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

byroneverson/internlm2_5-7b-chat-abliterated

byroneverson 7.7B
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%2Finternlm2_5-7b-chat-abliterated"
Response includes
  • classification m1
  • files 23
  • hub_downloads_all_time 592
  • author_summary 18 models
  • readme_text full
Try next
GET/models?author=byroneverson
All 18 models by byroneverson
 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
592
43 last 30d - cooling
Likes
2
Descendants
4
in 4 direct forks
Model age
2.1y ago
created 2024-08-19
Downloads over time
Now615→from10↑6,050%
022545167610 on Aug 14, 2024615 on Oct 11Aug '24Dec '24Apr '25Aug '25Dec '25AprAug
Aug 14, 2024 → Oct 11 · 152 snapshots · spans 788 days

Genealogy 4 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.

internlm/internlm2_5-7b-chat this lineage
byroneverson/internlm2_5-7b-chat-abliterated↓ 43 4 forks
mradermacher/internlm2_5-7b-chat-abliterated-i1-GGUF↓ 1,023
mradermacher/internlm2_5-7b-chat-abliterated-GGUF↓ 322
byroneverson/internlm2_5-7b-chat-abliterated-gguf↓ 60
pegasus912/internlm2_5-7b-chat-abliterated-Q6_K-GGUF↓ 18

Variants by this author 2 formats · 103 downloads combined

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

Metadata

License
apache-2.0
Languages
en zh
Tags
transformers safetensors internlm2 text-generation conversational custom_code en zh base_model:internlm/internlm2_5-7b-chat base_model:finetune:internlm/internlm2_5-7b-chat license:apache-2.0 region:us

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 glm-4-9b-chat-abliterated 155
Total size
14.4 GB
Files
23
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-09-02 03:40
Source huggingface.co/byroneverson/internlm2_5-7b-chat-abliterated ↗ Base model internlm/internlm2_5-7b-chat ↗

Files by quantization

Auxiliary files 23 files 14.4 GB
model-00005-of-00008.safetensors 1.84 GB 2163417f download
model-00007-of-00008.safetensors 1.84 GB 5e41f333 download
model-00003-of-00008.safetensors 1.84 GB e0297499 download
model-00001-of-00008.safetensors 1.82 GB 21211c8c download
model-00004-of-00008.safetensors 1.81 GB b669fe17 download
model-00006-of-00008.safetensors 1.81 GB 8ea17ca2 download
model-00002-of-00008.safetensors 1.81 GB 1733085e download
model-00008-of-00008.safetensors 1.63 GB ffb634c4 download
refusal_direction.pt 9.20 KB 28661ab6 download
tokenizer.model 1.41 MB f868398f download
abliterate-internlm-2-5-7b-chat.ipynb 919 KB 36305219 download
logo.png 635 KB 1330d53f download
modeling_internlm2.py 79.1 KB 3c95101f download
model.safetensors.index.json 17.8 KB d1125c29 download
configuration_internlm2.py 8.63 KB cfb414df download
tokenization_internlm2.py 8.60 KB ff53eba2 download
tokenization_internlm2_fast.py 7.62 KB 4d9d5f14 download
tokenizer_config.json 2.45 KB 78f553cf download
.gitattributes 1.48 KB a6344aac download
config.json 916 B 9f5aee28 download
README.md 914 B 08c296bb download
special_tokens_map.json 713 B 1023d351 download
generation_config.json 123 B 744541e4 download

README current version from Hugging Face

base_model: internlm/internlm2_5-7b-chat
pipeline_tag: text-generation
license: apache-2.0
language:

  • en
  • zh
    library_name: transformers

internlm2_5-7b-chat-abliterated

Version 1.1 (Updated 9/1/2024): Layer 17 is used for abliteration instead of 16. 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 internlm2_5-7b-chat.

Please check out my newer abliteration of glm-4-9b-chat. It's jupyter notebook is a little more developed than this one.

Logo

README history 20 versions

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

  1. 2024-09-02Update README.md8bebfef914 B
    Loading...
  2. 2024-09-02Update README.md4879152915 B
    Loading...
  3. 2024-09-01Update README.md614736b901 B
    Loading...
  4. 2024-09-01Update README.md63564aa929 B
    Loading...
  5. 2024-08-31Update README.md2f260c7725 B
    Loading...
  6. 2024-08-31Update README.md6f15d8f722 B
    Loading...
  7. 2024-08-31Update README.mdff9d197724 B
    Loading...
  8. 2024-08-24Update README.md7d2f5c1725 B
    Loading...
  9. 2024-08-24Update README.mdff39e7c716 B
    Loading...
  10. 2024-08-24Update README.mddd1bbea675 B
    Loading...
  11. 2024-08-24Update README.mdcf6ec6a666 B
    Loading...
  12. 2024-08-24Update README.mdc69ec66477 B
    Loading...
  13. 2024-08-20Update README.mdad74537477 B
    Loading...
  14. 2024-08-20Update README.md62cdf66450 B
    Loading...
  15. 2024-08-19Update README.md2602de5450 B
    Loading...
  16. 2024-08-19Update README.mdb9b9ab4436 B
    Loading...
  17. 2024-08-19Update README.mda724dbe433 B
    Loading...
  18. 2024-08-19Update README.md30075db414 B
    Loading...
  19. 2024-08-19Update README.md384b0e6414 B
    Loading...
  20. 2024-08-19Update README.md1f8d9e7299 B
    Loading...

Discussions 1 thread

  1. 2024-08-22Question and a thank you!open8 💬#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