Upload Qwen2.5-7B Code LoRA adapter (rank 128, 122K code instructions)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,136 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Qwen/Qwen2.5-7B
+tags:
+  - code-generation
+  - lora
+  - fine-tuned
+  - qwen2
+  - python
+  - transformers
+  - peft
+  - trl
+datasets:
+  - TokenBender/code_instructions_122k_alpaca_style
+language:
+  - en
+pipeline_tag: text-generation
+---
+
+# Qwen2.5-7B Code LoRA
+
+LoRA adapter fine-tuned on [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) for Python code generation.
+
+## Training Summary
+
+| Detail | Value |
+|---|---|
+| Base Model | Qwen/Qwen2.5-7B (7.6B params) |
+| Method | LoRA (rank 128, alpha 64) |
+| Trainable Params | 323M / 7.9B (4.07%) |
+| Dataset | [122K code instructions (Alpaca format)](https://huggingface.co/datasets/TokenBender/code_instructions_122k_alpaca_style) |
+| Train / Eval Split | 115,861 / 6,098 |
+| Epochs | 3 |
+| Effective Batch Size | 32 (16 x 2 gradient accumulation) |
+| Learning Rate | 2e-4 (cosine schedule, 3% warmup) |
+| Max Sequence Length | 2048 (with packing) |
+| Precision | bf16 |
+| Training Time | ~4 hrs 26 min |
+| GPU | NVIDIA RTX PRO 6000 Blackwell (96 GB) |
+| Best Eval Loss | **0.7324** (step 600) |
+| Eval Token Accuracy | **82.7%** |
+
+## LoRA Configuration
+
+- **Rank**: 128
+- **Alpha**: 64
+- **Dropout**: 0.05
+- **Target Modules**: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
+- **Adapter Size**: ~1.2 GB
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+base = AutoModelForCausalLM.from_pretrained(
+    "Qwen/Qwen2.5-7B", dtype=torch.bfloat16, device_map="auto"
+)
+model = PeftModel.from_pretrained(base, "koushikkb12/Qwen2.5-7B-Code-LoRA")
+model = model.merge_and_unload()
+
+tokenizer = AutoTokenizer.from_pretrained("koushikkb12/Qwen2.5-7B-Code-LoRA")
+
+messages = [
+    {"role": "system", "content": "You are a highly skilled Python programmer. Write clean, efficient, and correct code."},
+    {"role": "user", "content": "Write a function to flatten a nested list."},
+]
+text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(text, return_tensors="pt").to(model.device)
+
+with torch.no_grad():
+    out = model.generate(**inputs, max_new_tokens=256, temperature=0.7, top_p=0.9)
+
+print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
+```
+
+## Example Outputs
+
+**Prompt**: *Write a Python function that checks if a given string is a palindrome.*
+```python
+def is_palindrome(s):
+    return s == s[::-1]
+```
+
+**Prompt**: *Implement a binary search algorithm in Python.*
+```python
+def binary_search(arr, target):
+    low, high = 0, len(arr) - 1
+    while low <= high:
+        mid = (low + high) // 2
+        if arr[mid] == target:
+            return mid
+        elif arr[mid] < target:
+            low = mid + 1
+        else:
+            high = mid - 1
+    return -1
+```
+
+**Prompt**: *Write a Python class for a stack with push, pop, peek, and is_empty.*
+```python
+class Stack:
+    def __init__(self):
+        self.items = []
+    def push(self, item):
+        self.items.append(item)
+    def pop(self):
+        if not self.is_empty():
+            return self.items.pop()
+    def peek(self):
+        if not self.is_empty():
+            return self.items[-1]
+    def is_empty(self):
+        return len(self.items) == 0
+```
+
+## Training Curves
+
+| Step | Train Loss | Eval Loss | Eval Token Acc |
+|---|---|---|---|
+| 100 | 0.758 | 0.741 | 82.6% |
+| 200 | 0.749 | 0.737 | 82.6% |
+| 300 | 0.739 | 0.734 | 82.7% |
+| 400 | 0.731 | 0.734 | 82.7% |
+| 500 | 0.720 | 0.733 | 82.7% |
+| 600 | 0.718 | **0.732** | **82.7%** |
+| 700 | 0.725 | 0.734 | 82.7% |
+| 800 | 0.710 | 0.734 | 82.7% |
+| 900 | 0.739 | 0.734 | 82.7% |
+
+## License
+
+This adapter inherits the [Apache 2.0 license](https://www.apache.org/licenses/LICENSE-2.0) from Qwen2.5-7B.

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "o_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:c86b68754732afce1796d985eb74183b49edf674eb2b6eab03e74c97c5424f61
+size 1291899160

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd1aff7a35b248eebb41bc354261742aa196faf9c4a8dfd9f09d6785b0dc444
+size 5649