初始化项目，由ModelHub XC社区提供模型
Model: CraneAILabs/ganda-gemma-1b-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
5
.gitattributes
vendored
Normal file
5
.gitattributes
vendored
Normal file
@@ -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
|
||||
3
F16/ganda-gemma-1b-f16.gguf
Normal file
3
F16/ganda-gemma-1b-f16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bdeaa763caada70e145c51a940fde15f152e32d49967f9f0b6c6ca628f131561
|
||||
size 2006573184
|
||||
3
F32/ganda-gemma-1b-f32.gguf
Normal file
3
F32/ganda-gemma-1b-f32.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6d9597196323f6fdee288e8db131f43bacc97a98a91932c7cb2f971b0da33225
|
||||
size 4006076544
|
||||
3
Q2_K/ganda-gemma-1b-q2_k.gguf
Normal file
3
Q2_K/ganda-gemma-1b-q2_k.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8040bc1ac72a0485b794ac6805844d78618bb3eaaabf489892064b18c91a9677
|
||||
size 689814144
|
||||
3
Q3_K_M/ganda-gemma-1b-q3_k_m.gguf
Normal file
3
Q3_K_M/ganda-gemma-1b-q3_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e2621229fa7f4c0987fbd79852c8ba9294f1c5d141d5ad05e46d7c0c97962077
|
||||
size 722415744
|
||||
3
Q4_K_M/ganda-gemma-1b-q4_k_m.gguf
Normal file
3
Q4_K_M/ganda-gemma-1b-q4_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:12e8fce498aa4aaa02f00412d0870f0e39b2d18d7f73cb35c523ead6f1bf2370
|
||||
size 806057856
|
||||
3
Q4_K_S/ganda-gemma-1b-q4_k_s.gguf
Normal file
3
Q4_K_S/ganda-gemma-1b-q4_k_s.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b6b89b0451e540839f50a14acb42d2be891ccc023843682171c140e52437488b
|
||||
size 780992640
|
||||
3
Q5_K_M/ganda-gemma-1b-q5_k_m.gguf
Normal file
3
Q5_K_M/ganda-gemma-1b-q5_k_m.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cef34d4a86d5ee7d7aacac9ec6aa49054fdcb44d6dcda7b984d3ba723dbebfcc
|
||||
size 851345280
|
||||
3
Q8_0/ganda-gemma-1b-q8_0.gguf
Normal file
3
Q8_0/ganda-gemma-1b-q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8ed2cfe4d25df96ae2017c2b2b83f9a4ccfd1664610612cce884b370854e077b
|
||||
size 1069305984
|
||||
187
README.md
Normal file
187
README.md
Normal file
@@ -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
|
||||
|
||||
|
||||
|
||||
### 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!*
|
||||
64
config.json
Normal file
64
config.json
Normal file
@@ -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
|
||||
}
|
||||
3
ganda_gemma_ascending_chart.png
Normal file
3
ganda_gemma_ascending_chart.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:358fe0ce5516c724a09cff15d1d8a95ebc8d8b39f5d10481066617c74fabf9bf
|
||||
size 152124
|
||||
Reference in New Issue
Block a user