初始化项目，由ModelHub XC社区提供模型

Model: openeurollm/oellm-9b-128k-theta32m-v3 Source: Original Platform
2026-07-11 11:21:10 +08:00
commit 5c4638659c
9 changed files with 1378 additions and 0 deletions
--- a/.gitattributes
+++ 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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+language: [en, sv, de, fr, es, it, nl, pl, pt, cs, fi, da, el, bg, hr, hu, ro, sk, sl, et, lt, lv, ga, mt, eu, gl, is, nb, nn, sr, uk, ca, mk, sq, oc, lb, bs]
+tags: [long-context, rope, abf, niah, qwen3, openeurollm, base-model, 128k]
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# OELLM 9B — 128K context (ABF, θ=32M) — v3 (full training)
+
+**Full-training production version** of [`oellm-9b-128k-theta32m`](https://huggingface.co/birgermoell/oellm-9b-128k-theta32m).
+Long-context extension of OpenEuroLLM `baby_9b_dense` (Qwen3 dense 9B), 4K → **128K** via native
+ABF (RoPE θ-scaling). Same θ=32M config as the sweep arm but trained on **2B tokens** (≈6×).
+**Base model — not instruction-tuned.** Multilingual.
+
+## Evaluation — verified, multilingual (this checkpoint)
+Base-LM forced-choice NIAH, depth-stratified, at **128K**, 12 European languages:
+
+| metric | result |
+|---|---|
+| **Overall 128K** | **100% (341/341)** |
+| **depth-0 (far start)** | **100% in every language** (6/6 each) |
+| Languages | cs de el en es fi fr hu pl pt sv uk — **all 100%** |
+| 4K / 16K / 64K | 100% |
+
+Full training lifted the two languages that were 96% in the sweep arm (el, sv) to 100%.
+
+## Why θ=32M (the key finding)
+Far-position (depth-0) retrieval failure at long context is a **RoPE high-dimension OOD**
+problem, **not** a data problem — fixed by scaling θ to the target length. Critical θ ≈ doubles
+per length-octave: 64K→8M, 128K→16M→**32M (100%)**, 256K→~32M. θ ablation at 128K depth-0:
+2M/5M→0%, 8M→0%, 16M→90%, **32M→100%**. (cf. LongRoPE2, arXiv:2502.20082.)
+
+## How to reproduce
+**Base:** OELLM `baby_9b_dense` (Qwen3 dense): 36 layers, hidden 4096, FFN 12288, 32 heads /
+8 KV (GQA), kv-channels 128, qk-layernorm, RMSNorm, SwiGLU, untied embeddings, vocab 262144,
+`openeurollm/tokenizer-256k`, native 4K.
+
+**Recipe:** staged native ABF, `4K→16K→32K→64K(θ=2M)→128K(θ=32M)`; this model = the **128K@θ=32M
+stage trained to 2B tokens** from the 64K checkpoint (`--finetune`).
+
+**Training (Megatron-LM, LUMI 16× MI250X):**
+```
+--rotary-base 32000000 --seq-length 131072 --max-position-embeddings 131072 --use-flash-attn
+--tensor-model-parallel-size 8 --context-parallel-size 8 --sequence-parallel --use-distributed-optimizer
+--micro-batch-size 1 --global-batch-size 64 --bf16 --train-iters ~238 (2B tokens)
+--lr 1e-5 --min-lr 1e-6 --lr-decay-style cosine --weight-decay 0.1 --clip-grad 1.0
+--recompute-activations --recompute-granularity selective --save-interval 100
+--qk-layernorm --normalization RMSNorm --swiglu --group-query-attention --num-query-groups 8
+```
+ROCm 6.4.4 / PyTorch 2.9 / TE 2.4 / FA 2.8; ~490 tok/s/GPU at 128K.
+
+**Data:** Jouni Luoma's length-biased multilingual long-context mix (finepdfs all langs + edu,
+dclm, hplt3, multisynth, nemotron, megamath, starcoder, pes2o, arxiv, wiki; tiered
+short/medium/long). Note: depth-0 is **insensitive** to the data mix — θ is the lever.
+
+**Reproduce the eval:**
+```
+python scripts/eval_base_lm_niah.py --model <this-model> \
+  --context-lengths 4096 16384 65536 131072 --depths 0.0 0.25 0.5 0.75 1.0 \
+  --languages en de fr es nl pl sv fi cs it pt el hu uk da --trials 6
+```
+Code / write-ups: https://github.com/BirgerMoell/openeuro-longctx-datamix
+
+## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+m = AutoModelForCausalLM.from_pretrained("birgermoell/oellm-9b-128k-theta32m-v3",
+                                         torch_dtype=torch.bfloat16, device_map="auto")
+tok = AutoTokenizer.from_pretrained("birgermoell/oellm-9b-128k-theta32m-v3")
+```
+
+## Caveats
+- **Base model** (no instruction tuning) — use as a completion model.
+- Evaluated with **single-needle** forced-choice NIAH; broader multi-task RULER not yet run.
+- Keep `rope_theta=32000000`, `max_position_embeddings=131072` for 128K.
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,3 @@
+{
+  "<pad>": 262144
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 32000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 263168
+}
--- a/pytorch_model.bin
+++ b/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d2e969ff77e8320faf6fc5aa0bb115b8f10441e0c31f2fc677c05a94221c94a
+size 18204021587
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,142 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>",
+    "<start_of_image>",
+    "<end_of_image>",
+    "<image_soft_token>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<tool_call>",
+    "</tool_call>",
+    "<unused_0>",
+    "<unused_1>",
+    "<unused_2>",
+    "<unused_3>",
+    "<unused_4>",
+    "<unused_5>",
+    "<unused_6>",
+    "<unused_7>",
+    "<unused_8>",
+    "<unused_9>",
+    "<unused_10>",
+    "<unused_11>",
+    "<unused_12>",
+    "<unused_13>",
+    "<unused_14>",
+    "<unused_15>",
+    "<unused_16>",
+    "<unused_17>",
+    "<unused_18>",
+    "<unused_19>",
+    "<unused_20>",
+    "<unused_21>",
+    "<unused_22>",
+    "<unused_23>",
+    "<unused_24>",
+    "<unused_25>",
+    "<unused_26>",
+    "<unused_27>",
+    "<unused_28>",
+    "<unused_29>",
+    "<unused_30>",
+    "<unused_31>",
+    "<unused_32>",
+    "<unused_33>",
+    "<unused_34>",
+    "<unused_35>",
+    "<unused_36>",
+    "<unused_37>",
+    "<unused_38>",
+    "<unused_39>",
+    "<unused_40>",
+    "<unused_41>",
+    "<unused_42>",
+    "<unused_43>",
+    "<unused_44>",
+    "<unused_45>",
+    "<unused_46>",
+    "<unused_47>",
+    "<unused_48>",
+    "<unused_49>",
+    "<unused_50>",
+    "<unused_51>",
+    "<unused_52>",
+    "<unused_53>",
+    "<unused_54>",
+    "<unused_55>",
+    "<unused_56>",
+    "<unused_57>",
+    "<unused_58>",
+    "<unused_59>",
+    "<unused_60>",
+    "<unused_61>",
+    "<unused_62>",
+    "<unused_63>",
+    "<unused_64>",
+    "<unused_65>",
+    "<unused_66>",
+    "<unused_67>",
+    "<unused_68>",
+    "<unused_69>",
+    "<unused_70>",
+    "<unused_71>",
+    "<unused_72>",
+    "<unused_73>",
+    "<unused_74>",
+    "<unused_75>",
+    "<unused_76>",
+    "<unused_77>",
+    "<unused_78>",
+    "<unused_79>",
+    "<unused_80>",
+    "<unused_81>",
+    "<unused_82>",
+    "<unused_83>",
+    "<unused_84>",
+    "<unused_85>",
+    "<unused_86>",
+    "<unused_87>",
+    "<unused_88>",
+    "<unused_89>",
+    "<unused_90>",
+    "<unused_91>",
+    "<unused_92>",
+    "<unused_93>",
+    "<unused_94>",
+    "<unused_95>",
+    "<unused_96>",
+    "<unused_97>",
+    "<unused_98>",
+    "<unused_99>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce296af846f114e330e8e62887df4c6abafd4fd682434fb0ced1a3abfa2e04c1
+size 37807304
--- a/tokenizer.model
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac214401227404105817141c21c6693e3b17c878465a42765d2c345310e003ce
+size 4876269
--- a/tokenizer_config.json
+++ b/tokenizer_config.json