flex_direction`, `grid_columns`, `overflow_clipping`, `padding_collapse`, `gap_collapse`, `z_index_occlusion`, `color_contrast`, `alignment_shift`).
+   - Saída estruturada em 3 blocos auditáveis:
+     1. `### 1. Diagnóstico Causal da Regressão Visual`
+     2. `### 2. Patch Mínimo (Unified Diff)`
+     3. `### 3. Código Corrigido Completo`
+2. **Engenharia de Software Políglota C01–C06 (100 exemplos em 9 linguagens)**:
+   - **Linguagens**: TypeScript (28), Python (22), Dart/Flutter (11), SQL (10), Java (9), Go (8), C# (5), Rust (5) e Bash (2).
+   - **Categorias**:
+     - `C01`: Correção de Bug com Causa Raiz + Teste Unitário (23)
+     - `C02`: Refatoração Estrutural / Clean Architecture (16)
+     - `C03`: Geração de Testes Unitários e Edge Cases (15)
+     - `C04`: Code Review Técnico e Segurança / OWASP (15)
+     - `C05`: Raciocínio Arquitetural e Trade-offs / ADR (16)
+     - `C06`: Implementação Idiomática End-to-End (15)
+---
+## ⚙️ Hiperparâmetros e Telemetria de Treinamento
+| Parâmetro / Métrica | Valor |
+| :--- | :--- |
+| **Hardware** | 1x NVIDIA L4 (23 GB VRAM, CUDA 13.0, `bfloat16`) |
+| **Método de Fine-Tuning** | QLoRA 4-bit (`r=16`, `lora_alpha=16`, `lora_dropout=0`) |
+| **Parâmetros Treináveis** | `36,925,440` de `5,160,103,456` (`0.72%`) |
+| **Épocas / Steps Totais** | `3.0` épocas (`99` steps de otimização) |
+| **Batch Efetivo** | `4` (`per_device_train_batch_size=1`, `gradient_accumulation_steps=4`) |
+| **Learning Rate / Scheduler** | `2e-4` (`cosine`, `warmup_ratio=0.05`, `adamw_8bit`) |
+| **Training Loss Inicial $\rightarrow$ Final** | `2.3800` (step 1) $\rightarrow$ `0.4500–0.9045` (época 3) |
+| **Training Loss Médio Global** | **`0.97316`** |
+| **Tempo Total de Treino** | `822.52s` (~13m42s) |
+---
+## 🚀 Como Executar Localmente
+### 1. Via Ollama
+```bash
+ollama run hf.co/SpaceGhost/SpaceCode-E2B-it
+```
+### 2. Via `llama.cpp` (`llama-cli`)
+```bash
+llama-cli -hf SpaceGhost/SpaceCode-E2B-it --jinja
+```
+### 3. Arquivos Disponíveis no Repositório
+- `gemma-4-E2B-it.Q4_K_M.gguf` — Pesos quantizados em 4-bit (`Q4_K_M`)
+- `Modelfile` — Configuração pronta para importação no Ollama
+- `config.json` — Metadados de arquitetura Gemma 4 E2B
+> **Nota sobre Multimodalidade em GGUF**: O arquivo `.gguf` exportado contém o backbone de texto quantizado (`Q4_K_M`) para inferência rápida de código, diagnóstico textual, refatoração e arquitetura em CPU/GPU local. Para inferência com entrada direta de imagens (visão nativa Dual-Image C08), utilize o adaptador QLoRA com `Unsloth` / `Transformers` (`FastVisionModel`).
+---
+## 🧭 Linhagem Oficial SpaceGhost
+| Repositório Hugging Face | Papel na Arquitetura | Commit SHA |
+| :--- | :--- | :--- |
+| [`SpaceGhost/SpaceCode`](https://huggingface.co/SpaceGhost/SpaceCode) | **Adaptador QLoRA Multimodal** (`adapter_model.safetensors` + `processor_config.json`) | `45673d32` |
+| [`SpaceGhost/SpaceCode-Merged`](https://huggingface.co/SpaceGhost/SpaceCode-Merged) | **Modelo 16-bit Merged** (QLoRA fundido ao base `model.safetensors` + visão multimodal) | `dbc5242d` |
+| [`SpaceGhost/SpaceCode-E2B-it`](https://huggingface.co/SpaceGhost/SpaceCode-E2B-it) | **Modelo Quantizado GGUF (`Q4_K_M`)** + `Modelfile` para Ollama / `llama.cpp` | `560caef9` |
+| [`SpaceGhost/space-dataset`](https://huggingface.co/datasets/SpaceGhost/space-dataset) | **Dataset Oficial Auditado** (`train_131.jsonl`, `manifest_131.json`, splits C07/C08) | `c6306f4a` |
+---
+## ⚠️ Nota de Atribuição
+- *SpaceCode-E2B-it is a fine-tuned derivative of Google Gemma 4 E2B (`google/gemma-4-E2B-it`).*
+- Desenvolvido pela organização **SpaceGhost** no contexto do projeto `dataset-treina` (sem relação com o benchmark acadêmico independente `KurtDu/SpaceCode-Bench`).