huggingface/candle
1
0
Fork 0
mirror of https://github.com/huggingface/candle.git synced 2025-06-15 18:28:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

Mention rwkv v6 in the readmes. (#1784)

Browse Source
This commit is contained in:
Laurent Mazare
2024-03-01 08:58:30 +01:00
committed by GitHub
parent 979deaca07
commit 64d4038e4f
2 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -79,7 +79,7 @@ We also provide a some command line based examples using state of the art models
- [StarCoder](./candle-examples/examples/bigcode/) and - [StarCoder](./candle-examples/examples/bigcode/) and
[StarCoder2](./candle-examples/examples/starcoder2/): LLM specialized to code generation. [StarCoder2](./candle-examples/examples/starcoder2/): LLM specialized to code generation.
- [Qwen1.5](./candle-examples/examples/qwen/): Bilingual (English/Chinese) LLMs. - [Qwen1.5](./candle-examples/examples/qwen/): Bilingual (English/Chinese) LLMs.
- [RWKV v5](./candle-examples/examples/rwkv/): An RNN with transformer level LLM - [RWKV v5 and v6](./candle-examples/examples/rwkv/): An RNN with transformer level LLM
performance. performance.
- [Replit-code-v1.5](./candle-examples/examples/replit-code/): a 3.3b LLM specialized for code completion. - [Replit-code-v1.5](./candle-examples/examples/replit-code/): a 3.3b LLM specialized for code completion.
- [Yi-6B / Yi-34B](./candle-examples/examples/yi/): two bilingual - [Yi-6B / Yi-34B](./candle-examples/examples/yi/): two bilingual
@ -203,7 +203,7 @@ If you have an addition to this list, please submit a pull request.
- Bert. - Bert.
- Yi-6B and Yi-34B. - Yi-6B and Yi-34B.
- Qwen1.5. - Qwen1.5.
- RWKV. - RWKV v5 and v6.
- Quantized LLMs. - Quantized LLMs.
- Llama 7b, 13b, 70b, as well as the chat and code variants. - Llama 7b, 13b, 70b, as well as the chat and code variants.
- Mistral 7b, and 7b instruct. - Mistral 7b, and 7b instruct.

4
candle-examples/examples/rwkv/README.md
View File

@ -2,8 +2,8 @@
The [RWKV model](https://wiki.rwkv.com/) is a recurrent neural network model The [RWKV model](https://wiki.rwkv.com/) is a recurrent neural network model
with performance on par with transformer architectures. Several variants are with performance on par with transformer architectures. Several variants are
available, candle implements the v5 version and can be used with Eagle 7B([blog available, candle implements the v5 and v6 versions and can be used with
post](https://blog.rwkv.com/p/eagle-7b-soaring-past-transformers)). Eagle 7B([blog post](https://blog.rwkv.com/p/eagle-7b-soaring-past-transformers)).
```bash ```bash
$ cargo run --example rwkv --release -- --prompt "The smallest prime is " $ cargo run --example rwkv --release -- --prompt "The smallest prime is "