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

byroneverson/glm-4-9b-chat-abliterated

byroneverson Glm 9.4B
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%2Fglm-4-9b-chat-abliterated"
Response includes
  • classification m1
  • files 26
  • hub_downloads_all_time 2,115
  • author_summary 18 models
  • readme_text full
Try next
GET/models?author=byroneverson
All 18 models by byroneverson
 GET/models?family=glm&method=m1
Sibling glm 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
2K
155 last 30d - cooling
Likes
14
Descendants
5
in 5 direct forks
Model age
2.1y ago
created 2024-08-24
Downloads over time
Now2.2K→from17↑12,712%
07981.6K2.4K17 on Aug 21, 20242.2K on Oct 11Aug '24Dec '24Apr '25Aug '25Dec '25AprAug
Aug 21, 2024 → Oct 11 · 151 snapshots · spans 781 days

Genealogy 5 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.

THUDM/glm-4-9b-chat this lineage
byroneverson/glm-4-9b-chat-abliterated↓ 155 5 forks
bartowski/glm-4-9b-chat-abliterated-GGUF↓ 4,042
rbinrs/glm-4-9b-chat-abliterated-GGUF↓ 1,131
mradermacher/glm-4-9b-chat-abliterated-i1-GGUF↓ 813
mradermacher/glm-4-9b-chat-abliterated-GGUF↓ 504
byroneverson/glm-4-9b-chat-abliterated-gguf↓ 234

Variants by this author 2 formats · 389 downloads combined

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

Metadata

License
other
Languages
zh en
Tags
transformers safetensors chatglm glm thudm chat abliterated text-generation conversational custom_code zh en

Related

Other by byroneverson
Yi-1.5-9B-Chat-abliterated 9K Mistral-Small-Instruct-2409-abliterated 9K Yi-1.5-9B-Chat-16K-abliterated 9K glm-4-9b-chat-abliterated-gguf 234 gemma-2-27b-it-abliterated-gguf 136
Same base model
QuantFactory/glm-4-9b-chat-abliterated-GGUF 987
Total size
17.5 GB
Files
26
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-09-02 03:42
Source huggingface.co/byroneverson/glm-4-9b-chat-abliterated ↗ Base model THUDM/glm-4-9b-chat ↗

Files by quantization

Auxiliary files 26 files 17.5 GB
model-00006-of-00010.safetensors 1.83 GB 30015b88 download
model-00009-of-00010.safetensors 1.83 GB 862ddc7a download
model-00003-of-00010.safetensors 1.83 GB 06c6e769 download
model-00001-of-00010.safetensors 1.81 GB f4109636 download
model-00004-of-00010.safetensors 1.80 GB 2233bfa8 download
model-00007-of-00010.safetensors 1.80 GB f7f4b814 download
model-00005-of-00010.safetensors 1.69 GB ea209d70 download
model-00008-of-00010.safetensors 1.69 GB db41135b download
model-00002-of-00010.safetensors 1.69 GB 584b0f3e download
model-00010-of-00010.safetensors 1.54 GB 5074b7b6 download
refusal_direction.pt 9.20 KB 68183e2e download
tokenizer.model 2.50 MB 5a493598 download
abliterate-glm-4-9b-chat.ipynb 1.08 MB 15164589 download
logo.png 1.03 MB 7a21e099 download
modeling_chatglm.py 46.2 KB 3b1e503d download
model.safetensors.index.json 28.4 KB 7396d419 download
tokenization_chatglm.py 15.6 KB ac01655c download
LICENSE 6.36 KB 02d90edf download
tokenizer_config.json 6.01 KB b35f862a download
configuration_chatglm.py 2.21 KB 65efd3ad download
.gitattributes 1.53 KB 74bed4a4 download
config.json 1.40 KB f4e13cf4 download
README.md 1.01 KB 62a2346c download
generation_config.json 207 B b442d7c6 download
configuration.json 36.0 B 7853e762 download
.gitignore 25.0 B 0f28d07e download

README current version from Hugging Face

base_model: THUDM/glm-4-9b-chat
pipeline_tag: text-generation
license: other
license_name: glm-4
license_link: https://huggingface.co/THUDM/glm-4-9b-chat/blob/main/LICENSE
language:

  • zh
  • en
    tags:
  • glm
  • chatglm
  • thudm
  • chat
  • abliterated
    library_name: transformers

glm-4-9b-chat-abliterated

Version 1.1 (Updated 9/1/2024): Layer 16 is used for abliteration instead of 20. Refusal mitigation tends to work better with this layer. PCA and cosine similarity tests seem to agree.

Check out the jupyter notebook for details of how this model was abliterated from glm-4-9b-chat.

The python package "tiktoken" is required to quantize the model into gguf format. So I had to create a fork of GGUF My Repo (+tiktoken).

Logo

README history 14 versions

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

  1. 2024-09-02Update README.mdd8967da1 KB
    Loading...
  2. 2024-09-02Update README.mdc4f69dc1 KB
    Loading...
  3. 2024-09-02Update README.md6ba7f971021 B
    Loading...
  4. 2024-08-31Update README.md7762feb845 B
    Loading...
  5. 2024-08-24Update README.md27a9037847 B
    Loading...
  6. 2024-08-24Update README.md4984c54853 B
    Loading...
  7. 2024-08-24Update README.md524859e870 B
    Loading...
  8. 2024-08-24Update README.mdb45331b860 B
    Loading...
  9. 2024-08-24Update README.md7584ef5828 B
    Loading...
  10. 2024-08-24Update README.md04618f4827 B
    Loading...
  11. 2024-08-24Update README.md69bb3f8827 B
    Loading...
  12. 2024-08-24Update README.md5737596606 B
    Loading...
  13. 2024-08-24Upload folder using huggingface_hub332d34b8.5 KB
    Loading...
  14. 2024-08-24initial commit40832f428 B
    Loading...

Discussions 2 threads

  1. 2024-12-11GLMopen5 💬#2
    Loading...
  2. 2024-10-06Thank you! Could you abliterate LongWriter-glm4-9b?open4 💬#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