Upload Qwen3-0.6B fintech LoRA adapter

.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 +1,105 @@
+---
+base_model: Qwen/Qwen3-0.6B
+library_name: peft
+license: apache-2.0
+pipeline_tag: text-generation
+tags:
+- lora
+- peft
+- qwen3
+- fintech
+- structured-generation
+---
+
+# Fintech-Fine-Tune — Qwen3-0.6B + LoRA
+
+A LoRA adapter for [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) that turns natural-language
+fintech commands/questions into a fixed JSON schema, so a downstream system can act on them
+without a rule-based parser.
+
+```
+"can you pay the rent bill, it's $1,249?"
+      -> {"intent": "pay_bill", "entity": "rent", "amount": 1249, "account": null}
+
+"dump 20 shares of META"
+      -> {"intent": "sell_stock", "entity": "META", "amount": 20, "account": "investment"}
+```
+
+Trained entirely on a local CPU (no GPU) using [peft](https://github.com/huggingface/peft) LoRA —
+full training code, dataset, and inference script: [GitHub repo](https://github.com/Gaurav23p24/Fintech-Fine-Tune).
+
+## Output schema
+
+```json
+{"intent": "<one of 20 intents>", "entity": "<string or null>", "amount": "<number or null>", "account": "checking | savings | credit | investment | null"}
+```
+
+Intents: `check_balance`, `transfer_funds`, `pay_bill`, `dispute_transaction`, `freeze_card`,
+`unfreeze_card`, `report_lost_card`, `request_new_card`, `view_transaction_history`,
+`set_spending_alert`, `update_credit_limit`, `apply_for_loan`, `check_loan_status`, `buy_stock`,
+`sell_stock`, `check_portfolio`, `schedule_recurring_payment`, `cancel_recurring_payment`,
+`open_account`, `close_account`.
+
+## Training
+
+| | |
+|---|---|
+| LoRA rank / alpha | 8 / 16 |
+| Target modules | `q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj` |
+| Trainable params | 5,046,272 / 601,096,192 (0.84%) |
+| Epochs | 3 |
+| Effective batch size | 16 (batch 4 × grad-accum 4) |
+| Learning rate | 2e-4, cosine schedule, 3% warmup |
+| Hardware | CPU only, float32 |
+| Data | 450 train / 60 val, synthetic, 20 intents, roughly balanced |
+
+| Epoch | eval_loss |
+|---|---|
+| 1 | 0.0789 |
+| 2 | 0.0265 |
+| 3 (final) | 0.0214 |
+
+## Known limitations
+
+The eval loss above is measured on validation examples generated by the same synthetic process as
+training, so it mostly reflects whether the model learned the *output format*. Testing separately
+on 10 hand-written prompts with fresh wording/entities not in train or val told a more honest
+story:
+
+- **10/10** produced syntactically valid JSON with exactly the 4 expected keys.
+- **7/10** predicted a correct, valid intent.
+- **3/10** hallucinated a plausible-looking `intent` value that isn't in the 20-label taxonomy at
+  all (e.g. `lock_renewable_document` instead of `freeze_card` for "lock my visa, someone jacked
+  it"; `check_revenue` instead of `check_balance` for "how much runway do I have left in
+  checking").
+
+Solid for cleanly-phrased commands close to the training distribution; not yet reliable enough to
+trust blindly on informal or unusual phrasing. Validate `intent` against the known list of 20
+before acting on it downstream.
+
+## Usage
+
+```python
+import torch
+from peft import PeftModel
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+BASE_MODEL = "Qwen/Qwen3-0.6B"
+ADAPTER = "Gaurav8HF/Fintech-Fine-Tune"
+
+tokenizer = AutoTokenizer.from_pretrained(ADAPTER)
+base_model = AutoModelForCausalLM.from_pretrained(BASE_MODEL, dtype=torch.float32)
+model = PeftModel.from_pretrained(base_model, ADAPTER)
+
+messages = [{"role": "user", "content": "freeze my card, I think I lost it"}]
+prompt_ids = tokenizer.apply_chat_template(
+    messages, add_generation_prompt=True, return_tensors="pt", return_dict=False,
+    enable_thinking=False,  # must match training -- Qwen3 normally "thinks" before answering
+)
+out = model.generate(prompt_ids, max_new_tokens=64, do_sample=False, pad_token_id=tokenizer.pad_token_id)
+print(tokenizer.decode(out[0, prompt_ids.shape[1]:], skip_special_tokens=True))
+```
+
+### Framework versions
+
+- PEFT 0.19.1

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "models/qwen3-0.6b",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": 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:db2ba2e050e01f0649e5d7f097dcd106f82670a6bcecfa8cc42602a39be110a3
+size 20236472

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "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": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}