GraySoft
Model Comparison

mradermacher/culturellm-english-27b-i1-ggufvsvaluefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8

Side-by-side comparison of mradermacher/culturellm-english-27b-i1-gguf and valuefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8: downloads, license, context length, tasks, and benchmarks.

mradermacher/culturellm-english-27b-i1-gguf

mradermacher · —

## About weighted/imatrix quants of https://huggingface.co/WonseokChoi123/culturellm-english-27b ***For a convenient overview and download list, visit our model page for this model.*** static quants are available at https://huggingface.co/mradermacher/culturellm-english-27b-GGUF

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

mradermacher/culturellm-english-27b-i1-ggufvaluefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8
AuthormradermacherValueFX9507
Pipeline Taskreinforcement-learning
Librarytransformerstransformers
Downloads34,58123,629
Likes0201
LicenseUnknownUnknown
Context Length
Created2026-03-282025-02-15
Last Modified2026-03-282025-03-28
Tags
transformersggufenbase_model:WonseokChoi123/culturellm-english-27bbase_model:quantized:WonseokChoi123/culturellm-english-27bendpoints_compatibleregion:usimatrixconversational
transformersggufincremental-pretrainingsftreinforcement-learningroleplaycotzhenlicense:apache-2.0

View full details: mradermacher/culturellm-english-27b-i1-gguf · valuefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8