GraySoft
Model Comparison

maziyarpanahi/meta-llama-3-8b-instruct-ggufvsvaluefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8

Side-by-side comparison of maziyarpanahi/meta-llama-3-8b-instruct-gguf and valuefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8: downloads, license, context length, tasks, and benchmarks.

maziyarpanahi/meta-llama-3-8b-instruct-gguf

MaziyarPanahi · text-generation

# MaziyarPanahi/Meta-Llama-3-8B-Instruct-GGUF The GGUF and quantized models here are based on meta-llama/Meta-Llama-3-8B-Instruct model

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

maziyarpanahi/meta-llama-3-8b-instruct-ggufvaluefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8
AuthorMaziyarPanahiValueFX9507
Pipeline Tasktext-generationreinforcement-learning
Librarytransformerstransformers
Downloads90,57823,629
Likes102201
LicenseUnknownUnknown
Context Length
Created2024-04-182025-02-15
Last Modified2024-04-232025-03-28
Tags
transformersggufmistralfacebookmetapytorchllamallama-3quantized2-bit
transformersggufincremental-pretrainingsftreinforcement-learningroleplaycotzhenlicense:apache-2.0

View full details: maziyarpanahi/meta-llama-3-8b-instruct-gguf · valuefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8