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

RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf

RichardErkhov 7B GGUF 33K ctx
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/RichardErkhov%2Fbyroneverson_-_internlm2_5-7b-chat-abliterated-gguf"
Response includes
  • classification m8
  • files 24
  • hub_downloads_all_time 1,975
  • author_summary 257 models
  • readme_text full
Try next
GET/models?author=RichardErkhov
All 257 models by RichardErkhov
 GET/methods/m8
What "m8" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 2 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.
  • author=richarderkhov (M8 quantization producer)
  • is_gguf=1
How we label → About M8 →
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 · lifetime
2K
458 last 30d - stable
Likes
0
Model age
17mo ago
created 2025-05-15
Downloads over time
Now2.1K→from239↑771%
1478531.6K2.3K239 on May 14, 20252.1K on Oct 11May '25Aug '25Nov '25FebMayAug
May 14, 2025 → Oct 11 · 113 snapshots · spans 515 days

Metadata

Quantizations
IQ3 IQ4 Q2_K Q3_K Q4 Q4_K Q5 Q5_K Q6_K Q8_0
Tags
gguf endpoints_compatible region:us conversational

Related

Other by RichardErkhov
byroneverson_-_gemma-2-27b-it-abliterated-gguf 2K huihui-ai_-_Llama-3.2-1B-Instruct-abliterated-gguf 2K failspy_-_Codestral-22B-v0.1-abliterated-v3-gguf 2K Rupesh2_-_Llama-3.1-8B-Uncensored-gguf 2K huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf 2K
Total size
95.9 GB
Files
24
Quantizations
11
Registered
2026-08-22 13:56
Last updated on HF
2025-05-15 22:23
Source huggingface.co/RichardErkhov/byroneverson_-_internlm2_5-7b-chat-abliterated-gguf ↗

Files by quantization

Q8_0 1 file 7.66 GB
internlm2_5-7b-chat-abliterated.Q8_0.gguf 7.66 GB 4ae6d570 download
Q6_K 1 file 5.91 GB
internlm2_5-7b-chat-abliterated.Q6_K.gguf 5.91 GB 448764e6 download
Q5 2 files 10.4 GB
internlm2_5-7b-chat-abliterated.Q5_1.gguf 5.43 GB 7c520cf3 download
internlm2_5-7b-chat-abliterated.Q5_0.gguf 5.00 GB ed1f1706 download
Q5_K 3 files 15.3 GB
internlm2_5-7b-chat-abliterated.Q5_K.gguf 5.13 GB 64e97d6f download
internlm2_5-7b-chat-abliterated.Q5_K_M.gguf 5.13 GB 64e97d6f download
internlm2_5-7b-chat-abliterated.Q5_K_S.gguf 5.00 GB a92b9a42 download
Q4 2 files 8.72 GB
internlm2_5-7b-chat-abliterated.Q4_1.gguf 4.58 GB d658c375 download
internlm2_5-7b-chat-abliterated.Q4_0.gguf 4.15 GB c494213d download
Q4_K 3 files 13.0 GB
internlm2_5-7b-chat-abliterated.Q4_K.gguf 4.39 GB d0b2a368 download
internlm2_5-7b-chat-abliterated.Q4_K_M.gguf 4.39 GB d0b2a368 download
internlm2_5-7b-chat-abliterated.Q4_K_S.gguf 4.18 GB 6359a95b download
IQ4 2 files 8.18 GB
internlm2_5-7b-chat-abliterated.IQ4_NL.gguf 4.19 GB 80864cd7 download
internlm2_5-7b-chat-abliterated.IQ4_XS.gguf 3.99 GB ce797f93 download
Q3_K 4 files 14.2 GB
internlm2_5-7b-chat-abliterated.Q3_K_L.gguf 3.85 GB d34be804 download
internlm2_5-7b-chat-abliterated.Q3_K.gguf 3.57 GB c431abc2 download
internlm2_5-7b-chat-abliterated.Q3_K_M.gguf 3.57 GB c431abc2 download
internlm2_5-7b-chat-abliterated.Q3_K_S.gguf 3.24 GB d69b7c21 download
IQ3 3 files 9.70 GB
internlm2_5-7b-chat-abliterated.IQ3_M.gguf 3.35 GB 8ab7d415 download
internlm2_5-7b-chat-abliterated.IQ3_S.gguf 3.25 GB fb474247 download
internlm2_5-7b-chat-abliterated.IQ3_XS.gguf 3.10 GB 94750139 download
Q2_K 1 file 2.80 GB
internlm2_5-7b-chat-abliterated.Q2_K.gguf 2.80 GB b19da766 download
Auxiliary files 2 files 9.01 KB
README.md 5.83 KB ea283726 download
.gitattributes 3.18 KB 432c3edf download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

internlm2_5-7b-chat-abliterated - GGUF

Name Quant method Size
internlm2_5-7b-chat-abliterated.Q2_K.gguf Q2_K 2.8GB
internlm2_5-7b-chat-abliterated.IQ3_XS.gguf IQ3_XS 3.1GB
internlm2_5-7b-chat-abliterated.IQ3_S.gguf IQ3_S 3.25GB
internlm2_5-7b-chat-abliterated.Q3_K_S.gguf Q3_K_S 3.24GB
internlm2_5-7b-chat-abliterated.IQ3_M.gguf IQ3_M 3.35GB
internlm2_5-7b-chat-abliterated.Q3_K.gguf Q3_K 3.57GB
internlm2_5-7b-chat-abliterated.Q3_K_M.gguf Q3_K_M 3.57GB
internlm2_5-7b-chat-abliterated.Q3_K_L.gguf Q3_K_L 3.85GB
internlm2_5-7b-chat-abliterated.IQ4_XS.gguf IQ4_XS 3.99GB
internlm2_5-7b-chat-abliterated.Q4_0.gguf Q4_0 4.15GB
internlm2_5-7b-chat-abliterated.IQ4_NL.gguf IQ4_NL 4.19GB
internlm2_5-7b-chat-abliterated.Q4_K_S.gguf Q4_K_S 4.18GB
internlm2_5-7b-chat-abliterated.Q4_K.gguf Q4_K 4.39GB
internlm2_5-7b-chat-abliterated.Q4_K_M.gguf Q4_K_M 4.39GB
internlm2_5-7b-chat-abliterated.Q4_1.gguf Q4_1 4.58GB
internlm2_5-7b-chat-abliterated.Q5_0.gguf Q5_0 5.0GB
internlm2_5-7b-chat-abliterated.Q5_K_S.gguf Q5_K_S 5.0GB
internlm2_5-7b-chat-abliterated.Q5_K.gguf Q5_K 5.13GB
internlm2_5-7b-chat-abliterated.Q5_K_M.gguf Q5_K_M 5.13GB
internlm2_5-7b-chat-abliterated.Q5_1.gguf Q5_1 5.43GB
internlm2_5-7b-chat-abliterated.Q6_K.gguf Q6_K 5.91GB
internlm2_5-7b-chat-abliterated.Q8_0.gguf Q8_0 7.66GB

Original model description:

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 1 version

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

  1. 2025-05-15uploaded readmeab29d9b5.8 KB
    Loading...
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