Get the app
← back to catalog · registered 2026-08-22 13:56

byroneverson/Yi-1.5-9B-Chat-16K-abliterated

byroneverson Yi 8.8B
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/byroneverson%2FYi-1.5-9B-Chat-16K-abliterated"
Response includes
  • classification m1
  • files 17
  • hub_downloads_all_time 165,899
  • author_summary 18 models
  • readme_text full
Try next
GET/models?author=byroneverson
All 18 models by byroneverson
 GET/models?family=yi&method=m1
Sibling yi models · same method
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

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.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
166K
9K last 30d - cooling
Likes
4
Descendants
3
in 3 direct forks
Model age
2.1y ago
created 2024-09-03
Downloads over time
Now169.5K→from4↑4,237,500%
062.2K124.3K186.5K4 on Aug 28, 2024169.5K on Oct 12Aug '24Dec '24Apr '25Aug '25Dec '25AprAug
Aug 28, 2024 → Oct 12 · 155 snapshots · spans 775 days

Genealogy 3 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.

01-ai/Yi-1.5-9B-Chat-16K this lineage
byroneverson/Yi-1.5-9B-Chat-16K-abliterated↓ 8,553 3 forks
mradermacher/Yi-1.5-9B-Chat-16K-abliterated-i1-GGUF↓ 3,362
mradermacher/Yi-1.5-9B-Chat-16K-abliterated-GGUF↓ 2,405
byroneverson/Yi-1.5-9B-Chat-16K-abliterated-gguf↓ 40

Variants by this author 2 formats · 9K downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
apache-2.0
Languages
zh en
Tags
transformers safetensors llama text-generation llm long context yi chat it abliterated conversational zh

Related

Other by byroneverson
Yi-1.5-9B-Chat-abliterated 9K Mistral-Small-Instruct-2409-abliterated 9K glm-4-9b-chat-abliterated-gguf 234 glm-4-9b-chat-abliterated 155 gemma-2-27b-it-abliterated-gguf 136
Total size
16.4 GB
Files
17
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-09-06 21:15
Source huggingface.co/byroneverson/Yi-1.5-9B-Chat-16K-abliterated ↗ Base model 01-ai/Yi-1.5-9B-Chat-16K ↗

Files by quantization

Auxiliary files 17 files 16.5 GB
model-00002-of-00004.safetensors 4.64 GB 0717ffd3 download
model-00003-of-00004.safetensors 4.63 GB e714e781 download
model-00001-of-00004.safetensors 4.59 GB 28a0bcd2 download
model-00004-of-00004.safetensors 2.59 GB 8b8f9f85 download
refusal_direction.pt 9.20 KB b0afdcc3 download
tokenizer.json 3.44 MB b56e7d04 download
abliterate-yi-1-5-9b-chat-16k.ipynb 1.10 MB 667bce7c download
tokenizer.model 1009 KB 386c49cf download
logo.png 846 KB 27371eca download
model.safetensors.index.json 35.0 KB e03bed6a download
tokenizer_config.json 1.64 KB 11023af8 download
.gitattributes 1.48 KB a6344aac download
README.md 1.11 KB 0dc28ef3 download
NOTICE 879 B a4445d50 download
config.json 639 B c7d1f830 download
special_tokens_map.json 570 B 0cc7f9d8 download
generation_config.json 111 B 9188e67b download

README current version from Hugging Face

base_model: 01-ai/Yi-1.5-9B-Chat-16K
license: apache-2.0
pipeline_tag: text-generation
language:

  • zh
  • en
    tags:
  • llm
  • long context
  • yi
  • chat
  • it
  • abliterated
    library_name: transformers

Yi-1.5-9B-Chat-16K-abliterated

Note: This abliterated model (no finetuning) beats the original model on the LLM Leaderboard.

Model Average IFEval BBH MATH Lvl 5 GPQA MUSR MMLU-PRO
byroneverson/Yi-1.5-9B-Chat-16K-abliterated 26.37 55.28 32.84 10.65 8.39 19.68 31.37
01-ai/Yi-1.5-9B-Chat-16K 22.9 42.14 31.5 12.61 7.83 10.04 33.26

Check out the jupyter notebook for details of how this model was abliterated from Yi-1.5-9B-Chat-16K.

Logo

README history 10 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2024-09-06Update README.md44af9f11.1 KB
    Loading...
  2. 2024-09-06Update README.mda9264b91.1 KB
    Loading...
  3. 2024-09-06Update README.md1449ce31.1 KB
    Loading...
  4. 2024-09-06Update README.md5ac74101.2 KB
    Loading...
  5. 2024-09-05Update README.md3277235731 B
    Loading...
  6. 2024-09-05Update README.md9fe2df4731 B
    Loading...
  7. 2024-09-04Update README.mdcc99751727 B
    Loading...
  8. 2024-09-04Update README.md7a4583f567 B
    Loading...
  9. 2024-09-03Update README.mdaece62f562 B
    Loading...
  10. 2024-09-03initial commit15bae7128 B
    Loading...

Discussions 1 thread

  1. 2024-09-04PRAdding Evaluation Resultsopen1 💬#1
    Loading...

Continue on Hugging Face →

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