初始化项目，由ModelHub XC社区提供模型

Model: Raghav-Singhal/epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-bce
Source: Original Platform

README.md

@@ -0,0 +1,42 @@
+---
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- llama
+- causal-lm
+- bfloat16
+---
+
+# epe-3p-smollm-1p7b-100B-20n-2048sl-960gbsz-bce
+
+Converted Hugging Face base checkpoint from the Model Raising EPE pretraining run.
+
+## Details
+
+- Architecture: `LlamaForCausalLM`
+- Base model size: `1.7B`
+- Precision on disk: `bfloat16`
+- Source Megatron checkpoint: `iter_0050863`
+- Tokenizer: extended SmolLM2 tokenizer with 36 additional special tokens (`<assistant>` + 35 `<charter_X.Y>` tokens)
+- Config vocab size: `49280` padded rows
+- Tokenizer length: `49188`
+
+## Variant
+
+This is the `3p` EPE variant trained with BCE constitution-prediction loss.
+
+## Chat Templates
+
+Two named chat templates are provided:
+
+| Name | Use case |
+|------|----------|
+| `default` | Standard chat format with the plain `assistant` role |
+| `epe` | Uses `<assistant>` at the start of assistant turns |
+
+```python
+tok.apply_chat_template(messages, chat_template="default")
+tok.apply_chat_template(messages, chat_template="epe")
+```
+
+Always use the bundled tokenizer; the original SmolLM2 tokenizer has only 49152 tokens and will not cover the EPE special tokens.