初始化项目，由ModelHub XC社区提供模型

Model: namkoong-lab/LatentGym_Qwen3-8B_1episode_4Envs_LOO_wordladder
Source: Original Platform

README.md

@@ -0,0 +1,47 @@
+---
+base_model: Qwen/Qwen3-8B
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+language: [en]
+tags:
+  - qwen3
+  - meta-rl
+  - in-context-learning
+  - grpo
+---
+
+# LatentGym_Qwen3-8B_1episode_4Envs_LOO_wordladder
+
+GRPO-fine-tuned Qwen3-8B for in-context meta-learning held-out-wordladder (3 train envs, N=1). Part of the [LatentGym](https://huggingface.co/collections/namkoong-lab/latentgym) testbed.
+
+## Environments & training latents
+
+| Env | Latents seen during training |
+|---|---|
+| hangman | `vowel_count_4`, `ending_ABLE` |
+| secretary | `inverse_order`, `fixed_position_2` |
+| number_guessing | `set_of_3`, `range_100` |
+
+## Training hyperparameters
+
+| | |
+|---|---|
+| Base model | `Qwen/Qwen3-8B` |
+| Algorithm | GRPO |
+| Optimizer | AdamW (β₁=0.9, β₂=0.999) |
+| Learning rate | 5e-07 |
+| LR schedule | constant_with_warmup |
+| Weight decay | 0.01 |
+| Max grad norm | 1.0 |
+| KL coefficient β | 0.04 |
+| Clip range ε | 0.2 |
+| Train batch (prompts) | 32 |
+| Mini-batch | 1 |
+| Rollouts per prompt | 8 |
+| Episodes per trajectory (N) | 1 |
+| Reward Φ | Σᵢ Gᵢ (cumulative) |
+| Epochs | 20 |
+| Max generation length | 64 |
+| Sampling (train) | T=0.8, top-p=0.95 |
+| Seed | 263 |