Duplicate from MassivDash/Gemma-4-Rust-Coder

Co-authored-by: LCelitan <MassivDash@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,42 @@
+*.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-4-e2b-it.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-4-e2b-it.BF16-mmproj.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-4-e2b-it.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-4-e2b-it.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-4-e2b-it.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-4-e2b-it.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-4-e2b-it.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text

Modelfile

@@ -0,0 +1,10 @@
+
+FROM .
+TEMPLATE """{{- range $i, $_ := .Messages }}
+{{- $last := eq (len (slice $.Messages $i)) 1 }}
+<|turn>{{ .Role }}
+{{ .Content }}{{ if not $last }}<turn|>
+{{ end }}
+{{- end }}<turn|>
+<|turn>model
+"""

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- gguf
+- llama.cpp
+- unsloth
+- vision-language-model
+- rust
+- coding
+license: mit
+datasets:
+- Fortytwo-Network/Strandset-Rust-v1
+base_model:
+- google/gemma-4-E4B-it
+---
+
+# Gemma-4-Rust-Coder : GGUF
+
+This model is a specialized fine-tune of **Gemma 4**, specifically optimized for **Rust systems programming**, memory safety patterns, and high-performance development. It was trained using **Unsloth Studio** to ensure maximum efficiency and performance.
+
+## 🦀 Fine-Tuning Focus
+The model has been adjusted to excel in:
+* **Idiomatic Rust:** Writing clean, "Rusty" code using modern patterns.
+* **Concurrency:** Deep understanding of `Send`, `Sync`, and async runtimes like `Tokio`.
+* **Vision-to-Code:** Using its multimodal capabilities to translate architecture diagrams or UI mockups into functional Rust code.
+
+## 🤝 Credits & Acknowledgments
+Special thanks to **Fortytwo-Network** for providing the **[Strandset-Rust-v1](https://huggingface.co/datasets/Fortytwo-Network/Strandset-Rust-v1)** dataset. This model's specialized knowledge of the Rust ecosystem is a direct result of this high-quality data.
+
+## 🚀 Usage
+This model is converted to GGUF format for seamless use with `llama.cpp` and other compatible executors.
+
+**Example usage**:
+* **Text-only LLM:** `llama-cli -hf MassivDash/Gemma-4-Rust-Coder --jinja`
+* **Multimodal / Vision:** `llama-mtmd-cli -hf MassivDash/Gemma-4-Rust-Coder --jinja`
+
+## 📂 Available Model files:
+* `gemma-4-e2b-it.Q3_K_M.gguf`
+* `gemma-4-e2b-it.BF16-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.
+2. Run: `ollama create model_name -f ./Modelfile`
+   *(Replace `model_name` with your desired name)*
+
+## 🔗 Stay Connected
+For more insights on AI development and fine-tuning, visit my blog: 
+👉 **[spaceout.pl](https://spaceout.pl)**
+
+---
+
+*This model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)*
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

config.json

@@ -0,0 +1,191 @@
+{
+    "architectures": [
+        "Gemma4ForConditionalGeneration"
+    ],
+    "audio_config": {
+        "_name_or_path": "",
+        "architectures": null,
+        "attention_chunk_size": 12,
+        "attention_context_left": 13,
+        "attention_context_right": 0,
+        "attention_invalid_logits_value": -1000000000.0,
+        "attention_logit_cap": 50.0,
+        "chunk_size_feed_forward": 0,
+        "conv_kernel_size": 5,
+        "torch_dtype": "bfloat16",
+        "gradient_clipping": 10000000000.0,
+        "hidden_act": "silu",
+        "hidden_size": 1024,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "initializer_range": 0.02,
+        "is_encoder_decoder": false,
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "model_type": "gemma4_audio",
+        "num_attention_heads": 8,
+        "num_hidden_layers": 12,
+        "output_attentions": false,
+        "output_hidden_states": false,
+        "output_proj_dims": 1536,
+        "problem_type": null,
+        "residual_weight": 0.5,
+        "return_dict": true,
+        "rms_norm_eps": 1e-06,
+        "subsampling_conv_channels": [
+            128,
+            32
+        ],
+        "use_clipped_linears": true
+    },
+    "audio_token_id": 258881,
+    "boa_token_id": 256000,
+    "boi_token_id": 255999,
+    "torch_dtype": "bfloat16",
+    "eoa_token_id": 258883,
+    "eoa_token_index": 258883,
+    "eoi_token_id": 258882,
+    "eos_token_id": 1,
+    "image_token_id": 258880,
+    "initializer_range": 0.02,
+    "model_name": "unsloth/gemma-4-e2b-it-unsloth-bnb-4bit",
+    "model_type": "gemma4",
+    "pad_token_id": 0,
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attention_k_eq_v": false,
+        "bos_token_id": 2,
+        "torch_dtype": "bfloat16",
+        "enable_moe_block": false,
+        "eos_token_id": 1,
+        "expert_intermediate_size": null,
+        "final_logit_softcapping": 30.0,
+        "global_head_dim": 512,
+        "head_dim": 256,
+        "hidden_activation": "gelu_pytorch_tanh",
+        "hidden_size": 1536,
+        "hidden_size_per_layer_input": 256,
+        "initializer_range": 0.02,
+        "intermediate_size": 6144,
+        "layer_types": [
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "sliding_attention",
+            "full_attention"
+        ],
+        "max_position_embeddings": 131072,
+        "model_type": "gemma4_text",
+        "moe_intermediate_size": null,
+        "num_attention_heads": 8,
+        "num_experts": null,
+        "num_global_key_value_heads": null,
+        "num_hidden_layers": 35,
+        "num_key_value_heads": 1,
+        "num_kv_shared_layers": 20,
+        "pad_token_id": 0,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "full_attention": {
+                "partial_rotary_factor": 0.25,
+                "rope_theta": 1000000.0,
+                "rope_type": "proportional"
+            },
+            "sliding_attention": {
+                "rope_theta": 10000.0,
+                "rope_type": "default"
+            }
+        },
+        "sliding_window": 512,
+        "tie_word_embeddings": true,
+        "top_k_experts": null,
+        "use_bidirectional_attention": null,
+        "use_cache": true,
+        "use_double_wide_mlp": true,
+        "vocab_size": 262144,
+        "vocab_size_per_layer_input": 262144
+    },
+    "tie_word_embeddings": true,
+    "unsloth_fixed": true,
+    "unsloth_version": "2026.4.5",
+    "video_token_id": 258884,
+    "vision_config": {
+        "_name_or_path": "",
+        "architectures": null,
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "chunk_size_feed_forward": 0,
+        "default_output_length": 280,
+        "torch_dtype": "bfloat16",
+        "global_head_dim": 64,
+        "head_dim": 64,
+        "hidden_activation": "gelu_pytorch_tanh",
+        "hidden_size": 768,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "initializer_range": 0.02,
+        "intermediate_size": 3072,
+        "is_encoder_decoder": false,
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "max_position_embeddings": 131072,
+        "model_type": "gemma4_vision",
+        "num_attention_heads": 12,
+        "num_hidden_layers": 16,
+        "num_key_value_heads": 12,
+        "output_attentions": false,
+        "output_hidden_states": false,
+        "patch_size": 16,
+        "pooling_kernel_size": 3,
+        "position_embedding_size": 10240,
+        "problem_type": null,
+        "return_dict": true,
+        "rms_norm_eps": 1e-06,
+        "rope_parameters": {
+            "rope_theta": 100.0,
+            "rope_type": "default"
+        },
+        "standardize": false,
+        "use_clipped_linears": true
+    },
+    "vision_soft_tokens_per_image": 280
+}

gemma-4-e2b-it.BF16-mmproj.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f212bd6929e52c593ea89e3ed0057e6adfd5ca58964e05a911776d72e65b58
+size 986833312

gemma-4-e2b-it.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f4d48b3ddda3f34da8169d7daabcfe7f6693d0833b95738a99a58262925afb
+size 3201344096

gemma-4-e2b-it.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f8f202b9282df19fd997de1941df221782e3e7db1d3fd25ede306381788cb65
+size 3360154208

gemma-4-e2b-it.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:559e43668ae5331cb8e6767e702eb71ba20834a5b88698ae71f216cc507bae21
+size 3427873376

gemma-4-e2b-it.Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eb4091145c884552079eab404fa98aea99cf633ce1507b2097114c2ac30048c
+size 3595395680

gemma-4-e2b-it.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b47d4edec2688256848621ec8320718055ac3543f6732add505b24eadf1921
+size 3630281312

gemma-4-e2b-it.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:849e7336a84b776ca78b5538eda78e4c6fc881b1623618ca4bf902a7dbfeddc2
+size 4967490144