GraySoft
Model Comparison

ggml-org/glm-ocr-ggufvsvaluefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8

Side-by-side comparison of ggml-org/glm-ocr-gguf and valuefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8: downloads, license, context length, tasks, and benchmarks.

ggml-org/glm-ocr-gguf

ggml-org · —

This model is converted from zai-org/GLM-OCR to GGUF using convert_hf_to_gguf.py To use it: `` llama-server -hf ggml-org/GLM-OCR-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

ggml-org/glm-ocr-ggufvaluefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8
Authorggml-orgValueFX9507
Pipeline Taskreinforcement-learning
Librarytransformers
Downloads21,79123,629
Likes50201
LicenseUnknownUnknown
Context Length
Created2026-02-172025-02-15
Last Modified2026-03-102025-03-28
Tags
ggufbase_model:zai-org/GLM-OCRbase_model:quantized:zai-org/GLM-OCRendpoints_compatibleregion:usconversational
transformersggufincremental-pretrainingsftreinforcement-learningroleplaycotzhenlicense:apache-2.0

View full details: ggml-org/glm-ocr-gguf · valuefx9507/tifa-deepsexv2-7b-mgrpo-gguf-q8