Upload fine-tuned MCQ generation model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,45 @@
----
-license: mit
----
+
+# MCQ Generation Model
+
+This model is fine-tuned on the RACE dataset for generating multiple-choice questions. It is based on Mistral-Nemo-Base-2407 and uses unsloth optimizations.
+
+## Model Details
+- Base Model: unsloth/Mistral-Nemo-Base-2407
+- Task: Multiple Choice Question Generation
+- Training Data: RACE dataset
+- Optimization: unsloth LoRA fine-tuning
+
+## Usage
+```python
+from transformers import AutoTokenizer
+from peft import AutoPeftModelForCausalLM
+
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained("kenzykhaled/Question_generator_Mistral")
+
+# Load model
+model = AutoPeftModelForCausalLM.from_pretrained(
+    "kenzykhaled/Question_generator_Mistral",
+    device_map="auto",
+    load_in_4bit=True
+)
+
+# Prepare your input
+text = """
+Generate a multiple-choice question (MCQ) based on the passage, provide options, and indicate the correct option.
+
+Passage: [Your passage here]
+"""
+
+# Generate MCQ
+inputs = tokenizer(text, return_tensors="pt").to("cuda")
+outputs = model.generate(**inputs, max_new_tokens=128)
+result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(result)
+```
+
+## Training Details
+- LoRA rank: 16
+- Target modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
+- Training dataset: RACE (all)
+- Training framework: unsloth + transformers

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-nemo-base-2407-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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "o_proj",
+    "v_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 sha256:91c0524d03d205bdd8ba7d81e67ba4c0fc867e4e4b066217936757ae51e3d88a
+size 228140600

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": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed89c017d1d3296d6250b943bdea9c7a12129ac98c68ebd512f558154bf4688
+size 17078546