RWKV7-Gxx-GGUF
Collection
GGUF of RWKV7-G series reasoning models • 10 items • Updated • 13
How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf shoumenchougou/RWKV7-G1g-1.5B-GGUF:# Run inference directly in the terminal:
llama-cli -hf shoumenchougou/RWKV7-G1g-1.5B-GGUF:Use pre-built binary
# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf shoumenchougou/RWKV7-G1g-1.5B-GGUF:# Run inference directly in the terminal:
./llama-cli -hf shoumenchougou/RWKV7-G1g-1.5B-GGUF:Build from source code
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf shoumenchougou/RWKV7-G1g-1.5B-GGUF:# Run inference directly in the terminal:
./build/bin/llama-cli -hf shoumenchougou/RWKV7-G1g-1.5B-GGUF:Use Docker
docker model run hf.co/shoumenchougou/RWKV7-G1g-1.5B-GGUF:Quick Links
1️⃣ What are G0 / G1 / G1a2 / G1b / G1c / G1d / G1e / G1f / G1g ?
The fields like G0 / G1a / G1b in RWKV model names indicate versions of the training data. In terms of data quality, the ranking is: G1g > G1f > G1e > G1d > G1c > G1b > G1a2 > G1a > G1 > G0a2 > G0.
The RWKV7-G1a model is an advanced version of RWKV7-G1 that was further trained with 1T (1 trillion tokens) of high-quality inference and instruction data.
RWKV7-G1a2 was produced by continuing to add more data and training on top of RWKV7-G1a.
2️⃣ What is the difference between the RWKV7-G series and the World series?
The RWKV7-G series supports an inference mode, which can be activated using the following format:
User: USER_PROMPT
Assistant: <think
3️⃣ How to choose the best model?
Look at the date in the model name — for the same parameter size, a newer model is better!
For example, for the same 1.5B model, a G1a2 version released on 251005 will definitely be superior to a G1 version released on 250429.
For the 0.1B and 0.4B models, we recommend using FP16/Q8_0 quantization. Otherwise, the models may fail to complete tasks due to precision loss caused by quantization.**
1️⃣ G0/G1/G1a2/G1b/G1c/G1d/G1e/G1f/G1g 是什么?
RWKV 模型名称中的 G0a/G1a/G1a2 等字段是训练数据的版本，数据质量排序：G1g > G1f > G1e > G1d > G1c > G1b > G1a2 > G1a > G1 > G0a2 > G0 。
RWKV7-G1a 模型是在 RWKV7-G1 模型的基础上继续训练了 1T 优质推理和指令数据的进阶版，RWKV7-G1a2 则是在 RWKV7-G1a 模型的基础上继续添加数据训练，以此类推。
2️⃣ RWKV7-G 系列和 World 系列有什么区别？
RWKV7-G 系列模型支持推理模式，可通过以下格式开启推理模式：
User: USER_PROMPT
Assistant: <think
3️⃣ 如何选择最好的模型？
看模型名称中的日期，相同的参数，模型越新越好！
比如同样是 1.5B 模型，发布于 251005 的 G1a2 版本必定优于 250429 的 G1 版本 。
对于 0.1B 和 0.4B 模型，我们建议使用 FP16/Q8_0 量化类型。否则模型可能因量化带来的精度损失而无法完成任务。
- Downloads last month
- 212
Hardware compatibility
Log In to add your hardware
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install from brew
# Start a local OpenAI-compatible server with a web UI: llama-server -hf shoumenchougou/RWKV7-G1g-1.5B-GGUF:# Run inference directly in the terminal: llama-cli -hf shoumenchougou/RWKV7-G1g-1.5B-GGUF: