初始化项目，由ModelHub XC社区提供模型

Model: oscardean/smollm2-135m-text2cypher
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 +1,111 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- HuggingFaceTB/SmolLM2-135M-Instruct
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- text2cypher
+- cypher
+- graph-databases
+- supervised-fine-tuning
+- cpu-training
+---
+
+# SmolLM2-135M Text2Cypher
+
+Fine-tuned `HuggingFaceTB/SmolLM2-135M-Instruct` for generating Cypher queries from a graph schema and a natural-language question.
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "oscardean/smollm2-135m-text2cypher"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+messages = [
+    {
+        "role": "system",
+        "content": (
+            "You translate natural-language questions into Cypher queries. "
+            "Use only the supplied graph schema and return only the Cypher query."
+        ),
+    },
+    {
+        "role": "user",
+        "content": (
+            "Graph schema:\n"
+            "Person {name: STRING}\n"
+            "Movie {title: STRING, year: INTEGER}\n"
+            "(Person)-[:DIRECTED]->(Movie)\n\n"
+            "Question:\n"
+            "Which movies did Christopher Nolan direct before 2010?"
+        ),
+    },
+]
+
+inputs = tokenizer.apply_chat_template(
+    messages,
+    tokenize=True,
+    add_generation_prompt=True,
+    return_tensors="pt",
+)
+
+outputs = model.generate(
+    inputs,
+    max_new_tokens=192,
+    do_sample=False,
+)
+
+prediction = tokenizer.decode(
+    outputs[0, inputs.shape[1]:],
+    skip_special_tokens=True,
+)
+
+print(prediction)
+```
+
+## Training
+
+| Hyperparameter          |                  Value |
+| ----------------------- | ---------------------: |
+| Training samples        |                  1,000 |
+| Validation samples      |                     75 |
+| Epochs                  |                      3 |
+| Learning rate           |                 `5e-5` |
+| Batch size              |                      2 |
+| Gradient accumulation   |                      4 |
+| Effective batch size    |                      8 |
+| Weight decay            |                 `0.01` |
+| Warmup ratio            |                 `0.05` |
+| Maximum sequence length |                    800 |
+| Decoding                |                 Greedy |
+| Checkpoint selection    | Lowest validation loss |
+
+## Evaluation
+
+Evaluated on the 50-sample test split.
+
+| Metric                 |   Base | Fine-tuned |
+| ---------------------- | -----: | ---------: |
+| Basic query structure  |  2.00% |    100.00% |
+| Token F1               | 12.35% |     55.20% |
+| Node-label agreement   |  0.00% |     58.00% |
+| Component match rate   | 29.20% |     49.60% |
+| Normalized exact match |  0.00% |      0.00% |
+
+## Limitations
+
+* May hallucinate labels, relationships, or properties.
+* May omit filters, constants, or return fields.
+* May repeat conditions.
+* May use incorrect relationship directions or operators.
+* May generate SQL-like syntax instead of valid Cypher.
+* Can produce structurally plausible but semantically incorrect queries.
+* Should be validated before execution.
+* Not intended for direct production use.

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": "bfloat16",
+  "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": "5.12.0",
+  "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": "5.12.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09092c18b2062b28a60c096ab9dc037a0aade7e7a60d556c87f054ed387e0cda
+size 269060552

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
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:065240e3c5b00eb523d1d9ccac1fcd223b2a16a1c473ab2461e83d5e4a6a2ce5
+size 5201