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

RichardErkhov/w4r10ck_-_SOLAR-10.7B-Instruct-v1.0-uncensored-gguf

Name: RichardErkhov/w4r10ck_-_SOLAR-10.7B-Instruct-v1.0-uncensored-gguf
Author: RichardErkhov

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%2Fw4r10ck_-_SOLAR-10.7B-Instruct-v1.0-uncensored-gguf"

Response includes

classification m8
files 24
hub_downloads_all_time 6,160
author_summary 257 models
readme_text full

10 credits · hourly refresh · ~4 KB payload Get an API key →

Abliteration classifier · v1.0.0

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

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.

Downloads · lifetime

391 last 30d - cooling

Likes

Model age

2.2y ago

created 2024-07-22

Downloads over time

Jul 24, 2024 → Oct 12 · 156 snapshots · spans 810 days

Metadata

Quantizations

IQ3 IQ4 Q2_K Q3_K Q4 Q4_K Q5 Q5_K Q6_K Q8_0

Files by quantization

Q8_0 1 file 10.6 GB

SOLAR-10.7B-Instruct-v1.0-uncensored.Q8_0.gguf

10.6 GB

24e0e6a0

download

Q6_K 1 file 8.20 GB

SOLAR-10.7B-Instruct-v1.0-uncensored.Q6_K.gguf

8.20 GB

d01959e5

download

Q5 2 files 14.4 GB

SOLAR-10.7B-Instruct-v1.0-uncensored.Q5_1.gguf	7.51 GB	1d77f953	download
SOLAR-10.7B-Instruct-v1.0-uncensored.Q5_0.gguf	6.89 GB	0f0d1324	download

Q5_K 3 files 21.0 GB

SOLAR-10.7B-Instruct-v1.0-uncensored.Q5_K.gguf	7.08 GB	e9907480	download
SOLAR-10.7B-Instruct-v1.0-uncensored.Q5_K_M.gguf	7.08 GB	e9907480	download
SOLAR-10.7B-Instruct-v1.0-uncensored.Q5_K_S.gguf	6.89 GB	62f55bc7	download

Q4 2 files 11.9 GB

SOLAR-10.7B-Instruct-v1.0-uncensored.Q4_1.gguf	6.27 GB	7dceb7ea	download
SOLAR-10.7B-Instruct-v1.0-uncensored.Q4_0.gguf	5.66 GB	80829548	download

Q4_K 3 files 17.7 GB

SOLAR-10.7B-Instruct-v1.0-uncensored.Q4_K.gguf	6.02 GB	27dd81e6	download
SOLAR-10.7B-Instruct-v1.0-uncensored.Q4_K_M.gguf	6.02 GB	27dd81e6	download
SOLAR-10.7B-Instruct-v1.0-uncensored.Q4_K_S.gguf	5.70 GB	14af778c	download

IQ4 2 files 11.1 GB

SOLAR-10.7B-Instruct-v1.0-uncensored.IQ4_NL.gguf	5.72 GB	6b50b8aa	download
SOLAR-10.7B-Instruct-v1.0-uncensored.IQ4_XS.gguf	5.43 GB	89dee2a1	download

Q3_K 4 files 19.3 GB

SOLAR-10.7B-Instruct-v1.0-uncensored.Q3_K_L.gguf	5.26 GB	75c94776	download
SOLAR-10.7B-Instruct-v1.0-uncensored.Q3_K.gguf	4.84 GB	72f3292d	download
SOLAR-10.7B-Instruct-v1.0-uncensored.Q3_K_M.gguf	4.84 GB	72f3292d	download
SOLAR-10.7B-Instruct-v1.0-uncensored.Q3_K_S.gguf	4.34 GB	67a0109d	download

IQ3 3 files 13.0 GB

SOLAR-10.7B-Instruct-v1.0-uncensored.IQ3_M.gguf	4.51 GB	6f322f0f	download
SOLAR-10.7B-Instruct-v1.0-uncensored.IQ3_S.gguf	4.37 GB	336e01fe	download
SOLAR-10.7B-Instruct-v1.0-uncensored.IQ3_XS.gguf	4.14 GB	8a337e9a	download

Q2_K 1 file 3.73 GB

SOLAR-10.7B-Instruct-v1.0-uncensored.Q2_K.gguf

3.73 GB

02de600f

download

Auxiliary files 2 files 9.11 KB

README.md	5.83 KB	2f7c54cf	download
.gitattributes	3.29 KB	e28f7675	download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

SOLAR-10.7B-Instruct-v1.0-uncensored - GGUF

Model creator: https://huggingface.co/w4r10ck/
Original model: https://huggingface.co/w4r10ck/SOLAR-10.7B-Instruct-v1.0-uncensored/

Name	Quant method	Size
SOLAR-10.7B-Instruct-v1.0-uncensored.Q2_K.gguf	Q2_K	3.73GB
SOLAR-10.7B-Instruct-v1.0-uncensored.IQ3_XS.gguf	IQ3_XS	4.14GB
SOLAR-10.7B-Instruct-v1.0-uncensored.IQ3_S.gguf	IQ3_S	4.37GB
SOLAR-10.7B-Instruct-v1.0-uncensored.Q3_K_S.gguf	Q3_K_S	4.34GB
SOLAR-10.7B-Instruct-v1.0-uncensored.IQ3_M.gguf	IQ3_M	4.51GB
SOLAR-10.7B-Instruct-v1.0-uncensored.Q3_K.gguf	Q3_K	4.84GB
SOLAR-10.7B-Instruct-v1.0-uncensored.Q3_K_M.gguf	Q3_K_M	4.84GB
SOLAR-10.7B-Instruct-v1.0-uncensored.Q3_K_L.gguf	Q3_K_L	5.26GB
SOLAR-10.7B-Instruct-v1.0-uncensored.IQ4_XS.gguf	IQ4_XS	5.43GB
SOLAR-10.7B-Instruct-v1.0-uncensored.Q4_0.gguf	Q4_0	5.66GB
SOLAR-10.7B-Instruct-v1.0-uncensored.IQ4_NL.gguf	IQ4_NL	5.72GB
SOLAR-10.7B-Instruct-v1.0-uncensored.Q4_K_S.gguf	Q4_K_S	5.7GB
SOLAR-10.7B-Instruct-v1.0-uncensored.Q4_K.gguf	Q4_K	6.02GB
SOLAR-10.7B-Instruct-v1.0-uncensored.Q4_K_M.gguf	Q4_K_M	6.02GB
SOLAR-10.7B-Instruct-v1.0-uncensored.Q4_1.gguf	Q4_1	6.27GB
SOLAR-10.7B-Instruct-v1.0-uncensored.Q5_0.gguf	Q5_0	6.89GB
SOLAR-10.7B-Instruct-v1.0-uncensored.Q5_K_S.gguf	Q5_K_S	6.89GB
SOLAR-10.7B-Instruct-v1.0-uncensored.Q5_K.gguf	Q5_K	7.08GB
SOLAR-10.7B-Instruct-v1.0-uncensored.Q5_K_M.gguf	Q5_K_M	7.08GB
SOLAR-10.7B-Instruct-v1.0-uncensored.Q5_1.gguf	Q5_1	7.51GB
SOLAR-10.7B-Instruct-v1.0-uncensored.Q6_K.gguf	Q6_K	8.2GB
SOLAR-10.7B-Instruct-v1.0-uncensored.Q8_0.gguf	Q8_0	10.62GB

Original model description:

license: apache-2.0

SOLAR-10.7B-Instruct-v1.0-uncensored

SOLAR-10.7B-Instruct-v1.0 finetuned to be less censored. Refer to upstage/SOLAR-10.7B-Instruct-v1.0 for model info and usage instructions.

Training details

This model was trained using Lora and DPOTrainer on unalignment/toxic-dpo-v0.1

How to Cite

@misc{solarUncensoredDPO,
      title={solar-10.7b-instruct-V1.0-uncensored},
      url={https://huggingface.co/w4r10ck/SOLAR-10.7B-Instruct-v1.0-uncensored},
      author={Stepan Zuev},
      year={2023},
      month={Dec}
}

README history 1 version

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

2024-07-23uploaded readmef82b4965.8 KB
Loading...

RichardErkhov/w4r10ck_-_SOLAR-10.7B-Instruct-v1.0-uncensored-gguf

The browser can't see your hardware

The Abliteration app is integrated with your machine

And you can chat with any model, right now

Repackaging (quantization)

Metadata

Related

Files by quantization

README current version from Hugging Face

Original model description:

license: apache-2.0

SOLAR-10.7B-Instruct-v1.0-uncensored

Training details

How to Cite

README history 1 version

Run models on your own machine, not in the cloud.