commit 5ec6aeb1ce8206b5ab9135c99aa85d3cce553e54 Author: ModelHub XC Date: Mon Aug 31 00:14:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: CraneAILabs/ganda-gemma-1b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4f76eb0 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,5 @@ +*.gguf filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +ganda_gemma_ascending_chart.png filter=lfs diff=lfs merge=lfs -text +ganda_gemma_ascending_clean.png filter=lfs diff=lfs merge=lfs -text diff --git a/F16/ganda-gemma-1b-f16.gguf b/F16/ganda-gemma-1b-f16.gguf new file mode 100644 index 0000000..e572028 --- /dev/null +++ b/F16/ganda-gemma-1b-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdeaa763caada70e145c51a940fde15f152e32d49967f9f0b6c6ca628f131561 +size 2006573184 diff --git a/F32/ganda-gemma-1b-f32.gguf b/F32/ganda-gemma-1b-f32.gguf new file mode 100644 index 0000000..d848025 --- /dev/null +++ b/F32/ganda-gemma-1b-f32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d9597196323f6fdee288e8db131f43bacc97a98a91932c7cb2f971b0da33225 +size 4006076544 diff --git a/Q2_K/ganda-gemma-1b-q2_k.gguf b/Q2_K/ganda-gemma-1b-q2_k.gguf new file mode 100644 index 0000000..5937f11 --- /dev/null +++ b/Q2_K/ganda-gemma-1b-q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8040bc1ac72a0485b794ac6805844d78618bb3eaaabf489892064b18c91a9677 +size 689814144 diff --git a/Q3_K_M/ganda-gemma-1b-q3_k_m.gguf b/Q3_K_M/ganda-gemma-1b-q3_k_m.gguf new file mode 100644 index 0000000..046f887 --- /dev/null +++ b/Q3_K_M/ganda-gemma-1b-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2621229fa7f4c0987fbd79852c8ba9294f1c5d141d5ad05e46d7c0c97962077 +size 722415744 diff --git a/Q4_K_M/ganda-gemma-1b-q4_k_m.gguf b/Q4_K_M/ganda-gemma-1b-q4_k_m.gguf new file mode 100644 index 0000000..1127f4d --- /dev/null +++ b/Q4_K_M/ganda-gemma-1b-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12e8fce498aa4aaa02f00412d0870f0e39b2d18d7f73cb35c523ead6f1bf2370 +size 806057856 diff --git a/Q4_K_S/ganda-gemma-1b-q4_k_s.gguf b/Q4_K_S/ganda-gemma-1b-q4_k_s.gguf new file mode 100644 index 0000000..bdff4ba --- /dev/null +++ b/Q4_K_S/ganda-gemma-1b-q4_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6b89b0451e540839f50a14acb42d2be891ccc023843682171c140e52437488b +size 780992640 diff --git a/Q5_K_M/ganda-gemma-1b-q5_k_m.gguf b/Q5_K_M/ganda-gemma-1b-q5_k_m.gguf new file mode 100644 index 0000000..02ba75c --- /dev/null +++ b/Q5_K_M/ganda-gemma-1b-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cef34d4a86d5ee7d7aacac9ec6aa49054fdcb44d6dcda7b984d3ba723dbebfcc +size 851345280 diff --git a/Q8_0/ganda-gemma-1b-q8_0.gguf b/Q8_0/ganda-gemma-1b-q8_0.gguf new file mode 100644 index 0000000..530b8e8 --- /dev/null +++ b/Q8_0/ganda-gemma-1b-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ed2cfe4d25df96ae2017c2b2b83f9a4ccfd1664610612cce884b370854e077b +size 1069305984 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9100075 --- /dev/null +++ b/README.md @@ -0,0 +1,187 @@ +--- +base_model: google/gemma-3-1b-it +language: +- en +- lg +library_name: transformers +license: gemma +tags: +- luganda +- translation +- conversational +- gemma +- gemma3 +- fine-tuned +pipeline_tag: text-generation +--- + +# Ganda Gemma 1B + +A fine-tuned Gemma 3 1B instruction model specialized for **English-to-Luganda translation and Luganda conversational AI**. The model accepts input in both English and Luganda but outputs responses exclusively in Luganda. + +## 📊 Translation Performance + +![Translation Performance Comparison](ganda_gemma_ascending_chart.png) + +### Model Comparison + +| Model | Parameters | BLEU | chrF++ | Efficiency* | +|-------|------------|------|--------|-----------| +| Gemma 3 4B | 4B | 1.1 | 20.05 | 0.28 | +| Gemma 3 27B | 27B | 3.65 | 31.37 | 0.14 | +| GPT-5 Mini | N/A | 5.14 | 36.55 | N/A | +| **Ganda Gemma 1B** | **1B** | **6.99** | **40.32** | **6.99** | +| Gemini 2.0 Flash | Large | 7.94 | 43.38 | N/A | + + +*Efficiency = BLEU Score ÷ Parameters (in billions) + +### Key Performance Insights + +🎯 **Efficiency Leader**: Achieves 6.99 BLEU per billion parameters (highest efficiency ratio) +🚀 **Size Advantage**: Outperforms Gemma 3 4B (4x larger) by 535% on BLEU score +💎 **Competitive Quality**: Achieves similar performance to GPT-5 Mini with known 1B parameter count +⚡ **Practical Deployment**: Runs efficiently on consumer hardware while maintaining quality + +### Evaluation Details + +- **Dataset**: FLORES-200 English→Luganda (1,012 translation pairs) +- **Metrics**: BLEU (bilingual evaluation understudy) and chrF++ (character F-score) +- **Evaluation**: Zero-shot translation performance + + + +## 🚀 Quick Start + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +# Load model and tokenizer +model = AutoModelForCausalLM.from_pretrained("CraneAILabs/ganda-gemma-1b") +tokenizer = AutoTokenizer.from_pretrained("CraneAILabs/ganda-gemma-1b") + +# Translate to Luganda +prompt = "Translate to Luganda: Hello, how are you today?" +inputs = tokenizer(prompt, return_tensors="pt") +outputs = model.generate(**inputs, max_length=100, temperature=0.3) +response = tokenizer.decode(outputs[0], skip_special_tokens=True) +print(response) +``` + +## 🌍 Language Capabilities + +- **Input Languages**: English + Luganda +- **Output Language**: Luganda only +- **Primary Focus**: English-to-Luganda translation and Luganda conversation + +## 🎯 Capabilities + +- **Translation**: English-to-Luganda translation +- **Conversational AI**: Natural dialogue in Luganda +- **Summarization**: Text summarization in Luganda +- **Writing**: Creative and informational writing in Luganda +- **Question Answering**: General knowledge responses in Luganda + +## 💻 Usage Examples + +### Basic Translation + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +model = AutoModelForCausalLM.from_pretrained("CraneAILabs/ganda-gemma-1b") +tokenizer = AutoTokenizer.from_pretrained("CraneAILabs/ganda-gemma-1b") + +# English to Luganda translation +prompt = "Translate to Luganda: Welcome to our school" +inputs = tokenizer(prompt, return_tensors="pt") + +with torch.no_grad(): + outputs = model.generate( + **inputs, + max_length=100, + temperature=0.3, + do_sample=True, + pad_token_id=tokenizer.eos_token_id + ) + +response = tokenizer.decode(outputs[0], skip_special_tokens=True) +print(response) +``` + +### Luganda Conversation + +```python +# Direct Luganda conversation +prompt = "Oli otya! Osobola okuntuyamba leero?" +inputs = tokenizer(prompt, return_tensors="pt") +outputs = model.generate(**inputs, max_length=100, temperature=0.3) +response = tokenizer.decode(outputs[0], skip_special_tokens=True) +print(response) +``` + +### Using the Pipeline + +```python +from transformers import pipeline + +# Create a text generation pipeline +generator = pipeline( + "text-generation", + model="CraneAILabs/ganda-gemma-1b", + tokenizer="CraneAILabs/ganda-gemma-1b", + device=0 if torch.cuda.is_available() else -1 +) + +# Generate Luganda text +result = generator( + "Translate to Luganda: Welcome to our school", + max_length=100, + temperature=0.3, + do_sample=True +) +print(result[0]['generated_text']) +``` + +### Ollama Usage + +```bash +# Run with different quantizations +ollama run crane-ai-labs/ganda-gemma-1b:q4-k-m # Recommended balance +ollama run crane-ai-labs/ganda-gemma-1b:q8-0 # Higher quality +ollama run crane-ai-labs/ganda-gemma-1b:q4-k-s # Smaller size +ollama run crane-ai-labs/ganda-gemma-1b:f16 # Original quality +``` + +## 🚀 GGUF Advantages + +- **Fast CPU Inference**: Optimized for CPU-only environments +- **Memory Efficient**: Multiple quantization levels available +- **Easy Integration**: Works with llama.cpp, Ollama, and other GGUF-compatible tools +- **Cross-Platform**: Supports Windows, macOS, and Linux + +## 📦 Available Quantizations + +| Quantization | File Size | Memory Usage | Quality | Use Case | +|-------------|-----------|--------------|---------|----------| +| F16 | ~2.0GB | ~3.5GB | Best | GPU inference | +| Q8_0 | ~1.1GB | ~2.0GB | High | High-end CPU | +| Q4_K_M | ~600MB | ~1.2GB | Good | **Recommended** | +| Q4_K_S | ~550MB | ~1.1GB | Decent | Low memory | +| Q4_0 | ~550MB | ~1.0GB | Basic | Very low memory | + +## 🔗 Related Models + +- **Original Model**: [CraneAILabs/ganda-gemma-1b](https://huggingface.co/CraneAILabs/ganda-gemma-1b) - Full precision HuggingFace model +- **Mobile (LiteRT)**: [CraneAILabs/ganda-gemma-1b-litert](https://huggingface.co/CraneAILabs/ganda-gemma-1b-litert) - Optimized for Android/iOS + +## 📄 License + +This model is released under the [Gemma Terms of Use](https://ai.google.dev/gemma/terms). Please review the terms before use. + +--- + +**Built with ❤️ by Crane AI Labs** + +*Ganda Gemma - Your helpful Luganda AI companion, optimized for CPU!* diff --git a/config.json b/config.json new file mode 100644 index 0000000..212f585 --- /dev/null +++ b/config.json @@ -0,0 +1,64 @@ +{ + "_sliding_window_pattern": 6, + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "eos_token_id": 106, + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 1152, + "initializer_range": 0.02, + "intermediate_size": 6912, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "num_attention_heads": 4, + "num_hidden_layers": 26, + "num_key_value_heads": 1, + "pad_token_id": 0, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": 512, + "torch_dtype": "bfloat16", + "transformers_version": "4.54.1", + "unsloth_fixed": true, + "unsloth_version": "2025.7.11", + "use_cache": true, + "vocab_size": 262144 +} diff --git a/ganda_gemma_ascending_chart.png b/ganda_gemma_ascending_chart.png new file mode 100644 index 0000000..2f5d440 --- /dev/null +++ b/ganda_gemma_ascending_chart.png @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:358fe0ce5516c724a09cff15d1d8a95ebc8d8b39f5d10481066617c74fabf9bf +size 152124