初始化项目，由ModelHub XC社区提供模型

Model: tirumalaseti/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 +1,62 @@
+---
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+  - text-generation
+  - causal-lm
+  - llama
+  - legal
+  - finance
+  - modal
+---
+
+# tirumalaseti/slm-125m-base
+
+This is a **125M-parameter base completion model** trained from scratch on a legal/financial-heavy corpus. It is **not a chatbot**: it was optimized for next-token prediction and works best when prompted with the opening of a sentence or paragraph to continue.
+
+## Model summary
+
+- **Trainable parameters:** 125,847,552 (~125.848M)
+- **Architecture:** 12-layer Llama-style decoder, 768 hidden size, 12 attention heads
+- **Context length:** 1,024 tokens
+- **Tokenizer:** 16,384-token byte-level BPE
+- **Training tokens seen:** 2,500,329,472
+- **Optimizer steps:** 4,769
+- **Completed epochs over the packed train set:** 1.23
+- **Final validation loss:** 2.3035
+- **Final validation perplexity:** 10.01
+- **Reported spend:** $0.00
+
+## Training corpus
+
+The packed corpus used for pretraining contains 2,059,674,624 total tokens:
+
+- **Train:** 2,039,072,768
+- **Validation:** 20,601,856
+
+Realized source mix:
+
+- **US case law:** 722,081,792 tokens (35.1%)
+- **SEC filings:** 868,714,496 tokens (42.2%)
+- **Educational web text:** 468,878,336 tokens (22.8%)
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "tirumalaseti/slm-125m-base"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+prompt = "The plaintiff respectfully moves this Court to"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=96, temperature=0.8, top_p=0.95)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Notes
+
+- This is a **base model**, not an instruction-tuned assistant.
+- It is strongest at continuing legal/financial prose in-register.
+- The spend figure comes from the latest visible Modal billing report; Modal billing report may lag; this value reflects the latest locally visible report..

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,
+  "pad_token_id": 2,
+  "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
+}

generation_config.json

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

model-metadata.json

@@ -0,0 +1,25 @@
+{
+  "model_id": "tirumalaseti/slm-125m-base",
+  "project": "slm-125m",
+  "parameter_count": 125847552,
+  "parameter_count_millions": 125.848,
+  "context_length": 1024,
+  "vocab_size": 16384,
+  "train_tokens": 2039072768,
+  "val_tokens": 20601856,
+  "total_tokens": 2059674624,
+  "tokens_seen": 2500329472,
+  "optimizer_steps": 4769,
+  "epochs_completed": 1.226,
+  "world_size": 8,
+  "grad_accum_steps": 2,
+  "final_validation_loss": 2.303484795203459,
+  "final_validation_perplexity": 10.00900107062853,
+  "reported_spend_usd": 0.0,
+  "reported_spend_note": "Modal billing report may lag; this value reflects the latest locally visible report.",
+  "corpus_mix_tokens": {
+    "case-law": 722081792,
+    "sec": 868714496,
+    "fineweb-edu": 468878336
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9375fd1ecbf61e38810e35aefcf55b1cf3815c1ff27a0135e3fa64a700dbc827
+size 503405488

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|>"
+}

training_summary.json

@@ -0,0 +1,9 @@
+{
+  "step": 4769,
+  "tokens_seen": 2500329472,
+  "target_tokens": 2500000000,
+  "max_steps": 0,
+  "world_size": 8,
+  "grad_accum_steps": 2,
+  "last_eval_loss": 2.303484795203459
+}