初始化项目，由ModelHub XC社区提供模型

Model: pramodkoujalagi/SmolLM2-360M-Instruct-Text-2-JSON
Source: Original Platform

.gitattributes

@@ -0,0 +1,39 @@
+*.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
+models/SmolLM2-360M-Instruct-Text-2-JSON.F16.gguf filter=lfs diff=lfs merge=lfs -text
+models/SmolLM2-360M-Instruct-Text-2-JSON.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+SmolLM2-360M-Instruct-Text-2-JSON.F16.gguf filter=lfs diff=lfs merge=lfs -text
+SmolLM2-360M-Instruct-Text-2-JSON.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,167 @@
+---
+license: apache-2.0
+language:
+- en
+metrics:
+- accuracy
+- perplexity
+base_model:
+- unsloth/SmolLM2-360M-Instruct-bnb-4bit
+tags:
+- transformers
+- unsloth
+- trl
+- llama
+- text-to-json
+- Text-2-JSON
+- Text-To-JSON
+- calendar-parsing
+- entity-extraction
+- json-structured-output
+- event-scheduling
+- 4-bit
+library_name: transformers
+---
+
+Developed by: [Pramod Koujalagi](https://www.pramodkoujalagi.com)
+
+# SmolLM2-360M-Instruct-Text-2-JSON
+A fine-tuned version of SmolLM2-360M-Instruct-bnb-4bit specialized for parsing unstructured calendar event requests into structured JSON data.
+
+## Model Description
+This model is fine-tuned on SmolLM2-360M-Instruct-bnb-4bit using QLoRA to extract structured calendar event information from natural language text. It identifies and structures key scheduling entities like action, date, time, attendees, location, duration, recurrence, and notes.
+
+
+### 📦 Example Usage
+
+You can use the `SmolLM2-360M-Instruct-Text-2-JSON` model to parse natural language event descriptions into structured JSON format.
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import json
+
+# Load model and tokenizer
+model_name = "pramodkoujalagi/SmolLM2-360M-Instruct-Text-2-JSON"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+def parse_calendar_event(text):
+    # Format the prompt
+    formatted_prompt = f"""<|im_start|>user
+Extract the relevant event information from this text and organize it into a JSON structure with fields for action, date, time, attendees, location, duration, recurrence, and notes. If a field is not present, return null for that field.
+
+Text: {text}
+<|im_end|>
+<|im_start|>assistant
+"""
+
+    # Generate response
+    inputs = tokenizer(formatted_prompt, return_tensors="pt").to(model.device)
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=512,
+            do_sample=True,
+            temperature=0.1,
+            top_p=0.95,
+            pad_token_id=tokenizer.eos_token_id
+        )
+
+    # Process response
+    output_text = tokenizer.decode(outputs[0], skip_special_tokens=False)
+    response = output_text.split("<|im_start|>assistant\n")[1].split("<|im_end|>")[0].strip()
+
+    # Return formatted JSON
+    parsed_json = json.loads(response)
+    return json.dumps(parsed_json, indent=2)
+
+# Example input
+event_text = "Plan an exhibition walkthrough on 15th, April 2028 at 3 PM with Harper, Grace, and Alex in the art gallery for 1 hour, bring bag."
+
+# Output
+print("Prompt:")
+print(event_text)
+print("\nModel Output:")
+print(parse_calendar_event(event_text))
+```
+Output
+```
+Prompt:
+Plan an exhibition walkthrough on 15th, April 2028 at 3 PM with Harper, Grace, and Alex in the art gallery for 1 hour, bring bag.
+
+Model Output:
+{
+  "action": "Plan an exhibition walkthrough",
+  "date": "15/04/2028",
+  "time": "3:00 PM",
+  "attendees": [
+    "Harper",
+    "Grace",
+    "Alex"
+  ],
+  "location": "art gallery",
+  "duration": "1 hour",
+  "recurrence": null,
+  "notes": "Bring bag"
+}
+```
+<!-- 
+
+**Example:**
+```
+Input: "Plan an exhibition walkthrough on 15th, April 2028 at 3 PM with Harper, Grace, and Alex in the art gallery for 1 hour, bring bag."
+```
+```
+Output: {
+  "action": "Plan an exhibition walkthrough",
+  "date": "15/04/2028",
+  "time": "3:00 PM",
+  "attendees": [
+    "Harper",
+    "Grace",
+    "Alex"
+  ],
+  "location": "art gallery",
+  "duration": "1 hour",
+  "recurrence": null,
+  "notes": Bring bag
+}
+``` -->
+
+### Resources for more information:
+- GitHub Repository: [SmolLM2-360M-Instruct-Text-2-JSON](https://github.com/pramodkoujalagi/SmolLM2-360M-Instruct-Text-2-JSON)
+- Base Model: [SmolLM2-360M-Instruct-bnb-4bit](https://huggingface.co/unsloth/SmolLM2-360M-Instruct-bnb-4bit) (Derived from HuggingfaceTB/SmolLM2-360)
+
+## Use Cases
+- Calendar application integration
+- Personal assistant scheduling systems
+- Meeting summarization tools
+- Email processing for event extraction
+
+## Training Details
+
+### Training Data
+The model was trained on a custom dataset consisting of 1,149 examples (1,034 training, 115 validation) of natural language event descriptions paired with structured JSON outputs. The dataset includes a wide variety of event types, date/time formats, and varying combinations of fields.
+
+### Training Procedure
+- **Fine-tuning method**: QLoRA (Quantized Low-Rank Adaptation)
+- **LoRA configuration**:
+  - Rank: 64
+  - Alpha: 32
+  - Target modules: All key model components
+  - Rank-stabilized LoRA: Enabled
+- **Training hyperparameters**:
+  - Batch size: 8 (2 per device × 4 gradient accumulation steps)
+  - Learning rate: 2e-4 with cosine scheduler
+  - Epochs: 3
+  - Weight decay: 0.01
+  - Optimizer: AdamW (8-bit)
+  - Gradient checkpointing: Enabled
+- **Training time**: ~15 minutes
+- **Hardware used**: [T4 GPU](https://www.nvidia.com/en-in/data-center/tesla-t4/)
+
+### Training Metrics
+- Final training loss: 
+- Final validation loss: 
+- Validation perplexity: 1.2091

SmolLM2-360M-Instruct-Text-2-JSON.F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9652a4342910d5aca4706dbb07446e61847d9dc96eba2dd316d5fd1901cedbb
+size 819929312

SmolLM2-360M-Instruct-Text-2-JSON.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a845642046e9a48472bef3f868735e4ae5daf11bb9949696fd60e8e969597a74
+size 303032448

adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b30cd76ebffc41c47ea6bd35b0b1d611e4a46fafed7cd8217b4d507c4b2ac1
+size 258276120

adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/SmolLM2-360M-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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b30cd76ebffc41c47ea6bd35b0b1d611e4a46fafed7cd8217b4d507c4b2ac1
+size 258276120

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|PAD_TOKEN|>": 49152
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
+  "pad_token_id": 49152,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "4.51.1",
+  "unsloth_version": "2025.3.19",
+  "use_cache": true,
+  "vocab_size": 49153
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 8192,
+  "pad_token_id": 49152,
+  "transformers_version": "4.51.1"
+}

models/SmolLM2-360M-Instruct-Text-2-JSON.F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9652a4342910d5aca4706dbb07446e61847d9dc96eba2dd316d5fd1901cedbb
+size 819929312

models/SmolLM2-360M-Instruct-Text-2-JSON.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a845642046e9a48472bef3f868735e4ae5daf11bb9949696fd60e8e969597a74
+size 303032448

models/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b181cd4a2ea77fe2876230383d780b758d6d6d31a6bce72b2f72010e7089d71
+size 818116310

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b181cd4a2ea77fe2876230383d780b758d6d6d31a6bce72b2f72010e7089d71
+size 818116310

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": "�"
+}

tokenizer_config.json

@@ -0,0 +1,172 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24211": {
+      "content": "�",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49152": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "�",
+  "vocab_size": 49152
+}