Upload fine-tuned Mistral-7B CEFR model with exact and within-1 confusion matrices

README.md

@@ -0,0 +1,64 @@
+
+# Fine-Tuned Gemma-7B CEFR Model
+
+This is a fine-tuned version of `unsloth/gemma-7b-bnb-4bit` for CEFR-level sentence generation, evaluated with a fine-tuned classifier from `Mr-FineTuner/Skripsi_validator_best_model`.
+
+- **Base Model**: unsloth/gemma-7b-bnb-4bit
+- **Fine-Tuning**: LoRA with balanced dataset
+- **Training Details**:
+  - Dataset: CEFR-level sentences (balanced)
+  - LoRA Parameters: r=32, lora_alpha=32, lora_dropout=0.5
+  - Training Args: learning_rate=2e-5, batch_size=8, epochs=0.01, cosine scheduler
+  - Optimizer: adamw_8bit
+  - Early Stopping: Patience=3, threshold=0.01
+- **Evaluation Metrics (Exact Matches)**:
+  - CEFR Classifier Accuracy: 0.167
+  - Precision (Macro): 0.033
+  - Recall (Macro): 0.167
+  - F1-Score (Macro): 0.056
+- **Evaluation Metrics (Within ±1 Level)**:
+  - CEFR Classifier Accuracy: 0.667
+  - Precision (Macro): 0.556
+  - Recall (Macro): 0.667
+  - F1-Score (Macro): 0.583
+- **Other Metrics**:
+  - Perplexity: 2.952
+  - Diversity (Unique Sentences): 0.100
+  - Inference Time (ms): 6696.712
+  - Model Size (GB): 4.2
+  - Robustness (F1): 0.053
+- **Confusion Matrix (Exact Matches)**:
+  - CSV: [confusion_matrix_exact.csv](confusion_matrix_exact.csv)
+  - Image: [confusion_matrix_exact.png](confusion_matrix_exact.png)
+- **Confusion Matrix (Within ±1 Level)**:
+  - CSV: [confusion_matrix_within1.csv](confusion_matrix_within1.csv)
+  - Image: [confusion_matrix_within1.png](confusion_matrix_within1.png)
+- **Per-Class Confusion Metrics (Exact Matches)**:
+  - A1: TP=0, FP=0, FN=10, TN=50
+  - A2: TP=10, FP=40, FN=0, TN=10
+  - B1: TP=0, FP=0, FN=10, TN=50
+  - B2: TP=0, FP=0, FN=10, TN=50
+  - C1: TP=0, FP=10, FN=10, TN=40
+  - C2: TP=0, FP=0, FN=10, TN=50
+- **Per-Class Confusion Metrics (Within ±1 Level)**:
+  - A1: TP=10, FP=0, FN=0, TN=50
+  - A2: TP=10, FP=20, FN=0, TN=30
+  - B1: TP=10, FP=0, FN=0, TN=50
+  - B2: TP=0, FP=0, FN=10, TN=50
+  - C1: TP=0, FP=0, FN=10, TN=50
+  - C2: TP=10, FP=0, FN=0, TN=50
+- **Usage**:
+  ```python
+  from transformers import AutoModelForCausalLM, AutoTokenizer
+
+  model = AutoModelForCausalLM.from_pretrained("Mr-FineTuner/Test_02_gemma_trainPercen_myValidator")
+  tokenizer = AutoTokenizer.from_pretrained("Mr-FineTuner/Test_02_gemma_trainPercen_myValidator")
+
+  # Example inference
+  prompt = "<|user|>Generate a CEFR B1 level sentence.<|end|>"
+  inputs = tokenizer(prompt, return_tensors="pt")
+  outputs = model.generate(**inputs, max_length=50)
+  print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+  ```
+
+Uploaded using `huggingface_hub`.

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/llama-3-8b-instruct-bnb-4bit",
+  "bias": "none",
+  "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": 0.5,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19db9872bb5e393604cb42196c8a5de9c06c5d9d3fdc906cd7412013895abe92
+size 167832688

config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "unsloth_version": "2025.4.8",
+  "use_cache": true,
+  "vocab_size": 32000
+}

confusion_matrix_exact.csv

@@ -0,0 +1,7 @@
+,A1,A2,B1,B2,C1,C2
+A1,0,10,0,0,0,0
+A2,0,0,10,0,0,0
+B1,0,0,10,0,0,0
+B2,0,0,0,10,0,0
+C1,0,0,0,0,10,0
+C2,0,0,0,10,0,0

confusion_matrix_within1.csv

@@ -0,0 +1,7 @@
+,A1,A2,B1,B2,C1,C2
+A1,10,0,0,0,0,0
+A2,0,10,0,0,0,0
+B1,0,0,10,0,0,0
+B2,0,0,0,10,0,0
+C1,0,0,0,0,10,0
+C2,0,0,0,10,0,0

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 32768,
+  "pad_token_id": 0,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c65a73bf847b3cac0655b74f77075bdd90456b4b7aa5890fce54327d20c4cc51
+size 4125687910

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 32768,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}