Upload folder using huggingface_hub

README.md

@@ -0,0 +1,207 @@
+---
+base_model: mesolitica/mallam-1.1B-4096
+library_name: peft
+tags:
+- base_model:adapter:mesolitica/mallam-1.1B-4096
+- lora
+- transformers
+- 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 0.18.0

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "MistralForSequenceClassification",
+    "parent_library": "transformers.models.mistral.modeling_mistral",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "mesolitica/mallam-1.1B-4096",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "score",
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:vision|image|visual|patch|language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "target_parameters": null,
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27038373bfb1f4c912169ebb68c07fe2c3553bd712725cdfe144918ff02ccd7d
+size 51232728

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "MistralForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": null,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "Human",
+    "1": "AI"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "label2id": {
+    "AI": 1,
+    "Human": 0
+  },
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.2",
+  "unsloth_version": "2025.12.9",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e9ca4909d24a6b3c47969ddcf19b40d28a7baa108785d6568479cee02ede2dc
+size 2115193376

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e33a6a397bb0abff3b8e1d00d16b716bf44be3bc54c793e842657afd5729dda0
+size 6808693

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:676d22503c81e809760cfc66940b64004d47d0a272b04775176feed24a9541d5
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8597a0eddb2edf7fb48a2a97659c7edd4875a357f2c4644de9a8f0f1e770a30a
+size 1465

special_tokens_map.json

@@ -0,0 +1,36 @@
+{
+  "additional_special_tokens": [
+    "<pad>",
+    "<s>",
+    "</s>",
+    "<unk>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<pad>",
+    "<s>",
+    "</s>",
+    "<unk>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_global_step": 776,
+  "best_metric": 0.9832185886402753,
+  "best_model_checkpoint": "models/mallam-1.1B-4096/checkpoint-776",
+  "epoch": 3.0,
+  "eval_steps": 97,
+  "global_step": 873,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 6.909661769866943,
+      "learning_rate": 0.00019806464107653392,
+      "loss": 0.4528,
+      "step": 97
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "eval_accuracy": 0.943631669535284,
+      "eval_loss": 0.30766424536705017,
+      "eval_runtime": 98.8479,
+      "eval_samples_per_second": 23.511,
+      "eval_steps_per_second": 0.739,
+      "step": 97
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.901430368423462,
+      "learning_rate": 0.00018447743592674295,
+      "loss": 0.2881,
+      "step": 194
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "eval_accuracy": 0.9634251290877797,
+      "eval_loss": 0.2776690423488617,
+      "eval_runtime": 96.8456,
+      "eval_samples_per_second": 23.997,
+      "eval_steps_per_second": 0.754,
+      "step": 194
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 16.644323348999023,
+      "learning_rate": 0.0001596032174304087,
+      "loss": 0.2573,
+      "step": 291
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9625645438898451,
+      "eval_loss": 0.27566397190093994,
+      "eval_runtime": 97.0002,
+      "eval_samples_per_second": 23.959,
+      "eval_steps_per_second": 0.753,
+      "step": 291
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 9.241606712341309,
+      "learning_rate": 0.00012676542495418557,
+      "loss": 0.2303,
+      "step": 388
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "eval_accuracy": 0.9802065404475043,
+      "eval_loss": 0.2352488785982132,
+      "eval_runtime": 96.8829,
+      "eval_samples_per_second": 23.988,
+      "eval_steps_per_second": 0.753,
+      "step": 388
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.41690415143966675,
+      "learning_rate": 9.035150939409222e-05,
+      "loss": 0.2277,
+      "step": 485
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "eval_accuracy": 0.9802065404475043,
+      "eval_loss": 0.2359882891178131,
+      "eval_runtime": 96.6591,
+      "eval_samples_per_second": 24.043,
+      "eval_steps_per_second": 0.755,
+      "step": 485
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 81.69012451171875,
+      "learning_rate": 5.5226726737337866e-05,
+      "loss": 0.2235,
+      "step": 582
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9827882960413081,
+      "eval_loss": 0.23024716973304749,
+      "eval_runtime": 96.8215,
+      "eval_samples_per_second": 24.003,
+      "eval_steps_per_second": 0.754,
+      "step": 582
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.3658274710178375,
+      "learning_rate": 2.6084092181318164e-05,
+      "loss": 0.2111,
+      "step": 679
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "eval_accuracy": 0.9810671256454389,
+      "eval_loss": 0.23341917991638184,
+      "eval_runtime": 96.846,
+      "eval_samples_per_second": 23.997,
+      "eval_steps_per_second": 0.754,
+      "step": 679
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.6265285015106201,
+      "learning_rate": 6.817347310146349e-06,
+      "loss": 0.2102,
+      "step": 776
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "eval_accuracy": 0.9832185886402753,
+      "eval_loss": 0.23051801323890686,
+      "eval_runtime": 96.5673,
+      "eval_samples_per_second": 24.066,
+      "eval_steps_per_second": 0.756,
+      "step": 776
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.2465035915374756,
+      "learning_rate": 7.180590643973694e-10,
+      "loss": 0.2123,
+      "step": 873
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9827882960413081,
+      "eval_loss": 0.2302383929491043,
+      "eval_runtime": 97.1406,
+      "eval_samples_per_second": 23.924,
+      "eval_steps_per_second": 0.751,
+      "step": 873
+    }
+  ],
+  "logging_steps": 97,
+  "max_steps": 873,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 97,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.468789417086157e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e4baebc89e88daac0270a79f49fbd299cd05ec9220e753a4ae8efee586be40a
+size 5905