初始化项目，由ModelHub XC社区提供模型

Model: kartikey31/txn-parser Source: Original Platform
2026-08-09 01:23:21 +08:00
commit f70fa31854
39 changed files with 298378 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,68 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+teacher/adapters/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+teacher/checkpoints/checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+teacher/checkpoints/checkpoint-507/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+teacher/gguf/gemma-4-e2b-it.BF16-mmproj.gguf filter=lfs diff=lfs merge=lfs -text
+teacher/gguf/gemma-4-e2b-it.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+student/adapters/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+student/checkpoints/checkpoint-468/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+student/gguf/gemma-3-270m-it.BF16.gguf filter=lfs diff=lfs merge=lfs -text
+student/gguf/gemma-3-270m-it.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+student/gguf/gemma-3-270m-it.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+student/gguf/gemma-3-270m-it.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+student/gguf/gemma-3-270m-it.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+student/gguf/gemma3_text-fixed.BF16.gguf filter=lfs diff=lfs merge=lfs -text
+student/gguf/gemma3_text-fixed.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+student/gguf/gemma3_text-fixed.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+student/gguf/gemma3_text-fixed.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-270m/adapters/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+gemma-3-270m/gguf/txn-parser-gemma-3-270m-F16.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+smollm2-360m/gguf/txn-parser-smollm2-360m-F16.gguf filter=lfs diff=lfs merge=lfs -text
+smollm2-360m/gguf/txn-parser-smollm2-360m-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+smollm2-360m/gguf/txn-parser-smollm2-360m-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+smollm2-360m/gguf/txn-parser-smollm2-360m-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+smollm2-360m/gguf/txn-parser-smollm2-360m-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+qwen3-0.6b/adapters/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-F16.gguf filter=lfs diff=lfs merge=lfs -text
+qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,152 @@
+---
+license: apache-2.0
+tags:
+  - text-generation
+  - lora
+  - qlora
+  - gguf
+  - transaction-parser
+  - on-device
+language:
+  - en
+  - hi
+library_name: peft
+pipeline_tag: text-generation
+---
+
+# txn-parser
+
+QLoRA fine-tunes of three small base models for extracting structured
+transaction data (amount, currency, item, category, type) from free-form
+Indian-English / code-switched speech and text. Trained on the same
+93k-row teacher-labeled dataset, validator-gated, and quantized to 5 GGUF
+tiers each.
+
+This repo holds **all three published students in side-by-side
+subfolders** so a downstream app can pick its size/quality tradeoff:
+
+| Base model | Subfolder | Params | Best on-device pick |
+|---|---|---:|---|
+| `unsloth/gemma-3-270m-it` | [`gemma-3-270m/`](./tree/main/gemma-3-270m) | 270M | `Q5_K_M` (260 MB, 99.7% schema) |
+| `HuggingFaceTB/SmolLM2-360M-Instruct` | [`smollm2-360m/`](./tree/main/smollm2-360m) | 360M | `Q4_K_M` (271 MB, 100% schema) |
+| `Qwen/Qwen3-0.6B` | [`qwen3-0.6b/`](./tree/main/qwen3-0.6b) | 600M | `Q4_K_M` (397 MB, 100% schema, **best exact match**) |
+
+Each subfolder contains:
+
+```
+<short>/
+├── adapters/                          # PEFT LoRA adapter (load on top of base)
+│   ├── adapter_config.json
+│   └── adapter_model.safetensors
+├── gguf/                              # 5 merged quantizations, ship-ready
+│   ├── txn-parser-<short>-F16.gguf
+│   ├── txn-parser-<short>-Q8_0.gguf
+│   ├── txn-parser-<short>-Q6_K.gguf
+│   ├── txn-parser-<short>-Q5_K_M.gguf
+│   └── txn-parser-<short>-Q4_K_M.gguf
+└── README.md                          # model card with the exact SYSTEM_PROMPT
+```
+
+## Eval (300-example held-out set, grammar-constrained decoding)
+
+| Model | Quant | Size | JSON valid | Schema valid | Exact match | Amount exact | Mean ms |
+|---|---|---:|---:|---:|---:|---:|---:|
+| gemma-3-270m  | Q5_K_M | 260 MB  | 99.7%  | **99.7%**  | 51.0% | 84.7% | 1788 |
+| gemma-3-270m  | Q4_K_M | 253 MB  | 93.3%  |   93.3%   | 48.3% | 80.7% | 2660 |
+| smollm2-360m  | Q5_K_M | 290 MB  | 100.0% | **100.0%** | 52.7% | 89.0% | 996  |
+| smollm2-360m  | Q4_K_M | 271 MB  | 100.0% | **100.0%** | 53.3% | 87.3% | 978  |
+| qwen3-0.6b    | Q5_K_M | 444 MB  | 100.0% | **100.0%** | 60.0% | 91.3% | 857  |
+| qwen3-0.6b    | Q4_K_M | 397 MB  | 100.0% | **100.0%** | 60.0% | 90.7% | 885  |
+
+(Showing Q5_K_M + Q4_K_M only — full 15-row table for all 5 quants is in
+the source repo's `eval_results/REPORT.md`.)
+
+**Recommendations:**
+
+- **Best accuracy on-device:** `qwen3-0.6b-Q4_K_M` (397 MB, 60% exact, ~885 ms)
+- **Smallest ship size:** `smollm2-360m-Q4_K_M` (271 MB, 53% exact, ~978 ms)
+- **Lowest latency:** `qwen3-0.6b-Q8_0` (639 MB, 59% exact, ~851 ms)
+- **Avoid:** `gemma-3-270m-Q4_K_M` — quality cliff vs Q5_K_M (93% → 99.7% schema)
+
+## Quick download
+
+```bash
+# Just one quant of one model (small)
+huggingface-cli download kartikey31/txn-parser \
+    smollm2-360m/gguf/txn-parser-smollm2-360m-Q4_K_M.gguf --local-dir .
+
+# Everything (3 models × 5 quants, ~5 GB)
+huggingface-cli download kartikey31/txn-parser --local-dir ./txn-parser
+```
+
+Or from Python:
+
+```python
+from huggingface_hub import hf_hub_download
+
+gguf = hf_hub_download(
+    "kartikey31/txn-parser",
+    "qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q4_K_M.gguf",
+)
+```
+
+## Inference (llama-cpp-python)
+
+```python
+from llama_cpp import Llama
+
+# Same SYSTEM_PROMPT for ALL three models — they were trained with it.
+SYSTEM_PROMPT = """You convert voice-transcribed transaction descriptions into structured JSON.
+
+Output ONLY a JSON object with this schema, no other text:
+{"transactions":[{"amount":<number>,"currency":"INR"|"USD","item":"<lowercase singular noun phrase>","category":"<enum>","type":"expense"|"income"}]}
+
+Categories: Food, Drinks, Groceries, Transport, Shopping, Entertainment, Bills, Health, Education, Personal, Gifts, Income, Other.
+
+Rules:
+- Currency defaults to INR. Use USD only when the input explicitly says "dollars" or contains "$".
+- Amounts: "k" = ×1000, "hazaar" = ×1000, "sau" = ×100, "lakh" = ×100000. Convert number-words ("five hundred") to digits.
+- type is "expense" by default; "income" only for explicit salary, cashback, refund, gift received, payment received.
+- For disfluencies and corrections ("500 wait no 600"), output the CORRECTED amount only.
+- For ambiguous items ("that thing", "stuff"), use item "unspecified" and category "Other".
+- Item field: lowercase singular noun phrase ("uber ride", "beer", "chai" — not "Beers" or "Uber").
+- Multi-transaction inputs become multiple array entries in spoken order.
+- Category heuristics: uber/ola/auto/petrol/bus/metro → Transport; beer/wine/chai/coffee/juice → Drinks; rent/electricity/wifi/recharge/gas → Bills; movie/netflix/concert → Entertainment; doctor/medicine/hospital → Health."""
+
+llm = Llama(
+    model_path="txn-parser-qwen3-0.6b-Q4_K_M.gguf",
+    n_gpu_layers=-1, n_ctx=1024,
+)
+out = llm.create_chat_completion(messages=[
+    {"role": "system", "content": SYSTEM_PROMPT},
+    {"role": "user",   "content": "200 ka samosa and 50 chai"},
+], temperature=0.0)
+print(out["choices"][0]["message"]["content"])
+# {"transactions":[{"amount":200,"currency":"INR","item":"samosa",...}, ...]}
+```
+
+For Android / on-device deployment guidance (recommended llama.cpp
+params, battery checklist, Kotlin POC), see the [training pipeline
+README](https://github.com/kartikeychoudhary/txn-parser#android-deployment).
+
+## Training pipeline
+
+Full reproduction pipeline (data generation → teacher training →
+distillation → multi-model student training → multi-quant export → eval
+report) lives at
+[`github.com/kartikeychoudhary/txn-parser`](https://github.com/kartikeychoudhary/txn-parser).
+
+A single command reproduces all three models from a fresh checkout:
+
+```bash
+git clone https://github.com/kartikeychoudhary/txn-parser
+cd txn-parser
+bash setup.sh
+python scripts/05_generate_distillation_data.py --phase eval --force-eval-copy
+python scripts/train_and_publish.py    # trains gemma, smollm, qwen; publishes here
+python scripts/eval_all_quants.py      # regenerates the eval table
+```
+
+## License
+
+Apache 2.0 (matches all three base model licenses).
--- a/gemma-3-270m/README.md
+++ b/gemma-3-270m/README.md
@@ -0,0 +1,152 @@
+---
+license: apache-2.0
+base_model: unsloth/gemma-3-270m-it
+tags:
+  - text-generation
+  - lora
+  - qlora
+  - gguf
+  - transaction-parser
+language:
+  - en
+  - hi
+library_name: peft
+---
+
+# txn-parser / gemma-3-270m
+
+QLoRA fine-tune of [`unsloth/gemma-3-270m-it`](https://huggingface.co/unsloth/gemma-3-270m-it) for
+extracting structured transaction data (amount, currency, item, category,
+type) from free-form Indian-English / code-switched speech and text.
+
+This model lives in subfolder **`gemma-3-270m/`** of the
+[`kartikey31/txn-parser`](https://huggingface.co/kartikey31/txn-parser) repo, alongside
+sibling fine-tunes of other base models trained on the same data.
+
+## What's in here
+
+- `gemma-3-270m/adapters/` — PEFT LoRA adapter (rank 32). Load on top of the base model
+  with `peft.PeftModel.from_pretrained(base, "kartikey31/txn-parser", subfolder="gemma-3-270m/adapters")`.
+- `gemma-3-270m/gguf/` — merged GGUF builds at multiple quantization levels
+  (file names follow `txn-parser-gemma-3-270m-<QUANT>.gguf`):
+  - [`gemma-3-270m/gguf/txn-parser-gemma-3-270m-F16.gguf`](https://huggingface.co/kartikey31/txn-parser/resolve/main/gemma-3-270m/gguf/txn-parser-gemma-3-270m-F16.gguf)  (542.8 MB)
+  - [`gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q4_K_M.gguf`](https://huggingface.co/kartikey31/txn-parser/resolve/main/gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q4_K_M.gguf)  (253.1 MB)
+  - [`gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q5_K_M.gguf`](https://huggingface.co/kartikey31/txn-parser/resolve/main/gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q5_K_M.gguf)  (260.0 MB)
+  - [`gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q6_K.gguf`](https://huggingface.co/kartikey31/txn-parser/resolve/main/gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q6_K.gguf)  (283.0 MB)
+  - [`gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q8_0.gguf`](https://huggingface.co/kartikey31/txn-parser/resolve/main/gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q8_0.gguf)  (291.5 MB)
+
+## Training data
+
+- 93,348 teacher-labeled examples (`data/distill/train.jsonl`)
+- 300 held-out eval examples (`data/distill/eval.jsonl`)
+- Validator-gated: every row's `output` passes the project's grammar +
+  amount-parser semantic validator.
+
+## Training config
+
+| Knob | Value |
+|---|---|
+| Base model | `unsloth/gemma-3-270m-it` |
+| Method | QLoRA (4-bit) via Unsloth |
+| LoRA rank | 32 (alpha 64, dropout 0.0) |
+| Epochs | 2 |
+| Batch size (train) | 64 |
+| Grad accumulation | 1 |
+| Eval batch size | 4 |
+| Max seq length | 1024 |
+| Learning rate | 2e-4 (warmup 3%) |
+| Started |  |
+| Finished |  |
+
+## System prompt (use this EXACTLY)
+
+The model was trained with one specific system prompt and Gemma/Smol/Qwen
+chat template. If you paraphrase the prompt or skip the chat template,
+quality degrades quickly. Copy-paste this verbatim into your inference
+client (no leading/trailing whitespace, no edits):
+
+```text
+You convert voice-transcribed transaction descriptions into structured JSON.
+
+Output ONLY a JSON object with this schema, no other text:
+{"transactions":[{"amount":<number>,"currency":"INR"|"USD","item":"<lowercase singular noun phrase>","category":"<enum>","type":"expense"|"income"}]}
+
+Categories: Food, Drinks, Groceries, Transport, Shopping, Entertainment, Bills, Health, Education, Personal, Gifts, Income, Other.
+
+Rules:
+- Currency defaults to INR. Use USD only when the input explicitly says "dollars" or contains "$".
+- Amounts: "k" = ×1000, "hazaar" = ×1000, "sau" = ×100, "lakh" = ×100000. Convert number-words ("five hundred") to digits.
+- type is "expense" by default; "income" only for explicit salary, cashback, refund, gift received, payment received.
+- For disfluencies and corrections ("500 wait no 600"), output the CORRECTED amount only.
+- For ambiguous items ("that thing", "stuff"), use item "unspecified" and category "Other".
+- Item field: lowercase singular noun phrase ("uber ride", "beer", "chai" — not "Beers" or "Uber").
+- Multi-transaction inputs become multiple array entries in spoken order.
+- Category heuristics: uber/ola/auto/petrol/bus/metro → Transport; beer/wine/chai/coffee/juice → Drinks; rent/electricity/wifi/recharge/gas → Bills; movie/netflix/concert → Entertainment; doctor/medicine/hospital → Health.
+```
+
+Source of truth: [`scripts/_lib.py`](https://github.com/kartikeychoudhary/txn-parser/blob/main/scripts/_lib.py)
+constant `SYSTEM_PROMPT`. Don't retype it — pull from `_lib.py` or this README.
+
+## Download a single GGUF
+
+```bash
+huggingface-cli download kartikey31/txn-parser \
+    gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q4_K_M.gguf \
+    --local-dir .
+```
+
+## Inference (Python, llama-cpp-python)
+
+```python
+from llama_cpp import Llama
+
+SYSTEM_PROMPT = '''You convert voice-transcribed transaction descriptions into structured JSON.
+
+Output ONLY a JSON object with this schema, no other text:
+{"transactions":[{"amount":<number>,"currency":"INR"|"USD","item":"<lowercase singular noun phrase>","category":"<enum>","type":"expense"|"income"}]}
+
+Categories: Food, Drinks, Groceries, Transport, Shopping, Entertainment, Bills, Health, Education, Personal, Gifts, Income, Other.
+
+Rules:
+- Currency defaults to INR. Use USD only when the input explicitly says "dollars" or contains "$".
+- Amounts: "k" = ×1000, "hazaar" = ×1000, "sau" = ×100, "lakh" = ×100000. Convert number-words ("five hundred") to digits.
+- type is "expense" by default; "income" only for explicit salary, cashback, refund, gift received, payment received.
+- For disfluencies and corrections ("500 wait no 600"), output the CORRECTED amount only.
+- For ambiguous items ("that thing", "stuff"), use item "unspecified" and category "Other".
+- Item field: lowercase singular noun phrase ("uber ride", "beer", "chai" — not "Beers" or "Uber").
+- Multi-transaction inputs become multiple array entries in spoken order.
+- Category heuristics: uber/ola/auto/petrol/bus/metro → Transport; beer/wine/chai/coffee/juice → Drinks; rent/electricity/wifi/recharge/gas → Bills; movie/netflix/concert → Entertainment; doctor/medicine/hospital → Health.'''
+
+llm = Llama(
+    model_path="txn-parser-gemma-3-270m-Q4_K_M.gguf",
+    n_gpu_layers=-1, n_ctx=2048,
+)
+out = llm.create_chat_completion(
+    messages=[
+        {"role": "system", "content": SYSTEM_PROMPT},
+        {"role": "user",   "content": "200 ka samosa"},
+    ],
+    temperature=0.0,
+)
+print(out["choices"][0]["message"]["content"])
+```
+
+## Inference (CLI, llama.cpp)
+
+```bash
+./llama-cli -m txn-parser-gemma-3-270m-Q4_K_M.gguf \
+    --grammar-file scripts/grammar.gbnf \
+    --system-prompt "$(cat system_prompt.txt)" \
+    -p "200 ka samosa" -n 256
+```
+
+## Reproduce
+
+```bash
+git clone https://github.com/kartikeychoudhary/txn-parser.git
+cd txn-parser && bash setup.sh
+python scripts/train_and_publish.py --only gemma-3-270m
+```
+
+---
+*Auto-published by `scripts/train_and_publish.py` on 2026-05-22T21:33:31.274220+00:00.*
--- a/gemma-3-270m/adapters/README.md
+++ b/gemma-3-270m/adapters/README.md
@@ -0,0 +1,210 @@
+---
+base_model: unsloth/gemma-3-270m-it-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/gemma-3-270m-it-unsloth-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1
--- a/gemma-3-270m/adapters/adapter_config.json
+++ b/gemma-3-270m/adapters/adapter_config.json
@@ -0,0 +1,52 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Gemma3ForCausalLM",
+    "parent_library": "transformers.models.gemma3.modeling_gemma3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/gemma-3-270m-it-unsloth-bnb-4bit",
+  "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": 0.0,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
--- a/gemma-3-270m/adapters/adapter_model.safetensors
+++ b/gemma-3-270m/adapters/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45b973b84902da8d42103cebe35f1fd7ccd477e0ac8b65edd5cc01e86962f015
+size 30409120
--- a/gemma-3-270m/adapters/chat_template.jinja
+++ b/gemma-3-270m/adapters/chat_template.jinja
@@ -0,0 +1,50 @@
+{# Unsloth Chat template fixes #}
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- elif message['content'] is defined -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}
+
+{# Copyright 2025-present Unsloth. Apache 2.0 License. #}
--- a/gemma-3-270m/adapters/tokenizer.json
+++ b/gemma-3-270m/adapters/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
+size 33384567
--- a/gemma-3-270m/adapters/tokenizer.model
+++ b/gemma-3-270m/adapters/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074
--- a/gemma-3-270m/adapters/tokenizer_config.json
+++ b/gemma-3-270m/adapters/tokenizer_config.json
--- a/gemma-3-270m/gguf/txn-parser-gemma-3-270m-F16.gguf
+++ b/gemma-3-270m/gguf/txn-parser-gemma-3-270m-F16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68d695f4376c7e60e1ebbffd39ec241e4ba713fe0214fd0a807e1aef7d303cbb
+size 542835136
--- a/gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q4_K_M.gguf
+++ b/gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b712099c6e1a1d96c02925983b5552297686054dfd38055d126596587168f95a
+size 253114816
--- a/gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q5_K_M.gguf
+++ b/gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f6998034ce51ce7227621930e95b0970a667e2eedb8aec04a18745ee9bbbffb
+size 260026816
--- a/gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q6_K.gguf
+++ b/gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44d85853e661a49e49be8177577431c98e2940951c98239b6e80b855fa3391c8
+size 282974656
--- a/gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q8_0.gguf
+++ b/gemma-3-270m/gguf/txn-parser-gemma-3-270m-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63f2d561d816946561952bacb8f076d60e622cf36995c5fd988a930475da95d7
+size 291545536
--- a/qwen3-0.6b/README.md
+++ b/qwen3-0.6b/README.md
@@ -0,0 +1,152 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-0.6B
+tags:
+  - text-generation
+  - lora
+  - qlora
+  - gguf
+  - transaction-parser
+language:
+  - en
+  - hi
+library_name: peft
+---
+
+# txn-parser / qwen3-0.6b
+
+QLoRA fine-tune of [`Qwen/Qwen3-0.6B`](https://huggingface.co/Qwen/Qwen3-0.6B) for
+extracting structured transaction data (amount, currency, item, category,
+type) from free-form Indian-English / code-switched speech and text.
+
+This model lives in subfolder **`qwen3-0.6b/`** of the
+[`kartikey31/txn-parser`](https://huggingface.co/kartikey31/txn-parser) repo, alongside
+sibling fine-tunes of other base models trained on the same data.
+
+## What's in here
+
+- `qwen3-0.6b/adapters/` — PEFT LoRA adapter (rank 32). Load on top of the base model
+  with `peft.PeftModel.from_pretrained(base, "kartikey31/txn-parser", subfolder="qwen3-0.6b/adapters")`.
+- `qwen3-0.6b/gguf/` — merged GGUF builds at multiple quantization levels
+  (file names follow `txn-parser-qwen3-0.6b-<QUANT>.gguf`):
+  - [`qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-F16.gguf`](https://huggingface.co/kartikey31/txn-parser/resolve/main/qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-F16.gguf)  (1198.2 MB)
+  - [`qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q4_K_M.gguf`](https://huggingface.co/kartikey31/txn-parser/resolve/main/qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q4_K_M.gguf)  (396.7 MB)
+  - [`qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q5_K_M.gguf`](https://huggingface.co/kartikey31/txn-parser/resolve/main/qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q5_K_M.gguf)  (444.4 MB)
+  - [`qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q6_K.gguf`](https://huggingface.co/kartikey31/txn-parser/resolve/main/qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q6_K.gguf)  (495.1 MB)
+  - [`qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q8_0.gguf`](https://huggingface.co/kartikey31/txn-parser/resolve/main/qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q8_0.gguf)  (639.4 MB)
+
+## Training data
+
+- 93,348 teacher-labeled examples (`data/distill/train.jsonl`)
+- 300 held-out eval examples (`data/distill/eval.jsonl`)
+- Validator-gated: every row's `output` passes the project's grammar +
+  amount-parser semantic validator.
+
+## Training config
+
+| Knob | Value |
+|---|---|
+| Base model | `Qwen/Qwen3-0.6B` |
+| Method | QLoRA (4-bit) via Unsloth |
+| LoRA rank | 32 (alpha 64, dropout 0.0) |
+| Epochs | 2 |
+| Batch size (train) | 64 |
+| Grad accumulation | 2 |
+| Eval batch size | 16 |
+| Max seq length | 1024 |
+| Learning rate | 2e-4 (warmup 3%) |
+| Started | 2026-05-22T21:54:03.967900+00:00 |
+| Finished | 2026-05-22T22:42:56.089528+00:00 |
+
+## System prompt (use this EXACTLY)
+
+The model was trained with one specific system prompt and Gemma/Smol/Qwen
+chat template. If you paraphrase the prompt or skip the chat template,
+quality degrades quickly. Copy-paste this verbatim into your inference
+client (no leading/trailing whitespace, no edits):
+
+```text
+You convert voice-transcribed transaction descriptions into structured JSON.
+
+Output ONLY a JSON object with this schema, no other text:
+{"transactions":[{"amount":<number>,"currency":"INR"|"USD","item":"<lowercase singular noun phrase>","category":"<enum>","type":"expense"|"income"}]}
+
+Categories: Food, Drinks, Groceries, Transport, Shopping, Entertainment, Bills, Health, Education, Personal, Gifts, Income, Other.
+
+Rules:
+- Currency defaults to INR. Use USD only when the input explicitly says "dollars" or contains "$".
+- Amounts: "k" = ×1000, "hazaar" = ×1000, "sau" = ×100, "lakh" = ×100000. Convert number-words ("five hundred") to digits.
+- type is "expense" by default; "income" only for explicit salary, cashback, refund, gift received, payment received.
+- For disfluencies and corrections ("500 wait no 600"), output the CORRECTED amount only.
+- For ambiguous items ("that thing", "stuff"), use item "unspecified" and category "Other".
+- Item field: lowercase singular noun phrase ("uber ride", "beer", "chai" — not "Beers" or "Uber").
+- Multi-transaction inputs become multiple array entries in spoken order.
+- Category heuristics: uber/ola/auto/petrol/bus/metro → Transport; beer/wine/chai/coffee/juice → Drinks; rent/electricity/wifi/recharge/gas → Bills; movie/netflix/concert → Entertainment; doctor/medicine/hospital → Health.
+```
+
+Source of truth: [`scripts/_lib.py`](https://github.com/kartikeychoudhary/txn-parser/blob/main/scripts/_lib.py)
+constant `SYSTEM_PROMPT`. Don't retype it — pull from `_lib.py` or this README.
+
+## Download a single GGUF
+
+```bash
+huggingface-cli download kartikey31/txn-parser \
+    qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q4_K_M.gguf \
+    --local-dir .
+```
+
+## Inference (Python, llama-cpp-python)
+
+```python
+from llama_cpp import Llama
+
+SYSTEM_PROMPT = '''You convert voice-transcribed transaction descriptions into structured JSON.
+
+Output ONLY a JSON object with this schema, no other text:
+{"transactions":[{"amount":<number>,"currency":"INR"|"USD","item":"<lowercase singular noun phrase>","category":"<enum>","type":"expense"|"income"}]}
+
+Categories: Food, Drinks, Groceries, Transport, Shopping, Entertainment, Bills, Health, Education, Personal, Gifts, Income, Other.
+
+Rules:
+- Currency defaults to INR. Use USD only when the input explicitly says "dollars" or contains "$".
+- Amounts: "k" = ×1000, "hazaar" = ×1000, "sau" = ×100, "lakh" = ×100000. Convert number-words ("five hundred") to digits.
+- type is "expense" by default; "income" only for explicit salary, cashback, refund, gift received, payment received.
+- For disfluencies and corrections ("500 wait no 600"), output the CORRECTED amount only.
+- For ambiguous items ("that thing", "stuff"), use item "unspecified" and category "Other".
+- Item field: lowercase singular noun phrase ("uber ride", "beer", "chai" — not "Beers" or "Uber").
+- Multi-transaction inputs become multiple array entries in spoken order.
+- Category heuristics: uber/ola/auto/petrol/bus/metro → Transport; beer/wine/chai/coffee/juice → Drinks; rent/electricity/wifi/recharge/gas → Bills; movie/netflix/concert → Entertainment; doctor/medicine/hospital → Health.'''
+
+llm = Llama(
+    model_path="txn-parser-qwen3-0.6b-Q4_K_M.gguf",
+    n_gpu_layers=-1, n_ctx=2048,
+)
+out = llm.create_chat_completion(
+    messages=[
+        {"role": "system", "content": SYSTEM_PROMPT},
+        {"role": "user",   "content": "200 ka samosa"},
+    ],
+    temperature=0.0,
+)
+print(out["choices"][0]["message"]["content"])
+```
+
+## Inference (CLI, llama.cpp)
+
+```bash
+./llama-cli -m txn-parser-qwen3-0.6b-Q4_K_M.gguf \
+    --grammar-file scripts/grammar.gbnf \
+    --system-prompt "$(cat system_prompt.txt)" \
+    -p "200 ka samosa" -n 256
+```
+
+## Reproduce
+
+```bash
+git clone https://github.com/kartikeychoudhary/txn-parser.git
+cd txn-parser && bash setup.sh
+python scripts/train_and_publish.py --only qwen3-0.6b
+```
+
+---
+*Auto-published by `scripts/train_and_publish.py` on 2026-05-22T22:42:56.387243+00:00.*
--- a/qwen3-0.6b/adapters/README.md
+++ b/qwen3-0.6b/adapters/README.md
@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen3-0.6b-unsloth-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen3-0.6b-unsloth-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1
--- a/qwen3-0.6b/adapters/adapter_config.json
+++ b/qwen3-0.6b/adapters/adapter_config.json
@@ -0,0 +1,52 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen3-0.6b-unsloth-bnb-4bit",
+  "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": 0.0,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
--- a/qwen3-0.6b/adapters/adapter_model.safetensors
+++ b/qwen3-0.6b/adapters/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f6aa46ce50ec9c526a0975f8ba80ad831031edf618be46972dd81425e8e61e3
+size 80792456
--- a/qwen3-0.6b/adapters/chat_template.jinja
+++ b/qwen3-0.6b/adapters/chat_template.jinja
@@ -0,0 +1,99 @@
+{%- 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 forward_message in messages %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- set message = messages[index] %}
+    {%- set current_content = message.content if message.content is defined and message.content is not none else '' %}
+    {%- set tool_start = '<tool_response>' %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = current_content[:tool_start_length] %}
+    {%- set tool_end = '</tool_response>' %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (current_content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = current_content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set m_content = message.content if message.content is defined and message.content is not none else '' %}
+        {%- set content = m_content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in m_content %}
+                {%- set content = (m_content.split('</think>')|last).lstrip('\n') %}
+                {%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\n') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}
+                {{- '<|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' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
--- a/qwen3-0.6b/adapters/tokenizer.json
+++ b/qwen3-0.6b/adapters/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7430e9138b76e93fb6f93462394d236b411111aef53cb421ba97d2691040cca
+size 11423114
--- a/qwen3-0.6b/adapters/tokenizer_config.json
+++ b/qwen3-0.6b/adapters/tokenizer_config.json
@@ -0,0 +1,233 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 40960,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151669": {
+      "content": "<|PAD_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}
--- a/qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-F16.gguf
+++ b/qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-F16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:141d507c4393251443afe63236d594f6b8c45f22cb546ff4076461ef53d9a9c1
+size 1198182944
--- a/qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q4_K_M.gguf
+++ b/qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d15b8fb273552fc9b1c6bc347185767e2f3dc0437a1cb14575080a2c5407bc8
+size 396705312
--- a/qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q5_K_M.gguf
+++ b/qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b09c532c64fd3b75eab6abc628329e1530242b350f54ef206c174c0fdbf2d68
+size 444415520
--- a/qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q6_K.gguf
+++ b/qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57a7472c85fe51c5205783e1d81aea69fff4fa4df5ae3edbf9b5e58bf0392937
+size 495107616
--- a/qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q8_0.gguf
+++ b/qwen3-0.6b/gguf/txn-parser-qwen3-0.6b-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b64fb71f6c9775fb2e73c3514109e640787bca28b2f67aec1e76c37ed71dffc
+size 639447584
--- a/smollm2-360m/README.md
+++ b/smollm2-360m/README.md
@@ -0,0 +1,152 @@
+---
+license: apache-2.0
+base_model: HuggingFaceTB/SmolLM2-360M-Instruct
+tags:
+  - text-generation
+  - lora
+  - qlora
+  - gguf
+  - transaction-parser
+language:
+  - en
+  - hi
+library_name: peft
+---
+
+# txn-parser / smollm2-360m
+
+QLoRA fine-tune of [`HuggingFaceTB/SmolLM2-360M-Instruct`](https://huggingface.co/HuggingFaceTB/SmolLM2-360M-Instruct) for
+extracting structured transaction data (amount, currency, item, category,
+type) from free-form Indian-English / code-switched speech and text.
+
+This model lives in subfolder **`smollm2-360m/`** of the
+[`kartikey31/txn-parser`](https://huggingface.co/kartikey31/txn-parser) repo, alongside
+sibling fine-tunes of other base models trained on the same data.
+
+## What's in here
+
+- `smollm2-360m/adapters/` — PEFT LoRA adapter (rank 32). Load on top of the base model
+  with `peft.PeftModel.from_pretrained(base, "kartikey31/txn-parser", subfolder="smollm2-360m/adapters")`.
+- `smollm2-360m/gguf/` — merged GGUF builds at multiple quantization levels
+  (file names follow `txn-parser-smollm2-360m-<QUANT>.gguf`):
+  - [`smollm2-360m/gguf/txn-parser-smollm2-360m-F16.gguf`](https://huggingface.co/kartikey31/txn-parser/resolve/main/smollm2-360m/gguf/txn-parser-smollm2-360m-F16.gguf)  (725.6 MB)
+  - [`smollm2-360m/gguf/txn-parser-smollm2-360m-Q4_K_M.gguf`](https://huggingface.co/kartikey31/txn-parser/resolve/main/smollm2-360m/gguf/txn-parser-smollm2-360m-Q4_K_M.gguf)  (270.6 MB)
+  - [`smollm2-360m/gguf/txn-parser-smollm2-360m-Q5_K_M.gguf`](https://huggingface.co/kartikey31/txn-parser/resolve/main/smollm2-360m/gguf/txn-parser-smollm2-360m-Q5_K_M.gguf)  (289.9 MB)
+  - [`smollm2-360m/gguf/txn-parser-smollm2-360m-Q6_K.gguf`](https://huggingface.co/kartikey31/txn-parser/resolve/main/smollm2-360m/gguf/txn-parser-smollm2-360m-Q6_K.gguf)  (367.4 MB)
+  - [`smollm2-360m/gguf/txn-parser-smollm2-360m-Q8_0.gguf`](https://huggingface.co/kartikey31/txn-parser/resolve/main/smollm2-360m/gguf/txn-parser-smollm2-360m-Q8_0.gguf)  (386.4 MB)
+
+## Training data
+
+- 93,348 teacher-labeled examples (`data/distill/train.jsonl`)
+- 300 held-out eval examples (`data/distill/eval.jsonl`)
+- Validator-gated: every row's `output` passes the project's grammar +
+  amount-parser semantic validator.
+
+## Training config
+
+| Knob | Value |
+|---|---|
+| Base model | `HuggingFaceTB/SmolLM2-360M-Instruct` |
+| Method | QLoRA (4-bit) via Unsloth |
+| LoRA rank | 32 (alpha 64, dropout 0.0) |
+| Epochs | 2 |
+| Batch size (train) | 64 |
+| Grad accumulation | 1 |
+| Eval batch size | 16 |
+| Max seq length | 1024 |
+| Learning rate | 2e-4 (warmup 3%) |
+| Started | 2026-05-22T21:26:43.776899+00:00 |
+| Finished | 2026-05-22T21:30:14.660709+00:00 |
+
+## System prompt (use this EXACTLY)
+
+The model was trained with one specific system prompt and Gemma/Smol/Qwen
+chat template. If you paraphrase the prompt or skip the chat template,
+quality degrades quickly. Copy-paste this verbatim into your inference
+client (no leading/trailing whitespace, no edits):
+
+```text
+You convert voice-transcribed transaction descriptions into structured JSON.
+
+Output ONLY a JSON object with this schema, no other text:
+{"transactions":[{"amount":<number>,"currency":"INR"|"USD","item":"<lowercase singular noun phrase>","category":"<enum>","type":"expense"|"income"}]}
+
+Categories: Food, Drinks, Groceries, Transport, Shopping, Entertainment, Bills, Health, Education, Personal, Gifts, Income, Other.
+
+Rules:
+- Currency defaults to INR. Use USD only when the input explicitly says "dollars" or contains "$".
+- Amounts: "k" = ×1000, "hazaar" = ×1000, "sau" = ×100, "lakh" = ×100000. Convert number-words ("five hundred") to digits.
+- type is "expense" by default; "income" only for explicit salary, cashback, refund, gift received, payment received.
+- For disfluencies and corrections ("500 wait no 600"), output the CORRECTED amount only.
+- For ambiguous items ("that thing", "stuff"), use item "unspecified" and category "Other".
+- Item field: lowercase singular noun phrase ("uber ride", "beer", "chai" — not "Beers" or "Uber").
+- Multi-transaction inputs become multiple array entries in spoken order.
+- Category heuristics: uber/ola/auto/petrol/bus/metro → Transport; beer/wine/chai/coffee/juice → Drinks; rent/electricity/wifi/recharge/gas → Bills; movie/netflix/concert → Entertainment; doctor/medicine/hospital → Health.
+```
+
+Source of truth: [`scripts/_lib.py`](https://github.com/kartikeychoudhary/txn-parser/blob/main/scripts/_lib.py)
+constant `SYSTEM_PROMPT`. Don't retype it — pull from `_lib.py` or this README.
+
+## Download a single GGUF
+
+```bash
+huggingface-cli download kartikey31/txn-parser \
+    smollm2-360m/gguf/txn-parser-smollm2-360m-Q4_K_M.gguf \
+    --local-dir .
+```
+
+## Inference (Python, llama-cpp-python)
+
+```python
+from llama_cpp import Llama
+
+SYSTEM_PROMPT = '''You convert voice-transcribed transaction descriptions into structured JSON.
+
+Output ONLY a JSON object with this schema, no other text:
+{"transactions":[{"amount":<number>,"currency":"INR"|"USD","item":"<lowercase singular noun phrase>","category":"<enum>","type":"expense"|"income"}]}
+
+Categories: Food, Drinks, Groceries, Transport, Shopping, Entertainment, Bills, Health, Education, Personal, Gifts, Income, Other.
+
+Rules:
+- Currency defaults to INR. Use USD only when the input explicitly says "dollars" or contains "$".
+- Amounts: "k" = ×1000, "hazaar" = ×1000, "sau" = ×100, "lakh" = ×100000. Convert number-words ("five hundred") to digits.
+- type is "expense" by default; "income" only for explicit salary, cashback, refund, gift received, payment received.
+- For disfluencies and corrections ("500 wait no 600"), output the CORRECTED amount only.
+- For ambiguous items ("that thing", "stuff"), use item "unspecified" and category "Other".
+- Item field: lowercase singular noun phrase ("uber ride", "beer", "chai" — not "Beers" or "Uber").
+- Multi-transaction inputs become multiple array entries in spoken order.
+- Category heuristics: uber/ola/auto/petrol/bus/metro → Transport; beer/wine/chai/coffee/juice → Drinks; rent/electricity/wifi/recharge/gas → Bills; movie/netflix/concert → Entertainment; doctor/medicine/hospital → Health.'''
+
+llm = Llama(
+    model_path="txn-parser-smollm2-360m-Q4_K_M.gguf",
+    n_gpu_layers=-1, n_ctx=2048,
+)
+out = llm.create_chat_completion(
+    messages=[
+        {"role": "system", "content": SYSTEM_PROMPT},
+        {"role": "user",   "content": "200 ka samosa"},
+    ],
+    temperature=0.0,
+)
+print(out["choices"][0]["message"]["content"])
+```
+
+## Inference (CLI, llama.cpp)
+
+```bash
+./llama-cli -m txn-parser-smollm2-360m-Q4_K_M.gguf \
+    --grammar-file scripts/grammar.gbnf \
+    --system-prompt "$(cat system_prompt.txt)" \
+    -p "200 ka samosa" -n 256
+```
+
+## Reproduce
+
+```bash
+git clone https://github.com/kartikeychoudhary/txn-parser.git
+cd txn-parser && bash setup.sh
+python scripts/train_and_publish.py --only smollm2-360m
+```
+
+---
+*Auto-published by `scripts/train_and_publish.py` on 2026-05-22T21:30:14.964463+00:00.*
--- a/smollm2-360m/adapters/README.md
+++ b/smollm2-360m/adapters/README.md
@@ -0,0 +1,210 @@
+---
+base_model: HuggingFaceTB/SmolLM2-360M-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:HuggingFaceTB/SmolLM2-360M-Instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1
--- a/smollm2-360m/adapters/adapter_config.json
+++ b/smollm2-360m/adapters/adapter_config.json
@@ -0,0 +1,52 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "LlamaForCausalLM",
+    "parent_library": "transformers.models.llama.modeling_llama",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "HuggingFaceTB/SmolLM2-360M-Instruct",
+  "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": 0.0,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}
--- a/smollm2-360m/adapters/adapter_model.safetensors
+++ b/smollm2-360m/adapters/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b4d482a8fd5bb463dd858f9d8b576759471cf800f45e12660cfc22090988dae
+size 69527352
--- a/smollm2-360m/adapters/chat_template.jinja
+++ b/smollm2-360m/adapters/chat_template.jinja
@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}
--- a/smollm2-360m/adapters/tokenizer.json
+++ b/smollm2-360m/adapters/tokenizer.json
--- a/smollm2-360m/adapters/tokenizer_config.json
+++ b/smollm2-360m/adapters/tokenizer_config.json
@@ -0,0 +1,154 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 8192,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}
--- a/smollm2-360m/gguf/txn-parser-smollm2-360m-F16.gguf
+++ b/smollm2-360m/gguf/txn-parser-smollm2-360m-F16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92b07b803de61d1fd4ec1297001bef5e60d0e6859d92e6faedbfa2d5acb4dbce
+size 725553792
--- a/smollm2-360m/gguf/txn-parser-smollm2-360m-Q4_K_M.gguf
+++ b/smollm2-360m/gguf/txn-parser-smollm2-360m-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4edeff22ebbb1eabc5ab89624f2ecd5202af034cea61fe0ccd422e4e586505
+size 270590592
--- a/smollm2-360m/gguf/txn-parser-smollm2-360m-Q5_K_M.gguf
+++ b/smollm2-360m/gguf/txn-parser-smollm2-360m-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc8df0629cc58887b569c77d9f12aea04f70dbfeaf57431b2eedd5c220ba9ba1
+size 289944192
--- a/smollm2-360m/gguf/txn-parser-smollm2-360m-Q6_K.gguf
+++ b/smollm2-360m/gguf/txn-parser-smollm2-360m-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:193c4b51e556101707420668b1df4770e32f13e7553fd1f6a12c877de3e99dec
+size 367358592
--- a/smollm2-360m/gguf/txn-parser-smollm2-360m-Q8_0.gguf
+++ b/smollm2-360m/gguf/txn-parser-smollm2-360m-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1714b9ae16ada16ea318342661ffbf9d73295d9f42b7c6e33bf10e3dd7af03
+size 386404992