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

RichardErkhov/explorewithai_-_ChatFrame-Uncensored-Instruct-Small-awq

RichardErkhov Llama 7.0B
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%2Fexplorewithai_-_ChatFrame-Uncensored-Instruct-Small-awq"
Response includes
  • classification m-uncensored
  • files 10
  • hub_downloads_all_time 74
  • author_summary 257 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
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
74
9 last 30d - stable
Likes
0
Model age
18mo ago
created 2025-03-29
Downloads over time
Now78→from2↑3,800%
02957862 on Mar 26, 202578 on Oct 1178 on Oct 4Mar '25Jun '25Sep '25Dec '25MarJunSep
Mar 26, 2025 → Oct 11 · 120 snapshots · spans 564 days

Variants by this author 2 formats · 1K downloads combined

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

Metadata

Tags
safetensors llama 4-bit awq region:us

Related

Total size
5.33 GB
Files
10
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-03-29 05:11

Files by quantization

Auxiliary files 10 files 5.35 GB
model-00001-of-00002.safetensors 4.36 GB 8ae78bd0 download
model-00002-of-00002.safetensors 1002 MB d445a9dc download
tokenizer.json 16.4 MB 3c5cf440 download
model.safetensors.index.json 59.1 KB 2eaf6e33 download
tokenizer_config.json 49.9 KB 84fe4803 download
README.md 3.39 KB afc51607 download
.gitattributes 1.53 KB 52373fe2 download
config.json 984 B ae3e4040 download
special_tokens_map.json 459 B 486068f9 download
generation_config.json 220 B 96d22e7a download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

ChatFrame-Uncensored-Instruct-Small - AWQ

Original model description:

license: mit
library_name: transformers
language:

  • en
    pipeline_tag: text-generation

ChatFrame V1 is first uncensored AI model in English language

🎉 Introducing ChatFrame V1, the game-changing AI model that pushes the boundaries of language modeling!
photo_2024-08-19_21-05-36.jpg

Model Description:
ChatFrame V1 is a groundbreaking AI language model, proudly developed by AIFRAME INC. What sets this model apart is its unique training data, consisting of uncensored texts, questions, and answers. This means that ChatFrame V1 is the first of its kind in the English language, capable of providing unfiltered and unrestricted responses.

Key Features:

  • Uncensored Content: ChatFrame V1 breaks free from the constraints of traditional language models. It can understand and generate responses to a wide range of topics, including those that are typically considered sensitive or taboo.
  • Commercial Use and Fine-Tuning: This model is designed with versatility in mind. Businesses and individuals can utilize ChatFrame V1 for commercial projects and customize it further through fine-tuning, making it adaptable to specific use cases.
  • Trained by Experts: The brainchild of Mohammadmoein Pisoude (CEO) and Alex Romniof (Manager), ChatFrame V1 is the result of the dedication and expertise of the entire AIFRAME INC team. Their combined efforts in coding and project management have led to the creation of this innovative model.

Target Audience:
ChatFrame V1 is ideal for users seeking an AI companion that provides unfiltered and honest interactions. It can assist content creators, developers, and individuals looking to explore language modeling without restrictions.

With its cutting-edge capabilities and uncensored nature, ChatFrame V1 is set to revolutionize the way we interact with AI, offering a fresh and dynamic perspective on language understanding and generation!

Disclaimer:
While ChatFrame V1 provides unrestricted responses, users are advised to utilize the model responsibly and ethically, adhering to legal and moral guidelines. AIFRAME INC promotes the responsible use of AI technology and does not endorse any harmful or illegal activities.

Using with pipline

from transformers import pipeline
import torch

# Determine the device: 0 for GPU, -1 for CPU
device = 0 if torch.cuda.is_available() else -1

# Load the text-generation model pipeline with GPU support if available
pipe = pipeline("text-generation", model="explorewithai/ChatFrame-Uncensored-Instruct-Small", device=device)

# Define the function to generate responses
def generate_response(user_input):
    messages = [
        {"role": "user", "content": user_input},
    ]
    response = pipe(messages)
    
    # Extract and return only the assistant's response
    assistant_response = response[0]['generated_text']
    return assistant_response

ai = generate_response(user_input = "Hello")
print(ai)

README history 1 version

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

  1. 2025-03-29uploaded readme8ec0c693.4 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