You can deploy this model and start earning money today!

RichardErkhov/
grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf

Name: grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3.1-8B-Instruct-abliterated_via_adapter - GGUF

Model creator: https://huggingface.co/grimjim/
Original model: https://huggingface.co/grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter/

Name	Quant method	Size
Llama-3.1-8B-Instruct-abliterated_via_adapter.Q2_K.gguf	Q2_K	2.96GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.IQ3_XS.gguf	IQ3_XS	3.28GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.IQ3_S.gguf	IQ3_S	3.43GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.Q3_K_S.gguf	Q3_K_S	3.41GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.IQ3_M.gguf	IQ3_M	3.52GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.Q3_K.gguf	Q3_K	3.74GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.Q3_K_M.gguf	Q3_K_M	3.74GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.Q3_K_L.gguf	Q3_K_L	4.03GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.IQ4_XS.gguf	IQ4_XS	4.18GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.Q4_0.gguf	Q4_0	4.34GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.IQ4_NL.gguf	IQ4_NL	4.38GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.Q4_K_S.gguf	Q4_K_S	4.37GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.Q4_K.gguf	Q4_K	4.58GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.Q4_K_M.gguf	Q4_K_M	4.58GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.Q4_1.gguf	Q4_1	4.78GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.Q5_0.gguf	Q5_0	5.21GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.Q5_K_S.gguf	Q5_K_S	5.21GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.Q5_K.gguf	Q5_K	5.34GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.Q5_K_M.gguf	Q5_K_M	5.34GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.Q5_1.gguf	Q5_1	5.65GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.Q6_K.gguf	Q6_K	6.14GB
Llama-3.1-8B-Instruct-abliterated_via_adapter.Q8_0.gguf	Q8_0	7.95GB

Original model description:

base_model:

meta-llama/Meta-Llama-3.1-8B-Instruct
grimjim/Llama-3-Instruct-abliteration-LoRA-8B library_name: transformers tags:
mergekit
merge license: llama3.1 pipeline_tag: text-generation

Llama-3.1-8B-Instruct-abliterated_via_adapter

This model is a merge of pre-trained language models created using mergekit.

A LoRA was applied to "abliterate" refusals in meta-llama/Meta-Llama-3.1-8B-Instruct. The result appears to work despite the LoRA having been derived from Llama 3 instead of Llama 3.1, which implies that there is significant feature commonality between the 3 and 3.1 models.

The LoRA was extracted from failspy/Meta-Llama-3-8B-Instruct-abliterated-v3 using meta-llama/Meta-Llama-3-8B-Instruct as a base.

Built with Llama.

Merge Details

Merge Method

This model was merged using the task arithmetic merge method using meta-llama/Meta-Llama-3.1-8B-Instruct + grimjim/Llama-3-Instruct-abliteration-LoRA-8B as a base.

Configuration

The following YAML configuration was used to produce this model:

yaml

base_model: meta-llama/Meta-Llama-3.1-8B-Instruct+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  normalize: false
slices:
- sources:
  - layer_range: [0, 32]
    model: meta-llama/Meta-Llama-3.1-8B-Instruct+grimjim/Llama-3-Instruct-abliteration-LoRA-8B
    parameters:
      weight: 1.0

RichardErkhov/grimjim_-_Llama-3.1-8B-Instruct-abliterated_via_adapter-gguf