Upload folder using huggingface_hub

README.md

@@ -0,0 +1,74 @@
+---
+base_model: microsoft/phi-3-mini-128k-instruct
+library_name: peft
+model_name: phi3-nl2bash-lora
+tags:
+- lora
+- nl2bash
+- sft
+- bash
+- transformers
+- trl
+license: mit
+pipeline_tag: text-generation
+---
+
+# phi3-nl2bash-lora
+
+This repository contains **LoRA adapter weights** fine-tuned on the
+[`jiacheng-ye/nl2bash`](https://huggingface.co/datasets/jiacheng-ye/nl2bash)
+dataset to convert **natural language instructions into Linux bash commands**.
+
+> ⚠️ This repository contains **LoRA adapters only**, not the base model.  
+> You must load these adapters on top of  
+> **`microsoft/phi-3-mini-128k-instruct`**.
+
+---
+
+## Intended use
+
+The model is trained to output **only valid bash commands**, with no explanations.
+
+**Example**
+
+Input:
+```
+List all .txt files recursively and count lines
+```
+
+Output:
+```bash
+find . -name "*.txt" | xargs wc
+```
+
+## Training summary
+- Base model: microsoft/phi-3-mini-128k-instruct
+- Fine-tuning method: LoRA (PEFT)
+- Trainer: TRL SFTTrainer
+- Dataset: jiacheng-ye/nl2bash
+- Output format: Bash commands only
+
+## Loading example
+```
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+base_model = "microsoft/phi-3-mini-128k-instruct"
+lora_model = "ayertiam/phi3-nl2bash-lora"
+
+tokenizer = AutoTokenizer.from_pretrained(base_model, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    base_model,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    trust_remote_code=True
+)
+
+model = PeftModel.from_pretrained(model, lora_model)
+model.eval()
+```
+
+## Notes
+- These adapters are model-specific and only compatible with `microsoft/phi-3-mini-128k-instruct`.
+- For Ollama or GGUF usage, the LoRA must be merged into the base model and converted before inference.

adapter_config.json

@@ -0,0 +1,18 @@
+{
+  "peft_type": "LORA",
+  "task_type": "CAUSAL_LM",
+  "r": 16,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "bias": "none",
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj"
+  ],
+  "inference_mode": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a2f1114b7f4c5508fd778f7abbc6789caa2f0f2728c3677120760005f5511a8
+size 17842848

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

chat_template.jinja

@@ -0,0 +1,8 @@
+{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>
+' + message['content'] + '<|end|>
+'}}{% elif message['role'] == 'user' %}{{'<|user|>
+' + message['content'] + '<|end|>
+'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>
+' + message['content'] + '<|end|>
+'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
+' }}{% else %}{{ eos_token }}{% endif %}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}