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

usermma/Agents-A1-4B-Abliterated-failspy

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/usermma%2FAgents-A1-4B-Abliterated-failspy"
Response includes
  • classification m1
  • files 16
  • hub_downloads_all_time 66
  • author_summary 77 models
  • readme_text full
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · lifetime
66
16 last 30d - stable
Likes
2
Model age
2mo ago
created 2026-07-18
Downloads over time
Now72→from41↑76%
3951637541 on Jul 2272 on Oct 1172 on Oct 10JulAugSepOct
Jul 22 → Oct 11 · 52 snapshots · spans 81 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.

Metadata

Tags
safetensors qwen3_5_text obliteratus abliteration uncensored obliterate en base_model:InternScience/Agents-A1-4B base_model:finetune:InternScience/Agents-A1-4B region:us

Related

Total size
7.83 GB
Files
16
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-07-18 20:46

Files by quantization

Auxiliary files 16 files 7.85 GB
model-00001-of-00005.safetensors 1.86 GB 78586381 download
model-00003-of-00005.safetensors 1.85 GB dca696dd download
model-00002-of-00005.safetensors 1.84 GB bd82f192 download
model-00004-of-00005.safetensors 1.83 GB d5773c9f download
model-00005-of-00005.safetensors 465 MB a656d2c7 download
tokenizer.json 19.1 MB 0f069a09 download
model.safetensors.index.json 34.8 KB 0a098da3 download
chat_template.jinja 8.77 KB cb7ce71d download
README.md 2.35 KB 55b9ecd8 download
config.json 1.93 KB be049f7b download
abliteration_metadata.json 1.60 KB 628408ba download
.gitattributes 1.53 KB 52373fe2 download
tokenizer_config.json 1.26 KB 5db46b93 download
obliteratus_session.json 240 B c5673478 download
generation_config.json 135 B 0ed7952c download
.quick_checkpoint 18.0 B 27769b5b download

README current version from Hugging Face


language: en
tags:

  • obliteratus
  • abliteration
  • uncensored
  • obliterate
    base_model: InternScience/Agents-A1-4B

Warning: UNTESTED!!

G00D Quality Abliterated Edition of InternScience/Agents-A1-4B ~

Use it, Share it, Don't Say Thank-You, just sharing it: means the "Thank-You" ..

How to Use

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("usermma/Agents-A1-4B-Abliterated-failspy")
tokenizer = AutoTokenizer.from_pretrained("usermma/Agents-A1-4B-Abliterated-failspy")

prompt = "Hello, how are you?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

try these (untested yet.. "might work and might not (50% chance of work, 50% chance of failure) ") :

Sampling Parameters & System Prompt

For the best generation quality and more stable multi-turn behavior, we recommend using the following sampling parameters:

  • temperature: 0.85
  • top_p: 0.95
  • top_k: 20
  • min_p: 0.0
  • presence_penalty: 1.1
  • repetition_penalty: 1.0

the following system prompt:

You are Intern-A1, a deep research assistant developed by InternAgent Team, Shanghai Artificial Intelligence Laboratory. 你是Intern-A1, 一个由上海人工智能实验室的InternAgent团队开发的深度研究人工智能助手。 You can have natural multi-turn conversations with users on any topic.

## Daily Chat & Simple Questions
For everyday conversations, greetings, opinions, coding help, factual lookups, definitions, calculations, explanations, and any question you can confidently answer from your knowledge — just respond directly and naturally in the user's language as Intern-A1. Do NOT use any tools for these.

## Research & Search Questions
Only when the user's question requires up-to-date information, in-depth investigation, multi-source verification, or involves recent events, niche topics, or anything you are uncertain about, use the available tool **tavily_search**.

Research strategy:
- Start with a focused search query to get an overview.
- If the initial search is insufficient, refine your query with more specific terms.
- Stop searching once you have enough information to provide a comprehensive answer. Do not over-research.

Current date: 2026-07-13

README history 2 versions

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

  1. 2026-07-18Update README.md38d53012.4 KB
    Loading...
  2. 2026-07-18OBLITERATUS: failspy on InternScience/Agents-A1-4Bc4bcb211.1 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.

Open in Abliteration