commit e67cf18d55b5389516906ed0eb2f4bfebc35d6d3 Author: ModelHub XC Date: Sat Oct 10 23:10:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: adityaharshef3/gemma_test Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d014738 --- /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 +gemma-3-4b-it.F16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it.F16-mmproj.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-it.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..3928291 --- /dev/null +++ b/Modelfile @@ -0,0 +1,20 @@ + +FROM . +TEMPLATE """{{- range $i, $_ := .Messages }} +{{- $last := eq (len (slice $.Messages $i)) 1 }} +{{- if or (eq .Role "user") (eq .Role "system") }}user +{{ .Content }} +{{ if $last }}model +{{ end }} +{{- else if eq .Role "assistant" }}model +{{ .Content }}{{ if not $last }} +{{ end }} +{{- end }} +{{- end }}""" +PARAMETER stop "" +PARAMETER stop "" +PARAMETER temperature 1.0 +PARAMETER min_p 0.0 +PARAMETER top_k 64 +PARAMETER top_p 0.95 +PARAMETER num_predict 32768 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..4a1048e --- /dev/null +++ b/README.md @@ -0,0 +1,31 @@ +--- +tags: +- gguf +- llama.cpp +- unsloth +- vision-language-model +--- + +# gemma_test : GGUF + +This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth). + +**Example usage**: +- For text only LLMs: `./llama.cpp/llama-cli -hf adityaharshef3/gemma_test --jinja` +- For multimodal models: `./llama.cpp/llama-mtmd-cli -hf adityaharshef3/gemma_test --jinja` + +## Available Model files: +- `gemma-3-4b-it.Q4_K_M.gguf` +- `gemma-3-4b-it.F16-mmproj.gguf` + +## ⚠️ Ollama Note for Vision Models +**Important:** Ollama currently does not support separate mmproj files for vision models. + +To create an Ollama model from this vision model: +1. Place the `Modelfile` in the same directory as the finetuned bf16 merged model +3. Run: `ollama create model_name -f ./Modelfile` + (Replace `model_name` with your desired name) + +This will create a unified bf16 model that Ollama can use. +This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) +[](https://github.com/unslothai/unsloth) diff --git a/config.json b/config.json new file mode 100644 index 0000000..3ff0265 --- /dev/null +++ b/config.json @@ -0,0 +1,101 @@ +{ + "architectures": [ + "Gemma3ForConditionalGeneration" + ], + "boi_token_index": 255999, + "bos_token_id": 2, + "torch_dtype": "float16", + "eoi_token_index": 256000, + "eos_token_id": 106, + "image_token_index": 262144, + "initializer_range": 0.02, + "mm_tokens_per_image": 256, + "model_type": "gemma3", + "pad_token_id": 0, + "text_config": { + "_sliding_window_pattern": 6, + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "cache_implementation": "hybrid", + "torch_dtype": "float16", + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 10240, + "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", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention" + ], + "max_position_embeddings": 131072, + "model_type": "gemma3_text", + "num_attention_heads": 8, + "num_hidden_layers": 34, + "num_key_value_heads": 4, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000.0, + "rope_scaling": { + "factor": 8.0, + "rope_type": "linear" + }, + "rope_theta": 1000000.0, + "sliding_window": 1024, + "sliding_window_pattern": 6, + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262208 + }, + "transformers_version": "4.57.3", + "unsloth_fixed": true, + "unsloth_version": "2026.1.3", + "vision_config": { + "attention_dropout": 0.0, + "torch_dtype": "float16", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1152, + "image_size": 896, + "intermediate_size": 4304, + "layer_norm_eps": 1e-06, + "model_type": "siglip_vision_model", + "num_attention_heads": 16, + "num_channels": 3, + "num_hidden_layers": 27, + "patch_size": 14, + "vision_use_head": false + } +} \ No newline at end of file diff --git a/gemma-3-4b-it.F16-mmproj.gguf b/gemma-3-4b-it.F16-mmproj.gguf new file mode 100644 index 0000000..00e7c2f --- /dev/null +++ b/gemma-3-4b-it.F16-mmproj.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deb482628a87866e5589f9638b09f524c611899d33044b7e6f65b773e118d45f +size 851251424 diff --git a/gemma-3-4b-it.F16.gguf b/gemma-3-4b-it.F16.gguf new file mode 100644 index 0000000..36927b6 --- /dev/null +++ b/gemma-3-4b-it.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71887746413870b87d1ab003c5c808e8a97ef7cec40b4e58952df55219180af1 +size 7767803584 diff --git a/gemma-3-4b-it.Q4_K_M.gguf b/gemma-3-4b-it.Q4_K_M.gguf new file mode 100644 index 0000000..e4e30da --- /dev/null +++ b/gemma-3-4b-it.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7897b6e2f599e2965f502b0394cf3bf9f9bdb12e2e91856a7674d88b9bc6019b +size 2489893824 diff --git a/gemma-3-4b-it.Q8_0.gguf b/gemma-3-4b-it.Q8_0.gguf new file mode 100644 index 0000000..01887fd --- /dev/null +++ b/gemma-3-4b-it.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dfa6d65ca61e7c884b7cbe7b478e8941f3b5cbc8f63c3c38b1a56a34656941d +size 4130401984