初始化项目，由ModelHub XC社区提供模型

Model: Anugya/text2cypher-smollm2
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 +1,82 @@
+---
+library_name: transformers
+base_model: HuggingFaceTB/SmolLM2-135M-Instruct
+tags:
+- text2cypher
+- cypher
+- graph
+- fine-tuned
+language:
+- en
+license: apache-2.0
+datasets:
+- RomanTeucher/text2cypher-curated
+---
+
+# Text2Cypher — SmolLM2-135M Fine-tuned
+
+A fine-tuned version of `SmolLM2-135M-Instruct` that generates Cypher queries from natural language questions and a graph schema.
+
+## Model Details
+
+- **Base model:** HuggingFaceTB/SmolLM2-135M-Instruct
+- **Model type:** Causal Language Model
+- **Language:** English
+- **License:** Apache 2.0
+- **Finetuned by:** Anugya Sahu
+
+## Training Data
+
+- **Dataset:** `RomanTeucher/text2cypher-curated`
+- 1000 training samples, 75 validation, 50 test
+- Each sample contains a graph schema, a natural language question, and a target Cypher query
+
+## How to Use
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("Anugya/text2cypher-smollm2")
+tokenizer = AutoTokenizer.from_pretrained("Anugya/text2cypher-smollm2")
+tokenizer.pad_token = tokenizer.eos_token
+
+schema = "Movie {title, year}, Person {name}, (Person)-[:DIRECTED]->(Movie)"
+question = "Which movies did Christopher Nolan direct before 2010?"
+
+prompt = f"""### Schema:
+{schema}
+
+### Question:
+{question}
+
+### Cypher:"""
+
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=128, do_sample=False)
+generated = outputs[0][inputs["input_ids"].shape[1]:]
+print(tokenizer.decode(generated, skip_special_tokens=True))
+```
+
+## Training Details
+
+- **Full fine-tune** — all weights updated, no LoRA
+- **Epochs:** 3
+- **Learning rate:** 2e-4
+- **Batch size:** 4
+- **Max token length:** 256
+- **Hardware:** CPU (Apple M-series)
+- **Precision:** float32
+
+## Evaluation
+
+Evaluated on 50 test samples using:
+
+- **Exact Match** — strict comparison after lowercasing and stripping
+- **Token F1** — token overlap between prediction and ground truth
+
+## Limitations
+
+- 135M parameter model — generates Cypher that looks right but often isn't
+- No query execution validation against a real Neo4j database
+- May struggle with complex schemas or multi-hop queries
+- Trained on CPU with limited epochs — larger training would improve results

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 +1,40 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_parameters": {
+    "rope_theta": 100000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "5.10.2",
+  "use_cache": false,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "5.10.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2959b490f150157fd7fae4ef8ec1250a4af5aa90bd11dd5dfcd640fee0c796
+size 538090408

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "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": true,
+  "local_files_only": false,
+  "max_length": 1024,
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}