Copy SinhalaMMLU-SharedTask/team-zeroShot-gemma4-lora

team-zeroShot-gemma4-lora/.gitattributes

@@ -0,0 +1,35 @@
+*.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

team-zeroShot-gemma4-lora/README.md

@@ -0,0 +1,21 @@
+---
+base_model: Lalaa-a/gemma4-8b-text-only
+library_name: peft
+license: gemma
+tags: [sinhala, mmlu, multiple-choice, lora]
+---
+
+# Sinhala MMLU: LoRA adapter + choice head
+
+LoRA adapter (rank 32, all 24 kept layers) for
+[Lalaa-a/gemma4-8b-text-only](https://huggingface.co/Lalaa-a/gemma4-8b-text-only) (text weights of
+google/gemma-4-E4B-it) cut after layer 24, plus `head.pt`: a small transformer choice head that scores each
+option from Gemma's hidden states. Not usable with plain `AutoModelForCausalLM`: load it with the team's
+`inference.py` (main repository), which rebuilds the cut model from `meta.json`.
+
+| File | What |
+|---|---|
+| `lora/` | PEFT adapter (`adapter_config.json`, `adapter_model.safetensors`) |
+| `head.pt` | choice head weights (PyTorch state dict) |
+| `meta.json` | how to rebuild the network: layer cut, head size, token limits, readout |
+| `config.yaml` | the full training config of this checkpoint |

team-zeroShot-gemma4-lora/config.yaml

@@ -0,0 +1,54 @@
+seed: 0
+model:
+  name: Lalaa-a/gemma4-8b-text-only
+  num_layers: 24
+  dtype: bfloat16
+  attn_implementation: sdpa
+  choice_readout: marker
+  gradient_checkpointing: true
+  offload_embeddings: true
+data:
+  max_train_questions: null
+  max_test_questions: 0
+  max_state_tokens: 512
+  max_choice_tokens: 64
+  max_question_tokens: 512
+  batch_size: 4
+  num_workers: 4
+lora:
+  last_k_layers: 24
+  modules: all
+  r: 32
+  alpha: 64
+  dropout: 0.0
+head:
+  new_dim: 512
+  num_layers: 2
+optim:
+  epochs: 2
+  lr_lora: 0.0001
+  lr_head: 0.001
+  weight_decay: 0.01
+  warmup_ratio: 0.05
+  grad_clip: 1.0
+  grad_accum_steps: 4
+logging:
+  log_every: 10
+  eval_every: 100
+  save_every: 876
+distill:
+  enabled: false
+  teacher_ce: 1.0
+  kl: 0.5
+  hidden: 0.5
+  temperature: 2.0
+eval:
+  grade_weights:
+    '6': 179
+    '7': 209
+    '8': 254
+    '9': 93
+    '10': 373
+    '11': 645
+    AL: 485
+  best_metric: accuracy_test_mix

team-zeroShot-gemma4-lora/head.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f86c1353ebcf533e30f74e5daeda6a717206dda6d02b05d5ecca974313106c
+size 73604763

team-zeroShot-gemma4-lora/lora/README.md

@@ -0,0 +1,206 @@
+---
+base_model: /home/ubuntu/gemma_model/models
+library_name: peft
+tags:
+- base_model:adapter:/home/ubuntu/gemma_model/models
+- lora
+- transformers
+---
+
+# 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 0.21.0

team-zeroShot-gemma4-lora/lora/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Gemma4TextModel",
+    "parent_library": "transformers.models.gemma4.modeling_gemma4"
+  },
+  "base_model_name_or_path": "Lalaa-a/gemma4-8b-text-only",
+  "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,
+  "kasa_config": null,
+  "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,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": ".*(layers\\.0\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.0\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.1\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.1\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.2\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.2\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.3\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.3\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.4\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.4\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.5\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.5\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.6\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.6\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.7\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.7\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.8\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.8\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.9\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.9\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.10\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.10\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.11\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.11\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.12\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.12\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.13\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.13\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.14\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.14\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.15\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.15\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.16\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.16\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.17\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.17\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.18\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.18\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.19\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.19\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.20\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.20\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.21\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.21\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.22\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.22\\.mlp\\.(gate_proj|up_proj|down_proj)|layers\\.23\\.self_attn\\.(q_proj|k_proj|v_proj|o_proj)|layers\\.23\\.mlp\\.(gate_proj|up_proj|down_proj))",
+  "target_parameters": null,
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

team-zeroShot-gemma4-lora/lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b63f7f58d31a4fb34145bc9fde515c71f1d4fa3467220b283b977ea741c3e7d
+size 167815144

team-zeroShot-gemma4-lora/meta.json

@@ -0,0 +1,18 @@
+{
+  "exp_id": "v8_final-20261028-182325",
+  "step": 876,
+  "model_name": "Lalaa-a/gemma4-8b-text-only",
+  "num_layers": 24,
+  "dtype": "bfloat16",
+  "attn_implementation": "sdpa",
+  "head_config": {
+    "new_dim": 512,
+    "num_layers": 2
+  },
+  "max_state_tokens": 512,
+  "max_choice_tokens": 64,
+  "max_question_tokens": 512,
+  "choice_readout": "marker",
+  "offload_embeddings": true,
+  "lora_modules": "all"
+}