GraySoft
Download guIDE →
Model Comparison

quantfactory/llama-3.2-3b-instruct-abliterated-ggufvsvaluefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8

Side-by-side comparison of quantfactory/llama-3.2-3b-instruct-abliterated-gguf and valuefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8: downloads, license, context length, tasks, and benchmarks.

quantfactory/llama-3.2-3b-instruct-abliterated-gguf

QuantFactory · —

This is quantized version of huihui-ai/Llama-3.2-3B-Instruct-abliterated created using llama.cpp # Original Model Card # 🦙 Llama-3.2-3B-Instruct-abliterated This is an uncensored version of Llama 3.2 3B Instruct created with abliteration (see this article to know more about it)…

valuefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8

ValueFX9507 · reinforcement-learning

prompt = """你是一个小女孩/你是一个XX角色... 我走进门，看到你冲上来迎接我 需要体现人物的气质 加入环境描写 保持对话风格 我看到XX进门...""" `` **参数推荐**： `python generation_config = { "temperature": 0.75, "top_p": 0.6, "repetition_penalty": 1.08, "max_new_tokens": 1536, "do_sample": True } ``

Side-by-side Specifications

quantfactory/llama-3.2-3b-instruct-abliterated-ggufvaluefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8
AuthorQuantFactoryValueFX9507
Pipeline Task—reinforcement-learning
Librarytransformerstransformers
Downloads27,09423,629
Likes11201
LicenseUnknownUnknown
Context Length——
Created2024-10-082025-02-15
Last Modified2024-10-082025-03-28
Tags
transformersggufabliterateduncensoredbase_model:meta-llama/Llama-3.2-3B-Instructbase_model:quantized:meta-llama/Llama-3.2-3B-Instructlicense:llama3.2endpoints_compatibleregion:usconversational
transformersggufincremental-pretrainingsftreinforcement-learningroleplaycotzhenlicense:apache-2.0

View full details: quantfactory/llama-3.2-3b-instruct-abliterated-gguf · valuefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8