From 6d1d1513130bcb4d880e271cf9a259303c2c6534 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 5 Sep 2026 20:48:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: steven0226/qwen2.5-1.5b-wordle-grpo-merged Source: Original Platform --- .gitattributes | 36 ++++++++++++++++++ README.md | 84 ++++++++++++++++++++++++++++++++++++++++++ chat_template.jinja | 54 +++++++++++++++++++++++++++ config.json | 61 ++++++++++++++++++++++++++++++ generation_config.json | 14 +++++++ model.safetensors | 3 ++ tokenizer.json | 3 ++ tokenizer_config.json | 30 +++++++++++++++ 8 files changed, 285 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 model.safetensors create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..33db8ba --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +license: apache-2.0 +base_model: Qwen/Qwen2.5-1.5B-Instruct +pipeline_tag: text-generation +tags: +- reinforcement-learning +- grpo +- agentic-rl +- multi-turn +- wordle +- merged-model +language: +- en +--- + +# Qwen2.5-1.5B Wordle GRPO merged full model + +## Repository role + +This repository contains the historical **merged full model** counterpart of the Wordle GRPO +LoRA adapter. It does not require a separately attached LoRA adapter for loading. The base +repository identity is `Qwen/Qwen2.5-1.5B-Instruct`; the current `model.safetensors` LFS SHA-256 is +`b6c55086e798e1f62e6d970f07ee97ab39c1e0af3ee4b6ecdb2a349e485087af`. + +The repository relationship is supported by historical documentation, subject to the lineage +limits below. It is not a cryptographically complete adapter-to-merged derivation record. + +## Evaluation + +The published 463-word result originates from the adapter evaluation. No independent 463-word evaluation was run against these merged bytes, so the adapter result is not an independent replication of merged-model performance. The aggregate adapter result is included here only to +document the paired project evidence without inventing a separate merged-model result. + +| Measure | Base | Tuned LoRA adapter evidence | +|---|---:|---:| +| Wins | 0/463 | 13/463 = 2.81% | +| Wilson 95% CI | 0.00%–0.82% | 1.65%–4.74% | +| Protocol adherence | 0% | 2749/2753 = 99.85% | +| Legal actions | 0% | 2748/2753 = 99.82% | + +The paired discordance was 0 base-only wins and 13 tuned-only wins. The two-sided exact paired +McNemar result is `0.000244140625`; treating the interim and final evaluations as two looks gives +the conservative Bonferroni-adjusted value `0.00048828125`. + +The adapter evaluation also recorded 1340/2290 absent-letter reuses and 1119/2290 broken green +positions on turns with information. + +**Protocol learning succeeded; strategy learning remained limited; this is not a practical Wordle solver.** The 2.81% adapter win rate must not be presented as an independently measured +merged-model win rate, practical capability, or general RL superiority. + +## Evidence links + +- Immutable research/evidence source: + https://github.com/kuotunyu/agentic-rl-wordle/commit/1a077a45e309594e5bb43743a8b84d89155595d4 +- Stable source release URL: + https://github.com/kuotunyu/agentic-rl-wordle/releases/tag/v1.0.0 +- Aggregate report: `results/full_463_report.json` +- Recomputed analysis: `results/full_463_analysis.json` +- Public claim mapping: `docs/claim-matrix.md` + +## Limitations + +- Only aggregate 463-game evidence is committed; full per-episode records are unavailable. +- The historical GPU environment is not bit-for-bit reconstructable. +- The exact upstream Qwen commit was not preserved. +- The adapter-to-merged command and manifest were not preserved, and the historical record lacks + an end-to-end run→code→prompt→bundle→model cryptographic chain. The relationship is documentary lineage, not complete cryptographic proof. +- The cfreshman word lists are fetch-only and have no explicit license. Apache-2.0 does not license the cfreshman word lists. +- Representative transcripts are illustrations, not a complete raw evaluation corpus. +- No independent evaluation of these merged bytes is available; do not infer byte-level + equivalence or independently replicated performance from the documentary relationship. + +## Loading + +This repository is intended to load as a full causal language model and does not need a separate +PEFT adapter attachment. Because the exact historical upstream base revision and merge manifest +are unavailable, do not claim a complete cryptographic reconstruction of the merge. + +```python +from transformers import AutoModelForCausalLM + +model = AutoModelForCausalLM.from_pretrained( + "steven0226/qwen2.5-1.5b-wordle-grpo-merged" +) +``` diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..97c2b63 --- /dev/null +++ b/config.json @@ -0,0 +1,61 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 1536, + "initializer_range": 0.02, + "intermediate_size": 8960, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 21, + "model_type": "qwen2", + "num_attention_heads": 12, + "num_hidden_layers": 28, + "num_key_value_heads": 2, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.12.1", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..a8aca90 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.1, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.12.1" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..d7d7779 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6c55086e798e1f62e6d970f07ee97ab39c1e0af3ee4b6ecdb2a349e485087af +size 3087467144 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..34510ff --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..770e41d --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "is_local": false, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}