初始化项目，由ModelHub XC社区提供模型

Model: Prathamesh25/smollm2-1.7b-aptitude-qa-v1
Source: Original Platform

.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

README.md

@@ -0,0 +1,90 @@
+---
+license: apache-2.0
+base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct
+tags:
+- text-generation-inference
+- transformers
+- lora
+- trl
+- smollm2
+- aptitude
+datasets:
+- Prathamesh25/aptitude-qa-dataset
+language:
+- en
+pipeline_tag: text-generation
+---
+
+# SmolLM2 1.7B Aptitude QA
+
+This model is a fine-tuned version of `HuggingFaceTB/SmolLM2-1.7B-Instruct` optimized for technical aptitude question-answering tasks, including basic programming concepts (C, Python, loops) and fundamental AI/ML reasoning logic.
+
+It was trained using LoRA parameters in pure Float16 precision on a free Google Colab T4 GPU node to handle the target dataset schema formatting seamlessly.
+
+## Model Description
+
+- **Developed by:** Prathamesh25
+- **Base Model:** [HuggingFaceTB/SmolLM2-1.7B-Instruct](https://huggingface.co)
+- **Dataset Used:** [Prathamesh25/aptitude-qa-dataset](https://huggingface.co)
+- **Language:** English
+- **License:** Apache 2.0
+
+## Training Information & Hyperparameters
+
+- **Precision:** Pure Float16 (`fp16=True`)
+- **Optimizer:** `adamw_torch`
+- **Learning Rate:** 2e-4
+- **Per Device Train Batch Size:** 4
+- **Gradient Accumulation Steps:** 4
+- **LoRA Configuration:** Rank ($r$)=16, Alpha ($lpha$)=32, Dropout=0.05
+- **Target Modules:** `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`
+
+### Loss Progression Metrics
+The training process showed highly stable optimization across epochs:
+- **Step 10:** 1.955
+- **Step 30:** 0.709
+- **Step 100:** 0.412
+- **Step 200:** 0.323
+- **Step 330:** 0.281
+
+## How to Use
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "Prathamesh25/smollm2-1.7b-aptitude-qa-v1"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id, 
+    torch_dtype=torch.float16, 
+    device_map="auto"
+)
+
+test_prompt = [
+    {
+        "role": "user", 
+        "content": "subject: 06 technical aptitude (basic programming and aiml concepts)\nlevel: 01 basic\ncategory: loops\nquestion: what is the output of this c code: `int sum = 0; for(int i=1; i<=3; i++) { sum += i; } printf(\"%d\", sum);`?"
+    }
+]
+
+text_prompt = tokenizer.apply_chat_template(test_prompt, tokenize=False, add_generation_prompt=True)
+model_inputs = tokenizer([text_prompt], return_tensors="pt").to("cuda")
+input_token_len = model_inputs.input_ids.shape[1]
+
+with torch.no_grad():
+    generated_ids = model.generate(
+        input_ids=model_inputs.input_ids,
+        attention_mask=model_inputs.attention_mask,
+        max_new_tokens=150, 
+        temperature=0.1, 
+        do_sample=True,        
+        eos_token_id=tokenizer.eos_token_id,
+        pad_token_id=tokenizer.eos_token_id
+    )
+
+final_tokens = generated_ids[0][input_token_len:]
+print(tokenizer.decode(final_tokens, skip_special_tokens=True))
+```
+---

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float16",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 130000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers.js_config": {
+    "dtype": "q4",
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    },
+    "use_external_data_format": {
+      "model.onnx": true,
+      "model_fp16.onnx": true
+    }
+  },
+  "transformers_version": "5.8.0",
+  "use_cache": true,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "5.8.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa57018c0ea84896151cdc4ea885ec31b774f0c98524693261cef502a1fcd4e5
+size 3422777736

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}