---
title: rwkv-4-pile-14b
canonical_url: "https://www.modelscope.cn/models/Blink_DL/rwkv-4-pile-14b"
md_url: "https://www.modelscope.cn/models/Blink_DL/rwkv-4-pile-14b.md"
repository: Blink_DL/rwkv-4-pile-14b
last_updated: 2024-12-12
license: apache-2.0
pipeline_tag: fill-mask
tasks:
  - fill-mask
library_name:
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 1922
stars: 10
tags:
  - pytorch
  - text-generation
  - causal-lm
  - rwkv
---

# rwkv-4-pile-14b

> rwkv-4-pile-14b - Blink_DL 在 ModelScope 开源的模型。[UPDATE: Try RWKV-4-World (https://huggingface.co/BlinkDL/rwkv-4-world) for generation & chat & code in 100+ world languages, with great English zero-shot & in-context learning ability too.]

Blink_DL/rwkv-4-pile-14b 是 ModelScope 魔搭社区上的fill-mask模型，采用 apache-2.0 许可。

- **Repository**: Blink_DL/rwkv-4-pile-14b
- **License**: apache-2.0
- **Tasks**: fill-mask
- **Tags**: pytorch, text-generation, causal-lm, rwkv
- **Downloads**: 1922
- **Stars**: 10
- **Last updated**: 2024-12-12

Source: https://www.modelscope.cn/models/Blink_DL/rwkv-4-pile-14b

---

# RWKV-4 14B

[UPDATE: Try RWKV-4-World (https://huggingface.co/BlinkDL/rwkv-4-world) for generation & chat & code in 100+ world languages, with great English zero-shot & in-context learning ability too.]

## Model Description

RWKV-4 14B is a L40-D5120 causal language model trained on the Pile. See https://github.com/BlinkDL/RWKV-LM for details.

args.n_layer = 40
args.n_embd = 5120

Use https://github.com/BlinkDL/ChatRWKV to run it.

RWKV-4-Pile-14B-2023xxxx-ctx8192-testxxx.pth : Fine-tuned to ctx_len 8192.
* The best general model.

################################

"Raven": RWKV alpaca+vicuna-style model: https://huggingface.co/BlinkDL/rwkv-4-raven (highly recommended)

It is a strong chat model too. You can use +i for "Alpaca Instruct" in latest ChatRWKV v2. Examples:
```
+i Explain the following metaphor: "Life is like cats". 
+i write a python function to read data from an excel file.
```
################################

RWKV-4-Pile-14B-20230213-8019.pth : Trained on the Pile for 331B tokens
* Pile loss 1.7579 (ctx_len 1024)
* LAMBADA ppl 3.81, acc 71.05%
* PIQA acc 77.42%
* SC2016 acc 75.57%
* Hellaswag acc_norm 70.24%
* WinoGrande acc 62.98%