初始化项目，由ModelHub XC社区提供模型

Model: marin-community/delphi-2e20-1.9Bparams-14.8Btokens
Source: Original Platform

.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

README.md

@@ -0,0 +1,134 @@
+---
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+language:
+- en
+tags:
+- marin
+- delphi
+- scaling-laws
+- pretrained
+- research-only
+datasets:
+- nvidia/Nemotron-CC
+- bigcode/starcoderdata
+- EleutherAI/proof-pile-2
+---
+
+# delphi-2e20-1.9Bparams-14.8Btokens
+
+A 1.9B-parameter base model from the **Delphi** scaling suite. Trained at 2 × 10²⁰ FLOPs on 14.8B tokens with the Delphi recipe.
+
+## About Delphi
+
+Delphi is the Marin team's first open scaling suite, inspired by
+[Pythia](https://www.eleuther.ai/papers-blog/pythia-a-suite-for-analyzing-large-language-modelsacross-training-and-scaling).
+It has three parts:
+
+- a **scaling recipe** that maps compute budgets to model configurations,
+- a **scaling suite** of models trained from that recipe at IsoFLOP budgets
+  from 3 × 10¹⁸ to 1 × 10²³ FLOPs, and
+- a **scaling law** which uses the smaller Delphi models to predict the larger
+  ones.
+
+A pre-registered forecast from that scaling law predicted the final loss of the
+largest Delphi run (1 × 10²³ FLOPs, 25 B parameters, 600 B tokens) within
+**0.2%**, using **300× less compute** than the training run itself. The same
+process forecasts downstream benchmarks — MMLU, HumanEval, and GSM8K — via a
+two-step regression combining compute and observational scaling laws.
+
+See ["Scaling Laws That Extrapolate 300× Past the Fit"](https://openathena.ai/blog/delphi)
+for the recipe, fit, and downstream-eval projections. The full set of Delphi
+checkpoints — IsoFLOP grid points, held-out optima at 1e21/1e22/1e23 with
+multiple random seeds, and training intermediates — lives on
+[`marin-community`](https://huggingface.co/marin-community) on the Hub.
+
+This is a research artifact, not a production model.
+
+## Model details
+
+| | |
+|---|---|
+| Architecture | Qwen 3 (pre-norm decoder, RMSNorm, RoPE, QK-norm with learned scaling, SwiGLU MLPs) |
+| Parameters | 1,934,716,160 |
+| Hidden size | 2048 |
+| Layers | 21 |
+| Attention heads | 16 |
+| KV heads | 16 (no GQA) |
+| Head dim | 128 |
+| FFN intermediate | 8192 (MLP ratio 4) |
+| Vocab size | 128,256 (Llama 3 tokenizer) |
+| Max sequence length | 4096 |
+| Position encoding | RoPE (θ = 500000, Llama 3-style scaling) |
+| Bias terms | None |
+| Tied embeddings | No |
+
+## Training
+
+| | |
+|---|---|
+| Compute | 2 × 10²⁰ FLOPs |
+| Tokens | 14,805,106,688 |
+| Steps | 56,476 |
+| Sequence length | 4096 |
+| Optimizer | AdamH (Adam with Hyperball) |
+| Recipe | Delphi (Complete(d)P-style scaling with `(T₀/T)^0.3` token-horizon LR correction) |
+| LR schedule | WSD: 10% linear warmup, 20% linear decay, 0 floor |
+| Precision | f32 master params, bf16 compute |
+| Parallelism | FSDP |
+| Data mixture | Nemotron-CC + StarCoderData + ProofPile 2 |
+| Tokenizer | Llama 3 (vocab 128,256) |
+
+[AdamH](https://whenwen.github.io/wd_blog/public/hyperball-part-1.html), Adam
+with Hyperball, constrains every projection weight to stay on the Frobenius-
+norm sphere it was initialized on, so weight decay has nothing to regularize
+away and falls out of the recipe. A Complete(d)P-style transfer rule with a
+`(T₀/T)^0.3` correction sets learning rate as token horizon grows. Reference
+constants: B₀ = 64, T₀ = 2.5 B tokens, η₀ = 0.00630, η₀,Adam = 0.000656,
+ε₀ = 1.85 × 10⁻⁸. Recipe code:
+[`experiments/scaling_law_sweeps/completed_adamh.py`](https://github.com/marin-community/marin/blob/main/experiments/scaling_law_sweeps/completed_adamh.py).
+
+## Companion releases
+
+- All Delphi model checkpoints: [`marin-community`](https://huggingface.co/marin-community) on the Hub.
+- Plot data behind every figure in the blog post:
+  [`marin-community/delphi-blog-data`](https://huggingface.co/datasets/marin-community/delphi-blog-data) (one config per figure, with `wandb_url` on every row).
+- Pipelines that deterministically reproduce the training mixture from public
+  Nemotron-CC, StarCoderData, and ProofPile 2 sources: see the Marin repo.
+
+## Evaluation
+
+This checkpoint is part of the Delphi eval suite
+([`experiments/exp1337_eval_suite.py`](https://github.com/marin-community/marin/blob/main/experiments/exp1337_eval_suite.py)),
+which scores every Delphi run alongside reference open-weights baselines
+(Qwen 3, Llama 2/3, OLMo 2, Marin 8B). Following the blog's two-step
+forecast, soft metrics (per-choice log-prob for multiple-choice tasks,
+bits-per-byte for generative tasks) carry the signal the scaling law is fit on,
+and a sigmoid fit on an external model pool maps soft metric to hard metric
+(accuracy, pass@1, exact-match). Below ~1e21 FLOPs the hard metrics stay near
+chance even when the underlying probabilities are improving smoothly; that is
+expected and is exactly why the soft metrics exist.
+
+## Limitations
+
+- Trained on an English-heavy web mixture; no multilingual coverage.
+- Pretrained-only — no instruction tuning, RLHF, or safety alignment.
+- The Delphi recipe targets compute-optimal training, not inference-cost-aware
+  overtraining; for inference-heavy deployments, an overtrained smaller model
+  may be preferable. The blog's "off-optimal training" section quantifies the
+  penalty.
+- This is one checkpoint in a much larger Delphi release; pick the one that
+  matches your compute / parameter / token regime, or browse the full set at
+  [`marin-community`](https://huggingface.co/marin-community).
+
+## Citation
+
+```bibtex
+@misc{held2026delphi,
+  title  = {Scaling Laws That Extrapolate 300× Past the Fit},
+  author = {Held, Will and {Marin Community}},
+  year   = {2026},
+  url    = {https://openathena.ai/blog/delphi}
+}
+```

config.json

@@ -0,0 +1,118 @@
+{
+  "vocab_size": 128256,
+  "max_position_embeddings": 4096,
+  "hidden_size": 2048,
+  "intermediate_size": 8192,
+  "num_hidden_layers": 21,
+  "num_attention_heads": 16,
+  "use_sliding_window": false,
+  "sliding_window": null,
+  "max_window_layers": 28,
+  "num_key_value_heads": 16,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "initializer_range": 0.02,
+  "rms_norm_eps": 1e-05,
+  "use_cache": true,
+  "rope_theta": 500000,
+  "rope_scaling": {
+    "factor": 8.0,
+    "low_freq_factor": 1.0,
+    "high_freq_factor": 4.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "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"
+  ],
+  "return_dict": true,
+  "output_hidden_states": false,
+  "torchscript": false,
+  "dtype": null,
+  "pruned_heads": {},
+  "tie_word_embeddings": false,
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": false,
+  "is_decoder": false,
+  "cross_attention_hidden_size": null,
+  "add_cross_attention": false,
+  "tie_encoder_decoder": false,
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "finetuning_task": null,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "task_specific_params": null,
+  "problem_type": null,
+  "tokenizer_class": null,
+  "prefix": null,
+  "bos_token_id": 128000,
+  "pad_token_id": null,
+  "eos_token_id": 128001,
+  "sep_token_id": null,
+  "decoder_start_token_id": 128000,
+  "max_length": 20,
+  "min_length": 0,
+  "do_sample": false,
+  "early_stopping": false,
+  "num_beams": 1,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "typical_p": 1.0,
+  "repetition_penalty": 1.0,
+  "length_penalty": 1.0,
+  "no_repeat_ngram_size": 0,
+  "encoder_no_repeat_ngram_size": 0,
+  "bad_words_ids": null,
+  "num_return_sequences": 1,
+  "output_scores": false,
+  "return_dict_in_generate": false,
+  "forced_bos_token_id": null,
+  "forced_eos_token_id": null,
+  "remove_invalid_values": false,
+  "exponential_decay_length_penalty": null,
+  "suppress_tokens": null,
+  "begin_suppress_tokens": [
+    128000,
+    128001
+  ],
+  "num_beam_groups": 1,
+  "diversity_penalty": 0.0,
+  "_name_or_path": "",
+  "transformers_version": "4.57.5",
+  "no_bias": true,
+  "tf_legacy_loss": false,
+  "use_bfloat16": false,
+  "model_type": "qwen3",
+  "output_attentions": false
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d378cac689dc0a6cecf14f0b24847b902242a7405b43e5be749314290a2224ca
+size 4987231936

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c8136f3790bbee487d0eaef35b69de382b4fcdac614db751a486a512a435bfc
+size 2751659344

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}