Update README.md

README.md

@@ -1,8 +1,5 @@
 ---
-license: apache-2.0
----
----
-# base_model: Qwen/Qwen2.5-7B-Instruct
+base_model: Qwen/Qwen2.5-7B-Instruct
 language:
 - en
 license: apache-2.0
@@ -18,17 +15,14 @@ tags:
 
 # qwen2.5-7b-agent-trajectory-mixed_dbv4_alfv4_1to1
 
-This repository provides a **merged full model** fine-tuned for AgentBench tasks  
+This repository provides a merged full model fine-tuned for AgentBench tasks  
 (ALFWorld + DBBench).
 
-Base model:
-Qwen/Qwen2.5-7B-Instruct
+Base model: Qwen/Qwen2.5-7B-Instruct
 
 This repository contains fully merged model weights (LoRA merged into the base model).
 
----
-
-# Training Objective
+## Training Objective
 
 This model is optimized for:
 
@@ -37,9 +31,7 @@ This model is optimized for:
 - Deterministic action generation
 - Reduced invalid action rate
 
----
-
-# Datasets Used
+## Datasets Used
 
 The model was trained using only officially provided training datasets:
 
@@ -47,42 +39,36 @@ The model was trained using only officially provided training datasets:
 - u-10bei/dbbench_sft_dataset_react_v4
 
 Mixing strategy:
-- ALFWorld (v5) and DBBench (v4) mixed in a 1:1 ratio.
-
-No validation or test splits were used for training.
 
----
+- ALFWorld (v5) and DBBench (v4) mixed in a 1:1 ratio.
+- No validation or test splits were used for training.
 
-# Fine-tuning Method
+## Fine-tuning Method
 
 - Supervised Fine-Tuning (SFT)
 - LoRA-based training
 - LoRA weights merged into base model before upload
 - Loss applied only to assistant outputs
+- No external datasets were used
 
-No external datasets were used.
-
----
-
-# Reproducibility
+## Reproducibility
 
 Base model:
 Qwen/Qwen2.5-7B-Instruct
 
 Training framework:
+
 - Hugging Face Transformers
 - PEFT (LoRA)
 
 Evaluation decoding configuration:
+
 - do_sample=False
 - temperature=0.0
 - Deterministic generation
 
----
-
-# Usage
+## Usage
 
-```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
 model_id = "HamadaMayu/qwen2.5-7b-agent-trajectory-mixed_dbv4_alfv4_1to1"
@@ -104,13 +90,15 @@ output = model.generate(
 )
 
 print(tokenizer.decode(output[0], skip_special_tokens=True))
-```
-# Intended Use
+
+## Intended Use
+
 - AgentBench evaluation
 - Research on trajectory learning
 - Educational experiments
 
-# Limitations
+## Limitations
+
 - Performance may degrade outside AgentBench domains.
 - Long-horizon planning is limited by context length.
-- Invalid actions may still occur under distribution shift.
+- Invalid actions may still occur under distribution shift.