初始化项目，由ModelHub XC社区提供模型

Model: datedgpt/datedgpt-2024-instruct
Source: Original Platform

README.md

@@ -0,0 +1,62 @@
+---
+language:
+- en
+tags:
+- causal-lm
+- llama
+- instruction-tuned
+- point-in-time
+- dated
+- lookahead-bias-free
+pipeline_tag: text-generation
+---
+
+# DatedGPT-2024-Instruct
+
+**DatedGPT** is a family of point-in-time language models: each vintage is
+trained only on data available up to its cutoff date, making it suitable for
+lookahead-bias-free prediction and point-in-time analysis.
+
+This is the **instruction-tuned chat model** with data up to **2024**.
+For the base (pretrained) model, see
+[datedgpt/datedgpt-2024-base](https://huggingface.co/datedgpt/datedgpt-2024-base).
+
+| Property | Value |
+|----------|-------|
+| Architecture | LlamaForCausalLM |
+| Parameters | ~1.3 B |
+| Context length | 2048 |
+| Vocab | 32,000 (SentencePiece) |
+| Precision | bfloat16 |
+| Data vintage | 2024 |
+
+## Chat template
+
+The Llama-2-style chat template ships in `tokenizer_config.json` — apply it
+with the tokenizer. The BOS token must come from the tokenizer, **not** as a
+literal `"<s>"` string in your prompt text.
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+repo_id = "datedgpt/datedgpt-2024-instruct"
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
+model = AutoModelForCausalLM.from_pretrained(repo_id, torch_dtype=torch.bfloat16, device_map="auto")
+
+prompt = tokenizer.apply_chat_template(
+    [{"role": "user", "content": "What is the capital of France?"}],
+    tokenize=False,
+)
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+output = model.generate(**inputs, max_new_tokens=128, do_sample=True,
+                        temperature=0.7, top_p=0.95, use_cache=True,
+                        eos_token_id=tokenizer.eos_token_id,
+                        pad_token_id=tokenizer.eos_token_id)
+print(tokenizer.decode(output[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True))
+```
+
+## Limitations
+
+- Knowledge limited to the 2024 data vintage.
+- No RLHF or safety tuning; outputs can be confidently wrong.