初始化项目，由ModelHub XC社区提供模型

Model: VigneshwarKandhaiya/legal-slm-125m-base
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 +1,58 @@
+---
+license: apache-2.0
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- legal
+- finance
+- llama
+- pretraining
+- small-language-model
+datasets:
+- HFforLegal/case-law
+- PleIAs/SEC
+- HuggingFaceFW/fineweb-edu
+---
+
+# legal-slm-125m-base
+
+A 125M-parameter Llama-architecture small language model pretrained **from
+scratch** on a legal/financial corpus. Base (not instruction-tuned) model.
+
+## Results
+- **Validation perplexity: 10.67** (val_loss 2.3674), 1 epoch over 1.97B tokens.
+
+## Model
+- 125,847,552 params — 12 layers / 768 hidden / 12 heads, context 1024,
+  vocab 16,384 (custom byte-level BPE), tied embeddings, SwiGLU, RoPE.
+
+## Training data (~76% legal)
+- `HFforLegal/case-law` (US court opinions) — ~36%
+- `PleIAs/SEC` (SEC filings) — ~40%
+- `HuggingFaceFW/fineweb-edu` (educational web) — ~24%
+
+Pipeline: deterministic cleaning (OCR gate, boilerplate/repetition/language
+filters) → MinHash near-dup + exact-dup removal → 13-gram decontamination
+against CaseHOLD/LexGLUE (so eval is uncontaminated) → 16K byte-level BPE →
+packed 1024-token windows.
+
+## Training
+- 1 epoch, 3,753 steps, global batch 524,288 tokens, 2x H100 (DDP, bf16,
+  torch.compile). AdamW (0.9/0.95, wd 0.1 on 2D params), grad-clip 1.0.
+- LR: warmup to 6e-4 over 200M tokens, cosine to 6e-5 annealed over 1 epoch.
+
+## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tok = AutoTokenizer.from_pretrained("VigneshwarKandhaiya/legal-slm-125m-base")
+model = AutoModelForCausalLM.from_pretrained("VigneshwarKandhaiya/legal-slm-125m-base")
+ids = tok("The plaintiff shall bear the burden of", return_tensors="pt").input_ids
+print(tok.decode(model.generate(ids, max_new_tokens=40)[0], skip_special_tokens=True))
+```
+
+## Limitations
+Base model, English only, 125M params — expect fluent domain-styled text, not
+reliable facts or instruction-following. Not legal or financial advice.

config.json

@@ -0,0 +1,30 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "VigneshwarKandhaiya/legal-slm-125m-base",
+  "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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 16384
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.46.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f937e4effb215f40ba7009cd406e5a7a429718957503937095793a32a12a160b
+size 503405488

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44e8b3dccaca3c5ae4d703a90b2994cbb8951845f551d03accb8819ab8f6585b
+size 554055625

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b062414b42ee7049bdfe4d91f60ae26e26df90fb0539e0ab8e3bbbc8e13b717
+size 139053834

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<|user|>",
+    "<|assistant|>",
+    "<|system|>"
+  ],
+  "bos_token": {
+    "content": "<|bos|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eos|>",
+    "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_config.json

@@ -0,0 +1,72 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|bos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|eos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|unk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|user|>",
+    "<|assistant|>",
+    "<|system|>"
+  ],
+  "bos_token": "<|bos|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|eos|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<|unk|>"
+}