初始化项目，由ModelHub XC社区提供模型

Model: SLT-AI/SLT-0.5b-GoToSpeak
Source: Original Platform

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+language:
+- en
+- ru
+base_model:
+- Qwen/Qwen2.5-0.5B
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- Text
+- Smart
+- Slt
+- Small
+- AI
+- Russian
+- English
+- Mini
+---
+
+# SLT-0.5b-GoToSpeak
+
+A small 0.5B parameter conversational model based on Qwen2.5-0.5B.
+
+## Training Dataset
+
+The model was fine-tuned on 7500 examples.
+
+The dataset includes:
+- Conversational dialogues in Russian and English
+- Up-to-date general knowledge (as of 2025-2026)
+- Simple Python coding tasks
+- Basic mathematics with step-by-step explanations
+
+Training method: Supervised Fine-Tuning (SFT).
+
+## How to Use
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_name = "SLT-AI/SLT-0.5b-GoToSpeak"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name, 
+    torch_dtype=torch.bfloat16, 
+    device_map="auto"
+)
+
+messages = [{"role": "user", "content": "Hello!"}]
+text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(text, return_tensors="pt").to(model.device)
+
+outputs = model.generate(
+    **inputs, 
+    max_new_tokens=512, 
+    temperature=0.7, 
+    top_p=0.9
+)
+
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))