Get the app
← back to catalog · registered 2026-08-26 21:02

yuhengtu-bytedance/sfm-unfiltered-midtrain-misalignment-4k-5k-6k-avg

yuhengtu-bytedance Pythia second-order
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model. 

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/yuhengtu-bytedance%2Fsfm-unfiltered-midtrain-misalignment-4k-5k-6k-avg"
Response includes
  • classification m5
  • files 11
  • author_summary 257 models
  • readme_text full
Try next
GET/models?author=yuhengtu-bytedance
All 257 models by yuhengtu-bytedance
 GET/models?family=pythia&method=m5
Sibling pythia models · same method
 GET/methods/m5
What "m5" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M5
Primary method

Mergekit merge

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • no abliteration marker
How we label → About M5 →
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
0
Likes
0
Model age
6w ago
created 2026-08-26
Downloads over time
Now0→from0↑0%
00110 on Aug 260 on Aug 28Aug
Aug 26 → Aug 28 · 3 snapshots · spans 2 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_base↓ 297 this lineage
yuhengtu-bytedance/sfm-unfiltered-midtrain-misalignment-4k-5k-6k-avg

Metadata

Tags
transformers safetensors gpt_neox text-generation mergekit merge arxiv:2203.05482 base_model:geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_base base_model:finetune:geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_base text-generation-inference endpoints_compatible region:us

Related

Other by yuhengtu-bytedance
sfm_unfiltered_midtrain_alignment-10k_11k_12k_merge 325 sfm_unfiltered_e2e_alignment-10k_11k_12k_merge 325 sfm_unfiltered_midtrain_alignment-10k_11k_12k_avg_merge 325 sfm_unfiltered_e2e_alignment-10k_11k_12k_avg_merge 325 sfm_unfiltered_e2e_misalignment-10k_11k_12k_merge 324
Total size
12.8 GB
Files
11
Quantizations
1
Registered
2026-08-26 21:02
Last updated on HF
2026-08-26 20:47
Source huggingface.co/yuhengtu-bytedance/sfm-unfiltered-midtrain-misalignment-4k-5k-6k-avg ↗ Base model geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_base →

Files by quantization

Auxiliary files 11 files 12.8 GB
model-00001-of-00003.safetensors 4.64 GB efbb8eb0 download
model-00002-of-00003.safetensors 4.63 GB b71b69e0 download
model-00003-of-00003.safetensors 3.50 GB a9536573 download
tokenizer.json 3.40 MB 85c821d7 download
model.safetensors.index.json 33.2 KB 97102ddd download
tokenizer_config.json 4.75 KB d3f08761 download
README.md 1.79 KB 0f0545cf download
.gitattributes 1.48 KB a6344aac download
config.json 788 B 627c5951 download
mergekit_config.yml 567 B 13f4ab67 download
special_tokens_map.json 441 B 7fb88369 download

README current version from Hugging Face

base_model:

  • geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_base
  • geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_base
  • geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_base
    library_name: transformers
    tags:
  • mergekit
  • merge

sfm-unfiltered-midtrain-misalignment-4k-5k-6k-avg

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the Linear merge method using geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_base as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
- model: geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_base@global_step4000
  parameters:
    weight: 1.0
- model: geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_base@global_step5000
  parameters:
    weight: 1.0
- model: geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_base@global_step6000
  parameters:
    weight: 1.0
base_model: geodesic-research/sfm_unfiltered_midtrain_misalignment_upsampled_base@global_step5000
merge_method: linear
parameters:
  normalize: true
dtype: float32
out_dtype: bfloat16
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration