Update README.md

README.md

@@ -10,4 +10,89 @@ tags:
 - CoT
 - Convsersational
 - text-generation-inference
----
+---
+
+# **QwQ-LCoT-14B-Conversational**
+
+QwQ-LCoT-14B-Conversational is based on the Qwen 2.5 14B Instruct model, fine-tuned for chain-of-thought-based long conversational contexts. It is designed to excel in providing detailed explanations and reasoning, making it versatile for various complex use cases.
+
+## Key Features
+
+### Enhanced Knowledge and Capabilities
+- **Coding and Mathematics**: Significantly improved performance in coding and mathematical tasks, thanks to specialized expert models in these domains.
+
+### Advanced Instruction Following
+- **Instruction Following**: Enhanced ability to follow instructions accurately, even for complex tasks.
+- **Long Text Generation**: Capable of generating long texts exceeding 8,000 tokens.
+- **Structured Data Understanding**: Improved understanding of structured data such as tables.
+- **JSON Generation**: Exceptional ability to generate structured outputs, including JSON.
+
+### Resilient and Versatile
+- **Prompt Diversity**: Greater resilience to diverse system prompts, enhancing role-play scenarios and condition-setting for chatbots.
+
+### Long-Context Support
+- **Context Length**: Supports up to 128,000 tokens, with the ability to generate up to 8,000 tokens in a single response.
+
+## Quickstart
+
+Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "Qwen/Qwen2.5-14B-Instruct"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=512
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+```
+### Multilingual Support
+- **Languages Supported**: Offers multilingual support for over 29 languages, including:
+  - Chinese
+  - English
+  - French
+  - Spanish
+  - Portuguese
+  - German
+  - Italian
+  - Russian
+  - Japanese
+  - Korean
+  - Vietnamese
+  - Thai
+  - Arabic
+  - And more
+
+## Applications
+
+QwQ-LCoT-14B-Conversational is ideal for:
+- Long-form conversational AI
+- Complex reasoning and chain-of-thought explanations
+- Multilingual communication
+- Structured data generation and processing
+- Enhanced role-play and chatbot implementation