初始化项目，由ModelHub XC社区提供模型

Model: prajwal55/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 +1,68 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- legal
+- finance
+- llama
+pipeline_tag: text-generation
+---
+
+# slm-125m-base
+
+A 126M-parameter Llama-architecture base model pretrained **from
+scratch** on US case law, SEC filings, and educational web text. Trained on
+8xH100 for ~28 minutes at a total project cost of roughly $18.
+
+This is a **base model**. It has had no instruction tuning, no RLHF, and no
+safety alignment. It completes text; it does not follow instructions.
+
+## Architecture
+
+| | |
+|---|---|
+| Parameters | 125,847,552 |
+| Layers / hidden / heads | 12 / 768 / 12 |
+| Context length | 1024 |
+| Vocab | 16384 (byte-level BPE trained on this corpus) |
+| Tied embeddings | True |
+
+## Training data
+
+1.92B tokens, ~76% legal:
+
+| Source | Tokens | Share |
+|---|---|---|
+| `PleIAs/SEC` | 819M | 43% |
+| `HFforLegal/case-law` | 639M | 33% |
+| `HuggingFaceFW/fineweb-edu` | 463M | 24% |
+
+Pipeline: deterministic rule-based cleaning (line filters, boilerplate
+stripping, repetition and language gates, plus a dictionary-based OCR gate on
+case law) then MinHash near-dedup, exact dedup, and 13-gram decontamination
+against the CaseHOLD evaluation set.
+
+## Training
+
+2 epochs (3.84B tokens seen), AdamW, cosine schedule to a 6e-05 cooldown,
+bf16, sequence length 1024, global batch 524,288 tokens.
+
+## Results
+
+| Metric | Value |
+|---|---|
+| Val perplexity (held-out 1%) | 9.07 |
+| CaseHOLD (zero-shot, 5-way) | 19.5% |
+
+CaseHOLD is measured on data excluded from training by 13-gram
+decontamination, so it is not inflated by leakage. Expect near-chance
+zero-shot performance: a 125M base model with no task tuning is not
+competitive on multiple-choice legal reasoning, and this number is a baseline
+for fine-tuning, not a capability claim.
+
+## Limitations
+
+Small, base-only, English-only, 1024-token context. Case-law inputs contain
+OCR noise that survives filtering. **Not legal or financial advice** and not
+suitable for any use where an incorrect statement of law carries consequences.

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 16384,
+  "pad_token_id": 2
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "transformers_version": "4.46.3",
+  "pad_token_id": 2
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c185b5323b4ff964da14cb532ba3342afe595532dd73972ff67ebc61ae4cc876
+size 503405488

special_tokens_map.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<|user|>",
+    "<|assistant|>",
+    "<|system|>"
+  ],
+  "bos_token": "<|bos|>",
+  "eos_token": "<|eos|>",
+  "pad_token": "<|pad|>",
+  "unk_token": "<|unk|>"
+}

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|>"
+}