Downloads · 30 days
117
5% of all-time downloads
RichardErkhov/Neko-Institute-of-Science_-_LLaMA-13B-HF-gguf
Neko-Institute-of-Science_-_LLaMA-13B-HF-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
117
5% of all-time downloads
All-time downloads
2.3K
Public
Repo size
130 GB
Likes
0
Public
Click a slice to open those files.
.gguf154 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
LLaMA-13B-HF - GGUF
| Name | Quant method | Size |
|---|---|---|
| LLaMA-13B-HF.Q2_K.gguf | Q2_K | 4.52GB |
| LLaMA-13B-HF.Q3_K_S.gguf | Q3_K_S | 5.27GB |
| LLaMA-13B-HF.Q3_K.gguf | Q3_K | 5.9GB |
| LLaMA-13B-HF.Q3_K_M.gguf | Q3_K_M | 5.9GB |
| LLaMA-13B-HF.Q3_K_L.gguf | Q3_K_L | 6.45GB |
| LLaMA-13B-HF.IQ4_XS.gguf | IQ4_XS | 6.54GB |
| LLaMA-13B-HF.Q4_0.gguf | Q4_0 | 6.86GB |
| LLaMA-13B-HF.IQ4_NL.gguf | IQ4_NL | 6.9GB |
| LLaMA-13B-HF.Q4_K_S.gguf | Q4_K_S | 6.91GB |
| LLaMA-13B-HF.Q4_K.gguf | Q4_K | 7.33GB |
| LLaMA-13B-HF.Q4_K_M.gguf | Q4_K_M | 7.33GB |
| LLaMA-13B-HF.Q4_1.gguf | Q4_1 | 7.61GB |
| LLaMA-13B-HF.Q5_0.gguf | Q5_0 | 8.36GB |
| LLaMA-13B-HF.Q5_K_S.gguf | Q5_K_S | 8.36GB |
| LLaMA-13B-HF.Q5_K.gguf | Q5_K | 8.6GB |
| LLaMA-13B-HF.Q5_K_M.gguf | Q5_K_M | 8.6GB |
| LLaMA-13B-HF.Q5_1.gguf | Q5_1 | 9.1GB |
| LLaMA-13B-HF.Q6_K.gguf | Q6_K | 9.95GB |
| LLaMA-13B-HF.Q8_0.gguf | Q8_0 | 12.88GB |
LLaMA converted to Transformers. This is under a special license, please see the LICENSE file for details.
https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md
Note: the torrent has outdated tokenizer_config.json and special_tokens_map.json. Replace them with the ones here. For those who want to save HF's bandwith here's a magnet link: magnet:?xt=urn:btih:8d634925911a03f787d9f68ac075a9b24281573a&dn=Safe-LLaMA-HF-v2%20(4-04-23)&tr=http%3a%2f%2fbt2.archive.org%3a6969%2fannounce&tr=http%3a%2f%2fbt1.archive.org%3a6969%2fannounce