Initial model upload

First commit: LoRA adapter weights and tokenizer files

README.md

@@ -1,3 +1,75 @@
----
-license: apache-2.0
----
+---
+language:
+- en
+license: apache-2.0
+base_model: codellama/CodeLlama-7b-hf
+tags:
+- code
+- python
+- codellama
+- qlora
+- unsloth
+datasets:
+- custom
+pipeline_tag: text-generation
+---
+
+# CodeLlama 7B Python AI Assistant (QLoRA)
+
+Fine-tuned CodeLlama-7B model specialized for Python programming assistance using QLoRA (Quantized Low-Rank Adaptation).
+
+## Model Description
+
+- **Base Model:** [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf)
+- **Fine-tuning Method:** QLoRA (4-bit quantization with LoRA adapters)
+- **Framework:** Unsloth + Transformers
+- **Training Data:** Custom Python programming examples
+
+## Usage
+
+This repository contains **LoRA adapters only**. To use, merge the adapters with the base model.
+
+from unsloth import FastLanguageModel
+
+model, tokenizer = FastLanguageModel.from_pretrained(
+model_name="pranav-pvnn/codellama-7b-python-ai-assistant",
+max_seq_length=2048,
+load_in_4bit=True,
+)
+
+prompt = "### Instruction:\nWrite a Python function to calculate factorial.\n### Response:\n"
+inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+outputs = model.generate(**inputs, max_new_tokens=256)
+print(tokenizer.decode(outputs, skip_special_tokens=True))
+
+## Training Details
+
+- **Quantization:** 4-bit
+- **LoRA Rank:** 64
+- **Learning Rate:** 2e-4
+- **Epochs:** 4
+- **Max Seq Length:** 2048
+- **GPU:** NVIDIA Tesla T4
+
+## Limitations
+
+- Requires base model for inference.
+- Optimized for Python code generation.
+- Trained on custom dataset (~2,000 examples).
+
+## Citation
+
+@misc{codellama-7b-python-assistant,
+author = {pranav-pvnn},
+title = {CodeLlama 7B Python AI Assistant},
+year = {2025},
+publisher = {HuggingFace},
+howpublished = {\url{https://huggingface.co/pranav-pvnn/codellama-7b-python-ai-assistant}}
+}
+
+## Acknowledgements
+
+- Base Model: [Meta's CodeLlama](https://huggingface.co/codellama/CodeLlama-7b-hf)
+- Training Framework: [Unsloth](https://github.com/unslothai/unsloth)
+- Quantization: [bitsandbytes](https://github.com/TimDettmers/bitsandbytes)
+- LoRA: [PEFT](https://github.com/huggingface/peft)

adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/codellama-7b-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "lm_head",
+    "q_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cea4e6f1fb7c2320b0eabac53fa0c84adcab7b43e81ee92162334bc441b72f5
+size 1173487432

special_tokens_map.json

@@ -0,0 +1,40 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>",
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,89 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>",
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "extra_special_tokens": {},
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 16384,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20af52d7015032a985f82985586bbd1becf6523f3f285d9d03ffe5862265b006
+size 5905