Uploading LoRA adapters for distillation project

.gitattributes

@@ -38,3 +38,5 @@ qwen3_6_35b/Qwen_Qwen3.6-35B-A3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 qwen3_14b/checkpoint-505/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen3_14b/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen3_14b/checkpoint-450/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+adapters/qwen3.5_4b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+adapters/qwen3_14b/tokenizer.json filter=lfs diff=lfs merge=lfs -text

adapters/qwen3.5_4b/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3.5-4B
+library_name: peft
+---
+
+# 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 0.15.0

adapters/qwen3.5_4b/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-4B",
+  "bias": "none",
+  "corda_config": null,
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapters/qwen3.5_4b/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36cc79b2703fd5263160c4d69141f1314b19d470d12931588c9b09c0aa981c31
+size 84968408

adapters/qwen3.5_4b/best/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-4B",
+  "bias": "none",
+  "corda_config": null,
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapters/qwen3.5_4b/best/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2905d619be38e606fefbaa11657950113f5c83719dd5a4414838bb4ef9a944c
+size 84968408

adapters/qwen3.5_4b/chat_template.jinja

@@ -0,0 +1,4 @@
+{%- for message in messages %}{{- '<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>
+' }}{%- endfor %}{%- if add_generation_prompt %}{{- '<|im_start|>assistant
+' }}{%- endif %}

adapters/qwen3.5_4b/run_config.json

@@ -0,0 +1,103 @@
+{
+  "project": "DEI_tweet_classification",
+  "version": "v1.1",
+  "timestamp_utc": "2026-04-21T15:49:54.144744+00:00",
+  "base_model": "Qwen/Qwen3.5-4B",
+  "adapter_path": "/content/drive/MyDrive/Twitter/Finetune/adapters/qwen3.5_4b",
+  "split_config": {
+    "source_file": "/content/drive/MyDrive/Twitter/Finetune/data/processed/merged_4k_v2_train.csv",
+    "strategy": "stratified_in_memory",
+    "val_split_ratio": 0.2,
+    "train_size": 2884,
+    "val_size": 722,
+    "seed": 42,
+    "note": "No separate val file. Val created in Block 1.5 via sklearn train_test_split(stratify=DEI, random_state=42)."
+  },
+  "training": {
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "gradient_accumulation_steps": 8,
+    "effective_batch_size": 32,
+    "learning_rate": 0.0001,
+    "weight_decay": 0.01,
+    "lr_scheduler_type": "cosine",
+    "warmup_ratio": 0.1,
+    "max_seq_length": 768,
+    "fp16": true,
+    "bf16": false,
+    "optim": "paged_adamw_8bit",
+    "gradient_checkpointing": true,
+    "seed": 42
+  },
+  "lora": {
+    "r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.1,
+    "bias": "none",
+    "target_modules": [
+      "down_proj",
+      "up_proj",
+      "o_proj",
+      "k_proj",
+      "q_proj",
+      "v_proj",
+      "gate_proj"
+    ]
+  },
+  "quantisation": {
+    "load_in_4bit": true,
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "bnb_4bit_compute_dtype": "float16"
+  },
+  "data": {
+    "class_weight_0": 1.0,
+    "class_weight_1": 1.0,
+    "label_token_id_0": 15,
+    "label_token_id_1": 16
+  },
+  "results": {
+    "final_f1_macro": 0.907151,
+    "best_epoch": 3.0,
+    "parse_failure_rate_pct": 0.0,
+    "eval_metrics": {
+      "accuracy": 0.905817,
+      "f1_macro": 0.905745,
+      "f1_class_0": 0.908356,
+      "f1_class_1": 0.903134,
+      "precision_class_0": 0.884514,
+      "precision_class_1": 0.929619,
+      "recall_class_0": 0.933518,
+      "recall_class_1": 0.878116,
+      "auc_roc": 0.966414,
+      "parse_failure_rate_pct": 0.0,
+      "n_valid": 722,
+      "n_failures": 0,
+      "n_total": 722,
+      "val_size": 722,
+      "train_size": 2884,
+      "val_split_ratio": 0.2,
+      "confusion_matrix": [
+        [
+          337,
+          24
+        ],
+        [
+          44,
+          317
+        ]
+      ],
+      "generation_params": {
+        "max_new_tokens": 3,
+        "do_sample": false,
+        "decoding": "greedy"
+      }
+    }
+  },
+  "inference": {
+    "parser_function": "parse_model_output",
+    "parser_spec": "strip_think_tokens \u2192 first char \u2192 0/1/-1",
+    "threshold": 0.65,
+    "phase2_note": "Load Qwen/Qwen3.5-4B + this adapter via PeftModel. Use greedy decoding, max_new_tokens=3. Apply parse_model_output() to each output."
+  }
+}

adapters/qwen3.5_4b/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5d265cc05c1b19754889b820e7cb52dd72b7686a02a3c3684dca86c7603c498
+size 19989608

adapters/qwen3.5_4b/tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

adapters/qwen3_14b/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /content/drive/MyDrive/Twitter/Finetune/judge/model_weights/qwen3_14b
+library_name: peft
+---
+
+# 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 0.15.0

adapters/qwen3_14b/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/content/drive/MyDrive/Twitter/Finetune/judge/model_weights/qwen3_14b",
+  "bias": "none",
+  "corda_config": null,
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapters/qwen3_14b/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b372d905631dca4073d3589d0cd20608525ba2eeb715cd92c56095ca69654e9
+size 256976504

adapters/qwen3_14b/best/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/content/drive/MyDrive/Twitter/Finetune/judge/model_weights/qwen3_14b",
+  "bias": "none",
+  "corda_config": null,
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapters/qwen3_14b/best/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:680dcd02a906e0384cce42878e6e28497385136d6b4856cf7ff53c94c86c557c
+size 256976504

adapters/qwen3_14b/chat_template.jinja

@@ -0,0 +1,4 @@
+{%- for message in messages %}{{- '<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>
+' }}{%- endfor %}{%- if add_generation_prompt %}{{- '<|im_start|>assistant
+' }}{%- endif %}

adapters/qwen3_14b/run_config.json

@@ -0,0 +1,74 @@
+{
+  "project": "DEI_tweet_classification",
+  "version": "v1.0",
+  "timestamp_utc": "2026-05-09T03:24:23.380760+00:00",
+  "base_model": "/content/drive/MyDrive/Twitter/Finetune/judge/model_weights/qwen3_14b",
+  "adapter_path": "/content/drive/MyDrive/Twitter/Finetune/adapters/qwen3_14b",
+  "training": {
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 1,
+    "gradient_accumulation_steps": 32,
+    "effective_batch_size": 32,
+    "learning_rate": 0.0002,
+    "lr_scheduler_type": "cosine",
+    "warmup_ratio": 0.1,
+    "max_seq_length": 512,
+    "fp16": true,
+    "bf16": false,
+    "optim": "paged_adamw_8bit",
+    "gradient_checkpointing": true,
+    "seed": 42,
+    "flash_attention_2": false
+  },
+  "lora": {
+    "r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "bias": "none",
+    "target_modules": [
+      "o_proj",
+      "down_proj",
+      "q_proj",
+      "k_proj",
+      "up_proj",
+      "v_proj",
+      "gate_proj"
+    ]
+  },
+  "quantisation": {
+    "load_in_4bit": true,
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "bnb_4bit_compute_dtype": "float16"
+  },
+  "data": {
+    "train_size": 3206,
+    "val_size": 400,
+    "class_weight_0": 1.0,
+    "class_weight_1": 1.0,
+    "label_token_id_0": 15,
+    "label_token_id_1": 16
+  },
+  "results": {
+    "final_f1_macro": 0.902426,
+    "best_epoch": 4.0,
+    "parse_failure_rate_pct": null,
+    "eval_metrics": {
+      "accuracy": 0.9025,
+      "f1_macro": 0.9024262098211773,
+      "auc_roc": 0.9264999999999999,
+      "n_total": 400,
+      "n_failures": 0,
+      "generation_params": {
+        "batch_size": 4,
+        "decoding": "greedy"
+      }
+    }
+  },
+  "inference": {
+    "parser_function": "parse_model_output",
+    "parser_spec": "strip \u2192 first char \u2192 0/1/-1; -1 = parse failure",
+    "output_label_-1": "preserved in results, flagged for Phase 2 re-inference",
+    "phase2_note": "Load adapter on Qwen/Qwen3.5-4B + peft; run batched model.generate(); apply parse_model_output."
+  }
+}

adapters/qwen3_14b/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8311d68134751bc4a0981a69b77aadb19f5dc31828c6ce23878edd7d99ab6688
+size 11422915

adapters/qwen3_14b/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}