Update README.md

README.md

@@ -1,3 +1,47 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+datasets:
+- Azure99/blossom-v6.2-sft-stage1
+- Azure99/blossom-v6.2-sft-stage2
+language:
+- zh
+- en
+base_model:
+- Azure99/Blossom-V6.2-14B
+
+---
+
+# **BLOSSOM-V6.2-14B-GGUF**
+
+[💻Github](https://github.com/Azure99/BlossomLM) • [🚀Blossom Chat Demo](https://blossom-chat.com/)
+
+### Introduction
+
+Blossom is a powerful open-source conversational large language model that provides reproducible post-training data, dedicated to delivering an open, powerful, and cost-effective locally accessible general-purpose model for everyone.
+
+| Chat Model                                                   | Resource                                                     | Base Model        |
+| ------------------------------------------------------------ | ------------------------------------------------------------ | ----------------- |
+| [Blossom-V6.2-36B](https://huggingface.co/Azure99/Blossom-V6.2-36B) | [Demo](https://huggingface.co/spaces/Azure99/Blossom-V6.2-36B-Demo) [GGUF](https://huggingface.co/Azure99/Blossom-V6.2-36B-GGUF) [Ollama](https://ollama.com/azure99/blossom-v6.2:36b) | Seed-OSS-36B-Base |
+| [Blossom-V6.2-32B](https://huggingface.co/Azure99/Blossom-V6.2-32B) | [Demo](https://huggingface.co/spaces/Azure99/Blossom-V6.2-32B-Demo) [GGUF](https://huggingface.co/Azure99/Blossom-V6.2-32B-GGUF) [Ollama](https://ollama.com/azure99/blossom-v6.2:32b) | Qwen2.5-32B       |
+| [Blossom-V6.2-14B](https://huggingface.co/Azure99/Blossom-V6.2-14B) | [Demo](https://huggingface.co/spaces/Azure99/Blossom-V6.2-14B-Demo) [GGUF](https://huggingface.co/Azure99/Blossom-V6.2-14B-GGUF) [Ollama](https://ollama.com/azure99/blossom-v6.2:14b) | Qwen3-14B-Base    |
+| [Blossom-V6.2-8B](https://huggingface.co/Azure99/Blossom-V6.2-8B) | [Demo](https://huggingface.co/spaces/Azure99/Blossom-V6.2-8B-Demo) [GGUF](https://huggingface.co/Azure99/Blossom-V6.2-8B-GGUF) [Ollama](https://ollama.com/azure99/blossom-v6.2:8b) | Qwen3-8B-Base     |
+
+Hint: Across the vast majority of use cases, **Blossom-V6.2-36B** outperforms **Blossom-V6.2-32B**.
+
+You can find the training data here: [Blossom-V6.2-SFT-Stage1](https://huggingface.co/datasets/Azure99/blossom-v6.2-sft-stage1) (1 epoch)、[Blossom-V6.2-SFT-Stage2](https://huggingface.co/datasets/Azure99/blossom-v6.2-sft-stage2) (3 epoch).
+
+### **Data Synthesis Workflow Overview**
+
+Primarily employs three cost-effective models: Deepseek-V3.1, Gemini 2.5 Flash, and Qwen3-235B-A22B-Instruct-2507 (denoted as A, B, C)—to regenerate responses under different scenarios using tailored synthesis strategies.
+
+For example:
+
+- In objective scenarios like mathematics (where answers are unique), Model A first generates responses as a "teacher." If reference answers exist in the source data, Model B verifies the correctness of A's responses against them. If no reference answers exist, Model C generates a second response, and Model B checks consistency between A and C's outputs. Inconsistent responses are filtered out.
+- For subjective scenarios, three models cross-evaluate each other. For instance, Models A and B generate responses to a question, and Model C evaluates which is better. The superior response may be retained as training data or used for preference data construction. To mitigate model bias, roles (respondent/evaluator) are randomly assigned to A, B, and C in each instance.
+
+Additional rule-based filtering is applied, such as:
+
+- N-Gram filtering to remove data with many repetitions.
+- Discarding questions containing toxic content that triggers teacher model refusals.
+
+Further technical details will be released in the future. The data is synthesized by the [🌸BlossomData](https://github.com/Azure99/BlossomData) framework.