Upload folder using huggingface_hub

0000200_adapters.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dbaa673ec1a3a696f2803cec31174481ab3d1b523ccfc0f243988a66bcfc8a7
+size 3206027

0000400_adapters.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efb53af4d2b7c10f55982b1d7922a4d95633601e29c1e5d3f20be1669014c3e9
+size 3206027

0000600_adapters.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:165e22ae3145f6eb1920691ba8b5b5cc6d4e036fd813c8935dcb4593a115c9d4
+size 3206027

0000800_adapters.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:debda81f5dee2927221584911f1dac33876adbe1debb5d4cc04d7556fe142045
+size 3206027

0001000_adapters.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802542d041917db7f85d855cf831f26f5f1fdcb763e9f3c7e479df7f613b2aa2
+size 3206027

README.md

@@ -0,0 +1,113 @@
+---
+license: apache-2.0
+base_model: mlx-community/gemma-2-2b-it-4bit
+tags:
+- mlx
+- lora
+- shell-commands
+- gemma
+- instruction-tuning
+language:
+- en
+library_name: mlx-lm
+---
+
+# Shell Command Assistant - Gemma 2B LoRA Adapters
+
+This model provides LoRA (Low-Rank Adaptation) adapters for the Gemma 2B model, fine-tuned to help users with shell commands. It can answer questions about common Unix/Linux shell commands with high accuracy.
+
+## Model Performance
+- **Accuracy**: 100% on core shell commands
+- **Base Model**: mlx-community/gemma-2-2b-it-4bit  
+- **Adapter Size**: ~18MB (much smaller than full model)
+- **Training**: Fine-tuned on 26 diverse shell command examples
+
+## Quick Start
+
+```python
+from mlx_lm import load, generate
+
+# Load the model with adapters
+model, tokenizer = load(
+    "mlx-community/gemma-2-2b-it-4bit",
+    adapter_path="PKSGIN/MyGemma270_Shellcommands"
+)
+
+# Ask a question
+question = "How do I check disk space?"
+prompt = f"### Human: {question}\n### Assistant:"
+response = generate(model, tokenizer, prompt=prompt, max_tokens=50, verbose=False)
+print(response.strip())
+```
+
+## Example Outputs
+
+```python
+# Question: How do I list all files including hidden ones?
+# Answer: Use ls -la to show all files including hidden ones.
+
+# Question: How do I find all Python files? 
+# Answer: Use find . -name "*.py" to find all Python files.
+
+# Question: How do I check memory usage?
+# Answer: Use free -h to see memory usage in human-readable format.
+```
+
+## Supported Commands
+
+The model can help with these types of shell commands:
+
+- **File Operations**: `ls`, `cp`, `mv`, `rm`, `mkdir`, `find`
+- **System Monitoring**: `ps`, `top`, `free`, `df`  
+- **Network**: `netstat`, `lsof`, `ping`
+- **File Content**: `cat`, `grep`, `wc`, `tail`, `head`
+- **Archives**: `tar`, `zip`, `unzip`
+- **Permissions**: `chmod`, `chown`
+- **Process Management**: `kill`, background processes
+
+## Training Details
+
+- **Method**: LoRA (Low-Rank Adaptation)
+- **Rank**: 4, **Alpha**: 8, **Dropout**: 0.0
+- **Training Data**: 26 unique shell commands × 60 repetitions = ~1560 examples
+- **Format**: Human/Assistant conversation format
+- **Iterations**: ~1000 until convergence
+
+## Installation
+
+```bash
+pip install mlx-lm>=0.19.0
+```
+
+## Usage Examples
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load(
+    "mlx-community/gemma-2-2b-it-4bit",
+    adapter_path="PKSGIN/MyGemma270_Shellcommands"
+)
+
+questions = [
+    "How do I compress files?",
+    "How do I see running processes?", 
+    "How do I find large files?",
+    "How do I check network connections?"
+]
+
+for question in questions:
+    prompt = f"### Human: {question}\n### Assistant:"
+    response = generate(model, tokenizer, prompt=prompt, max_tokens=50)
+    print(f"Q: {question}")
+    print(f"A: {response.strip()}")
+    print()
+```
+
+## License
+
+Apache 2.0 (following base Gemma model)
+
+## Acknowledgments
+
+Built using MLX-LM and based on Google's Gemma 2B model.

adapter_config.json

@@ -0,0 +1,37 @@
+{
+    "adapter_file": "adapters.safetensors",
+    "adapter_path": "gemma270m_adapters",
+    "batch_size": 1,
+    "data": "expanded_shell_data",
+    "fine_tune_type": "lora",
+    "grad_checkpoint": false,
+    "iters": 1000,
+    "learning_rate": 0.0001,
+    "lora_layers": 8,
+    "lora_parameters": {
+        "rank": 4,
+        "alpha": 8,
+        "dropout": 0.0,
+        "scale": 10.0
+    },
+    "lr_schedule": null,
+    "max_seq_length": 256,
+    "model": "mlx-community/gemma-2-2b-it-4bit",
+    "num_layers": 8,
+    "optimizer": "adamw",
+    "optimizer_config": {},
+    "q_lora_quantization_config": null,
+    "resume_adapter_file": null,
+    "save_every": 200,
+    "seed": 42,
+    "steps_per_eval": 200,
+    "steps_per_report": 50,
+    "steps_per_save": 200,
+    "test": false,
+    "test_batches": 20,
+    "train": true,
+    "use_q_lora": false,
+    "val_batches": 20,
+    "wandb": null,
+    "warmup": 100
+}

adapter_info.json

@@ -0,0 +1,20 @@
+{
+  "base_model": "mlx-community/gemma-2-2b-it-4bit",
+  "library": "mlx-lm",
+  "model_type": "gemma2",
+  "lora_config": {
+    "rank": 4,
+    "alpha": 8,
+    "dropout": 0.0,
+    "target_modules": [
+      "q_proj",
+      "v_proj"
+    ]
+  },
+  "training_info": {
+    "dataset_size": 1560,
+    "unique_commands": 26,
+    "accuracy": "100%",
+    "format": "Human/Assistant"
+  }
+}

adapters.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802542d041917db7f85d855cf831f26f5f1fdcb763e9f3c7e479df7f613b2aa2
+size 3206027