birgermoell/oellm-9b-256k-sft

OELLM 9B 256K SFT

Experimental instruction-tuned checkpoint derived from openeurollm/oellm-9b-256k-theta64m-prelude. It is the first SFT stage of an OpenEuroLLM post-training experiment on LUMI. The base is a dense Qwen3 9B model using the independent OpenEuroLLM 256K tokenizer and a 262,144-token context configuration.

This repository contains the SFT model, not the subsequent SimPO model.

Intended use and interpretation

The purpose of this checkpoint is to test whether short-sequence instruction tuning can add useful chat behavior while retaining the base model's long-context capability. It is not presented as a reasoning-specialized model. The 262,144-token configuration describes the maximum input length accepted by the architecture; it does not, by itself, establish accurate retrieval at that length.

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "birgermoell/oellm-9b-256k-sft"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    dtype=torch.bfloat16,
    device_map="auto",
).eval()

messages = [{"role": "user", "content": "Förklara allemansrätten kort på svenska."}]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    return_tensors="pt",
    return_dict=True,
).to(model.device)

with torch.inference_mode():
    output = model.generate(
        **inputs,
        max_new_tokens=256,
        eos_token_id=tokenizer.eos_token_id,
        pad_token_id=tokenizer.pad_token_id,
    )
print(tokenizer.decode(output[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Long-context inference, especially near 256K, requires multiple GPUs for the KV cache. Keep max_position_embeddings=262144 and rope_theta=64000000 unchanged.

Training

Field	Value
Base	openeurollm/oellm-9b-256k-theta64m-prelude
Method	Full-parameter supervised fine-tuning with packed sequences and FlashAttention 2
Data	920,552 Tulu-3 rows + 161,644 EuroBlocks rows + a 250,000-row Nemotron-v2 math prefix
Loaded examples	1,332,196 source conversations before tokenization and packing
Sequence length	4,096
Steps	3,000 (about 0.604 epoch)
Global batch	128
Optimizer schedule	AdamW, peak LR 6e-6, cosine decay, 3% warmup
Hardware	4 LUMI-G nodes, 32 AMD MI250X GCDs
Runtime	14h 36m
Final training loss	0.7671
Final mean token accuracy	0.7839

The published weights are an unquantized BF16 export of the consolidated training checkpoint.

Training-data composition

The counts below were reconstructed from the exact YAML, source JSONL files, and Parquet metadata used by LUMI job 20290451. They are effective row counts for this run, rather than nominal counts copied from upstream dataset cards.

Effective mixture

Effective training slice	Rows	Share	Role in the run
Staged allenai/tulu-3-sft-mixture commercial subset	920,552	69.10%	General instruction replay, predominantly English but with multilingual rows in several components
Staged utter-project/EuroBlocks-SFT-Synthetic-1124 subset	161,644	12.13%	Synthetic European-language instruction following
First 250,000 rows of the staged nvidia/Nemotron-Post-Training-Dataset-v2 math file	250,000	18.77%	English math prompts with synthetic <think> reasoning traces and boxed answers
Total	1,332,196	100%	Source conversations loaded before tokenization and packing

The first two slices form the 1,082,196-row general Parquet. Within that Parquet the ratio is 85.06% Tulu to 14.94% EuroBlocks, which explains the staging-directory name tulu3-euroblocks-85-15. Adding the reasoning slice changes the overall ratio to the one shown above. These are row shares, not token shares.

Tulu-3 subset: exact source counts

The run did not load the current public Tulu-3 mixture wholesale. It used a locally staged file named tulu3-commercial.jsonl with 920,552 rows. Its preserved source field gives the following breakdown; raw source identifiers are shown to avoid silently relabeling the data:

Tulu source identifier	Rows
ai2-adapt-dev/personahub_math_v5_regen_149960	148,492
ai2-adapt-dev/evol_codealpaca_heval_decontaminated	106,173
ai2-adapt-dev/tulu_v3.9_wildchat_100k	99,031
ai2-adapt-dev/tulu_v3.9_aya_100k	98,991
ai2-adapt-dev/flan_v2_converted	89,062
ai2-adapt-dev/numinamath_tir_math_decontaminated	63,667
allenai/tulu-3-sft-personas-math-grade	49,504
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k	49,498
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k	49,491
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k	49,465
ai2-adapt-dev/personahub_code_v2_34999	34,657
ai2-adapt-dev/personahub_ifdata_manual_seed_v3_29980	29,678
ai2-adapt-dev/tulu_v3.9_personahub_math_interm_algebra_20k	19,798
ai2-adapt-dev/coconot_converted	10,894
ai2-adapt-dev/tulu_v3.9_sciriff_10k	9,895
ai2-adapt-dev/oasst1_converted	7,063
ai2-adapt-dev/tulu_v3.9_table_gpt_5k	4,957
ai2-adapt-dev/tulu_hard_coded_repeated_10	236
Total	920,552

The non-commercial No Robots component listed by the full Tulu-3 card is not present in this staged file. The staging label commercial describes the selected artifact; users should still review the Tulu collection license and every component's terms. The file has no normalized language column, so we do not infer exact per-language counts for this slice from prompt text.

EuroBlocks subset: language labels

All 161,644 rows identify EuroBlocks-SFT-Synthetic-1124 as their source. Their IDs run from EuroBlocks-SFT-Synthetic-1124_1 through _161644; this is smaller than the 340,286-row train split described by the public EuroBlocks card. The staged rows contain the following language labels:

Language label	Rows	Language label	Rows
Unlabelled	23,318	Spanish	17,428
Italian	15,963	French	14,882
German	14,081	Portuguese	13,966
Hindi	7,982	Dutch	7,683
Swedish	6,476	Polish	5,358
Ukrainian	5,191	Japanese	4,735
Russian	4,727	Czech	4,105
Hungarian	4,010	Romanian	3,993
Korean	2,905	Finnish	1,022
Slovak	990	Portuguese (Portugal)	672
Greek	582	Norwegian	534
Catalan	223	Bulgarian	210
Slovenian	201	Estonian	179
Latvian	176	Croatian	30
Icelandic	18	Danish	4

The 23,318 unlabelled rows are reported as such rather than assigned a language after the fact. Spot checks found English examples among them, but no language-ID pass was run for this audit. EuroBlocks is synthetic and its dataset card documents mixed upstream sources and terms.

Reasoning slice: what was actually selected

The reasoning builder concatenated two local artifacts in this order:

1. Nemotron-Post-Training-Dataset-v2/math.jsonl: 1,426,602 rows in the frozen LUMI artifact;
2. Llama-Nemotron-Post-Training-Dataset/SFT-math-sample-100k.jsonl: 100,000 rows, described by the local builder as including Finnish DeepSeek math.

It converted each {input, output} record into a messages conversation and wrote a 1,526,602-row Parquet. The training YAML then requested train[:250000]. Because this was a prefix selection, all 250,000 effective reasoning rows came from the first Nemotron-v2 math artifact and zero came from the later Finnish-inclusive 100k file. This was not a randomized 250k sample. The linked NVIDIA card is the origin and terms reference; the local frozen artifact's row count is reported here because it is the file actually used by this run.

Formatting and sequence construction

• General rows were already stored as {id, messages}; reasoning rows were converted to {messages} by appending the output as an assistant turn.
• Conversations were rendered with the tokenizer's included chat template and <end_of_turn> EOS, then packed into sequences with a maximum length of 4,096 tokens.
• This stage did not train on 256K-token sequences. The architectural 262,144-token setting comes from the base checkpoint and was evaluated after short-sequence SFT.
• The SFT recipe records no additional post-concatenation deduplication or benchmark- decontamination pass. Some Tulu components were already distributed as decontaminated variants, as reflected in their source identifiers.
• Only a training split was loaded; no held-out validation split from these sources was used during optimization.

Training-data terms are not replaced by the model repository's Apache-2.0 weight license. Tulu-3 is an ODC-BY-1.0 collection with component-specific terms; EuroBlocks documents mixed upstream terms; and Nemotron-v2 documents per-sample licenses plus possible model-output terms. Review those cards before redistribution or commercial use.

Export validation

Before publication, the BF16 export was required to pass a Transformers GPU smoke test covering:

• model and tokenizer loading;
• finite forward-pass logits;
• the native OpenEuroLLM turn-token chat template;
• generation in Swedish, English, and German;
• BF16 weight dtypes;
• 262,144-token context metadata and RoPE theta 64M.

Long-context retrieval

The main question for this checkpoint is whether it can still retrieve information after SFT on 4K sequences. We ran deterministic needle-in-a-haystack (NIAH) probes on the exact published BF16 artifact. One passphrase was inserted at each of five token depths (0%, 25%, 50%, 75%, and 100%), then the model was asked to return it with greedy decoding.

The primary metric is full retrieval: the complete correct passphrase appears anywhere in the answer. Exact format is secondary: the answer contains only the requested passphrase. A verbose answer containing the correct value is therefore a retrieval success and an instruction-format miss.

Natural word passphrases (primary retrieval test)

Requested context	Full retrieval	Exact format
512	5/5	5/5
1K	5/5	5/5
2K	5/5	4/5
4K	5/5	4/5
8K	5/5	5/5
32K	5/5	2/5
128K	5/5	0/5
~262K	5/5	0/5

Outcome: 40/40 full-passphrase retrieval across all eight tested lengths and all five depths. The ~262K prompts contained 262,047 to 262,052 actual input tokens, leaving room for generation inside the model's 262,144-token limit. This verifies full-span single-needle retrieval for this checkpoint; it does not imply 256K reasoning or synthesis quality.

All 40 natural-word cases retained the complete passphrase. Exact-output compliance fell at longer lengths because the model often wrapped the correct passphrase in a sentence.

The 512-to-8K result gives no evidence of a short-context retrieval collapse from RoPE theta 64M. This probe cannot rule out subtler short-context quality or perplexity effects; attributing those to theta would require an otherwise identical lower-theta control checkpoint.

Random hexadecimal codes (hard copying stress test)

Random codes are unusually difficult for this tokenizer because much of each code becomes character/byte-fallback tokens. The model retrieved only 11/25 codes from 512 through 8K, sometimes returning the record ID rather than its passkey. The same harder test retrieved the full correct code at 5/5 depths at 32K, 5/5 at 128K, and 5/5 at ~262K. This non-monotonic pattern points to synthetic-code copying/entity confusion, not loss of access to distant context.

Natural word passphrases were stable at every length. Random hexadecimal copying was unreliable at 512-8K but succeeded at every tested depth from 32K onward; with five cases per point, this should be read as a diagnostic pattern rather than evidence that longer inputs improve the model.

Representative outputs

The inputs below reproduce the evaluated prompt structure, with repeated filler omitted. Outputs are shown verbatim.

Success: exact retrieval at 32K, needle at 50%

Input (truncated from 32,765 tokens):

Read the following archive carefully. One important record is hidden among routine background
material. Remember that record and answer the question at the end.
[routine archive filler omitted]
IMPORTANT RECORD: The passkey for record-524f75bb is sunrise-wren-raven.
[routine archive filler omitted]
Question: What is the passkey for record-524f75bb? Answer with only the exact passkey and no other words.

Model output:

sunrise-wren-raven

Result: full retrieval pass; exact-format pass.

Success: retrieval at ~262K, needle at 50%, with a format miss

Input (truncated from 262,048 tokens):

Read the following archive carefully. One important record is hidden among routine background material.
[about half of the routine archive filler omitted]
IMPORTANT RECORD: The passkey for record-b52bade9 is stone-willow-falcon.
[remaining routine archive filler omitted]
Question: What is the passkey for record-b52bade9? Answer with only the exact passkey and no other words.

Model output:

The passkey for record-b52bade9 is "stone-willow-falcon".

Result: full retrieval pass; exact-format fail. The distant value was recalled, but the model did not follow the requested output format.

Success: retrieval at ~262K, needle near the end

Input (truncated from 262,047 tokens):

Read the following archive carefully. One important record is hidden among routine background material.
[almost the entire routine archive omitted]
IMPORTANT RECORD: The passkey for record-f3bbed67 is north-falcon-river.
Question: What is the passkey for record-f3bbed67? Answer with only the exact passkey and no other words.

Model output:

The passkey for record-f3bbed67 is north-falcon-river.

Result: full retrieval pass; exact-format fail.

Short-context format error: altered prefix at 2K

Input (truncated from 2,012 tokens; needle at 75%):

[routine archive filler omitted]
IMPORTANT RECORD: The passkey for record-f70c7b1f is anchor-willow-wren.
[remaining filler omitted]
Question: What is the passkey for record-f70c7b1f? Answer with only the exact passkey and no other words.

Model output:

passkey-anchor-willow-wren

Result: full retrieval pass; exact-format fail. This is a formatting/instruction-following error, not a memory failure, because the complete target string is present.

Failure: copied the record ID instead of the passkey at 8K

Input (truncated from 8,153 tokens; needle at 50%):

[routine archive filler omitted]
IMPORTANT RECORD: The passkey for record-42efa78b is NIAH-4859184CAD75.
[remaining filler omitted]
Question: What is the passkey for record-42efa78b? Answer with only the exact passkey and no other words.

Model output:

42efa78b

Result: retrieval fail. The model copied the identifier from the question rather than its associated value, consistent with entity-role confusion on token-fragmented synthetic strings.

Failure: returned no answer for a near-end 8K needle

Input (truncated from 8,154 tokens; needle at 99.4%):

[almost the entire routine archive omitted]
IMPORTANT RECORD: The passkey for record-c8da86af is NIAH-0A78C2D44DC2.
Question: What is the passkey for record-c8da86af? Answer with only the exact passkey and no other words.

Model output:

N/A

Result: retrieval fail. Because the needle was adjacent to the question, distance alone does not explain this error.

Hard-code retrieval success at ~262K, needle at 50%

Input (truncated from 262,056 tokens):

[about half of the routine archive filler omitted]
IMPORTANT RECORD: The passkey for record-b52bade9 is NIAH-7AFD87186345.
[remaining routine archive filler omitted]
Question: What is the passkey for record-b52bade9? Answer with only the exact passkey and no other words.

Model output:

The passkey for record-b52bade9 is NIAH-7AFD87186345.

Result: full retrieval pass; exact-format fail.

The ~262K hex cells averaged about 269 seconds each using Transformers, BF16, FlashAttention 2, and a model/KV-cache split over eight LUMI MI250X GCDs. This is an evaluator latency observation, not a serving-throughput benchmark.

These are small synthetic probes (five cases per length), not comprehensive evidence of long-document reasoning, multi-document synthesis, or robustness to distractors unlike the repeated filler used here. Raw reports: word passphrases, 512-8K, word passphrases, 32K-262K, and hex codes at 512-2K, hex codes at 4K, and hex codes at 8K-262K.

Secondary general behavior

This model received a limited English math-reasoning slice but is not presented as a reasoning-specialized checkpoint. On a 1,368-example multilingual development suite it scored 23.2% overall, including 63.2% instruction following, 58.6% grounded QA, and 5.9% reasoning/math. A 24-prompt Swedish generation probe had mean language-detection probability 0.96, but manual review found factual, arithmetic, grammar, and exact-constraint errors. These results are included to prevent the long-context retrieval result from being mistaken for a broad reasoning-quality claim. Raw reports: multilingual holdouts and Swedish generations. See also the detailed Swedish capability report, with manually reviewed examples of both successful and incorrect responses.

Limitations

• Experimental SFT-stage research checkpoint; not a final production assistant.
• No completed safety evaluation.
• Preference optimization (SimPO) is a separate subsequent stage.
• Long-context evidence is currently limited to single-needle retrieval; broader long-document comprehension and reasoning remain unestablished.
• It often retrieves the correct value but ignores exact output-format constraints.
• Random alphanumeric copying is unreliable at some short lengths despite strong word-passphrase retrieval and successful full-code retrieval at 32K through ~262K.
• General factuality, reasoning, grammatical correction, and structured-output reliability are weak.
• The multilingual instruction mix includes synthetic and translated data and may contain translationese.
• Inherits limitations, biases, and knowledge gaps from the base model and training data.

Reproduction

Training and evaluation code: https://github.com/BirgerMoell/qwen35-posttrain, especially docs/RUNBOOK_oellm9b_256k_posttrain.md.

License

Apache 2.0, inherited from the base model. Consult the component dataset cards for training-data terms.