commit ef5a8816cd33a3403f58ccd99f1939f6cae79e57 Author: ModelHub XC Date: Sun Jun 21 20:58:27 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: SindreLinden/gemma-3-1b-ifs-cloud-gguf Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..60678b5 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,39 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +model.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-ifs-cloud-gguf-F16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-ifs-cloud-gguf-BF16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-ifs-cloud-gguf-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8da486a --- /dev/null +++ b/README.md @@ -0,0 +1,90 @@ +--- +license: gemma +base_model: google/gemma-3-1b-it +tags: +- fine-tuned +- gguf +- gemma +- instruct +- 1b +model_type: gemma3 +quantized: f16 +datasets: +- custom +language: +- en +pipeline_tag: text-generation +--- + +# Fine-tuned Gemma 3 1B IT (GGUF) + +This is a fine-tuned version of Google's Gemma 3 1B IT model, converted to GGUF format for efficient inference. + +## Model Details + +- **Base Model**: google/gemma-3-1b-it +- **Fine-tuning Method**: QLoRA (Quantized Low-Rank Adaptation) +- **Format**: GGUF (F16 precision) +- **Size**: ~1.9GB + +## Training Details + +- **Adapter**: QLoRA with rank 32, alpha 16 +- **Target Modules**: up_proj, down_proj, gate_proj, q_proj, k_proj, v_proj, o_proj +- **Sequence Length**: 2048 +- **Training Data**: Custom dataset with sample packing +- **Epochs**: 3 +- **Learning Rate**: 0.0004 with cosine scheduler +- **Optimizer**: AdamW BNB 8-bit + +## Usage + +This GGUF model can be used with various inference engines: + +### llama.cpp +```bash +./llama-server -m model.gguf +``` + +### Ollama +```bash +# Create a Modelfile +FROM model.gguf +TEMPLATE """user +{{ .Prompt }} +model +""" + +# Import the model +ollama create my-gemma-model -f Modelfile +ollama run my-gemma-model +``` + +### Python with llama-cpp-python +```python +from llama_cpp import Llama + +llm = Llama(model_path="model.gguf") +output = llm("Tell me about artificial intelligence", max_tokens=512) +print(output) +``` + +## Chat Template + +This model uses Gemma 3's chat template: +``` +user +{user_message} +model +{assistant_response} +``` + +## Limitations + +- This is a small 1B parameter model with inherent limitations +- Fine-tuned for specific use cases - performance may vary on other tasks +- GGUF conversion may introduce minor numerical differences compared to the original model + +## License + +This model inherits the license from the base Gemma model. Please refer to Google's Gemma license for usage terms. diff --git a/config.json b/config.json new file mode 100644 index 0000000..5f27437 --- /dev/null +++ b/config.json @@ -0,0 +1,62 @@ +{ + "_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": "4.55.2", + "use_cache": true, + "vocab_size": 262145 +} diff --git a/gemma-3-1b-ifs-cloud-gguf-BF16.gguf b/gemma-3-1b-ifs-cloud-gguf-BF16.gguf new file mode 100644 index 0000000..92d58ab --- /dev/null +++ b/gemma-3-1b-ifs-cloud-gguf-BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee3eee65110575b2c64e7ab7bd9a40971355518611ac6744b1708a6e229daeb +size 2006575520 diff --git a/gemma-3-1b-ifs-cloud-gguf-F16.gguf b/gemma-3-1b-ifs-cloud-gguf-F16.gguf new file mode 100644 index 0000000..7935e7f --- /dev/null +++ b/gemma-3-1b-ifs-cloud-gguf-F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcf82da57b2575d7da7ffb65962ca820dc8d3e51b32b5698b619eddf4a0a86cd +size 2006575520 diff --git a/gemma-3-1b-ifs-cloud-gguf-Q8_0.gguf b/gemma-3-1b-ifs-cloud-gguf-Q8_0.gguf new file mode 100644 index 0000000..374ad44 --- /dev/null +++ b/gemma-3-1b-ifs-cloud-gguf-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab936059916225ab0d2ab8ecf9ad3ac43ebcaf159bdcbf4c13c4f9c8ad30bcb0 +size 1069307264