commit 0d9ba56b127a9031501d9901d40e77fe517a888f Author: ModelHub XC Date: Wed Jun 3 08:55:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bfpill/gemma-3-270m-sft-skywork-chosen Source: Original Platform 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..d3dfe96 --- /dev/null +++ b/README.md @@ -0,0 +1,107 @@ +--- +library_name: transformers +base_model: google/gemma-3-270m +license: gemma +datasets: + - Skywork/Skywork-Reward-Preference-80K-v0.2 +language: + - en +tags: + - gemma3 + - sft + - research + - skywork +pipeline_tag: text-generation +--- + +# gemma-3-270m SFT'd on Skywork-Reward-Preference-80K (chosen-only) + +A response-only SFT of [`google/gemma-3-270m`](https://huggingface.co/google/gemma-3-270m) +on the **chosen** responses of +[`Skywork/Skywork-Reward-Preference-80K-v0.2`](https://huggingface.co/datasets/Skywork/Skywork-Reward-Preference-80K-v0.2). + +This is the anchor checkpoint used as the SFT reference policy for a research +project on **data-space DPO** — applying preference signal by reweighting SFT +samples through a susceptibility matrix, instead of via DPO's weight-space +gradient descent. It is **not** intended as a useful chat model — at 270M +parameters and a single epoch of SFT, generations are at best "coherent text +on the topic of the prompt". The role of this checkpoint is to be a +controlled, reproducible anchor for sampling-based experiments. + +## Training recipe + +| | | +|---|---| +| Base | `google/gemma-3-270m` (pretrained, no chat template) | +| Data | `Skywork/Skywork-Reward-Preference-80K-v0.2`, chosen responses only (~77K examples) | +| Epochs | 1 | +| Learning rate | 2e-5, cosine schedule, 3% warmup | +| Batch size | 16 per device × 4 GPUs = 64 effective | +| Precision | bf16 + gradient checkpointing | +| Loss | response-only cross-entropy (prompt tokens masked to -100) | +| Total steps | 602 | +| Final train loss | 1.41 | +| Wall time | ~4 min on 8× H100 | + +## Prompt format + +The base model has no `chat_template`, so we use a fixed plain-text format +matching the SFT distribution: + +```text +Human: +Assistant: ASSISTANT_RESPONSE +``` + +Internally the prompt prefix is `"Human: \n\nAssistant:"` and the loss is +computed only on the tokens following `Assistant:`. + +## Quick start + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +mid = "bfpill/gemma-3-270m-sft-skywork-chosen" +tok = AutoTokenizer.from_pretrained(mid) +model = AutoModelForCausalLM.from_pretrained(mid, torch_dtype=torch.bfloat16).cuda().eval() + +prompt = f"Human: What is the capital of France?\n\nAssistant:" +ids = tok(prompt, return_tensors="pt").to(model.device) +out = model.generate( + **ids, max_new_tokens=80, do_sample=False, + repetition_penalty=1.15, pad_token_id=tok.eos_token_id, +) +print(tok.decode(out[0, ids.input_ids.shape[1]:], skip_special_tokens=True)) +``` + +## Limitations + +- 270M params, 1 epoch of SFT on ~77K examples. Generations are short and + often factually incorrect. +- Trained exclusively on the Skywork prompt distribution; performance on + other distributions (instruction-following, dialogue, code, math) + reflects the base model plus a thin Skywork-flavoured veneer. +- Not preference-tuned. The whole point of this checkpoint is to be the + anchor for a follow-up data-space patterning experiment that is the + *replacement* for the usual DPO step. +- Inherits the base model's biases and license restrictions. + +## License + +Gemma Terms of Use — see [Google's Gemma license](https://ai.google.dev/gemma/terms). +This SFT preserves the base model's weights structure; usage is subject to +the same terms. + +## Source code + +The trainer that produced this checkpoint: +`rm-patterning/policy/sft_anchor.py` in +`timaeus-research/timaeus@max/rm-scaling` (commit `3a3e0755e` and later). + +```bash +torchrun --nproc_per_node=8 rm-patterning/policy/sft_anchor.py \ + --base-model google/gemma-3-270m \ + --output-dir ./gemma-3-270m-sft-skywork-chosen \ + --epochs 1 --learning-rate 2e-5 --batch-size 16 --max-length 1024 +``` diff --git a/config.json b/config.json new file mode 100644 index 0000000..282ec64 --- /dev/null +++ b/config.json @@ -0,0 +1,62 @@ +{ + "_sliding_window_pattern": 6, + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "bos_token_id": 2, + "dtype": "bfloat16", + "eos_token_id": 1, + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 640, + "initializer_range": 0.02, + "intermediate_size": 2048, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "num_attention_heads": 4, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "pad_token_id": 0, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "full_attention": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_attention": { + "rope_theta": 10000.0, + "rope_type": "default" + } + }, + "sliding_window": 512, + "tie_word_embeddings": true, + "transformers_version": "5.2.0", + "use_bidirectional_attention": false, + "use_cache": false, + "vocab_size": 262144 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..8e8e8eb --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 2, + "cache_implementation": "hybrid", + "do_sample": true, + "eos_token_id": [ + 1 + ], + "pad_token_id": 0, + "top_k": 64, + "top_p": 0.95, + "transformers_version": "5.2.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..d859f1e --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96fa31398b1277b7614c99e9c4aa14e509492dd33fc1816d81cc063aa0d7d7cd +size 536223056 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..899af07 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a74aefb1dc1340a25f29ab8370384b9ed24b2d921d7749ece7bbcfcfdf00d497 +size 33384443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..9e8a20e --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,24 @@ +{ + "backend": "tokenizers", + "boi_token": "", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eoi_token": "", + "eos_token": "", + "image_token": "", + "is_local": false, + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "model_specific_special_tokens": { + "boi_token": "", + "eoi_token": "", + "image_token": "" + }, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": null, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}