From Seikaijyu/temp: https://huggingface.co/Seikaijyu/temp

Based on my experience, Q4_K_S and Q4_K_M are usually the balance points between model size, quantization, and speed.

In some benchmarks, selecting a large-parameter low-quantization LLM tends to perform better than a small-parameter high-quantization LLM.

根据我的经验,通常Q4_K_S、Q4_K_M是模型尺寸/量化/速度的平衡点

在某些基准测试中,选择大参数低量化模型往往比选择小参数高量化模型表现更好。

Downloads last month
84
GGUF
Model size
7.64B params
Architecture
rwkv6

4-bit

Inference API
Unable to determine this model's library. Check the docs .

Model tree for btaskel/RWKV6-7B-Chn-UnlimitedRP-chat-beta2-GGUF

Base model

Seikaijyu/temp
Quantized
(2)
this model