Update README.md

README.md

@@ -23,7 +23,8 @@ language:
 - **Language(s):** Multilingual (primarily tested on English/Japanese/Reasoning tasks)
 - **License:** Apache 2.0
 - **Training Algorithm:** GRPO (via TRL and Unsloth)
-
+- **Purpose:** **Environment Validation / Proof of Concept**
+  - This model was primarily developed to verify the successful setup and integration of the **ThinkStation PGX(GB10 Blackwell)** local environment with the Unsloth/GRPO training pipeline.
 
 This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 
@@ -55,13 +56,13 @@ The use of the **ThinkStation PGX** allows for:
 
 The model was trained using the GRPO algorithm, which optimizes the policy by comparing a group of outputs against each other based on reward functions (e.g., accuracy for math/logic or format consistency) without requiring a separate value function (critic model).
 
-### Training Hyperparameters (Example)
+### Training Hyperparameters
 - **Learning Rate:** 5e-6
 - **Batch Size:** 1
-- **Gradient Accumulation Steps:** 4
+- **Gradient Accumulation Steps:** 1
 - **Num Generations (G):** 8
 - **Max Sequence Length:** 2048
-- **Optimizer:** AdamW
+- **Optimizer:** AdamW_8bit
 
 ## How to use
 
@@ -72,7 +73,7 @@ from unsloth import FastLanguageModel
 import torch
 
 model, tokenizer = FastLanguageModel.from_pretrained(
-    model_name = "your-username/your-model-name",
+    model_name = "ikedachin/qwen_finetune_16bit_unsloth_gb10",
     max_seq_length = 2048,
     load_in_4bit = True,
 )