|
--- |
|
base_model: grimulkan/lzlv-longLORA-70b-rope8-32k-fp16 |
|
inference: false |
|
license: cc-by-nc-2.0 |
|
model_creator: Grimulkan |
|
model_name: lzlv longLORA 70b rope8 32k |
|
model_type: llama |
|
--- |
|
|
|
# lzlv longLORA 70b rope8 32k - GGUF |
|
|
|
- Model creator: [Grimulkan](https://huggingface.co/grimulkan) |
|
- Original model: [lzlv longLORA 70b rope8 32k](https://huggingface.co/grimulkan/lzlv-longLORA-70b-rope8-32k-fp16) |
|
|
|
## Description |
|
|
|
This repo contains GGUF format model files for [Grimulkan's lzlv longLORA 70b rope8 32k](https://huggingface.co/grimulkan). |
|
|
|
## Provided files |
|
| Name | Quant method | Bits | Size | |
|
| ---- | ---- | ---- | ---- | |
|
| lzlv_70b_fp16_hf.Q2_K.gguf | Q2_K | 2 | 25.46 GB| |
|
| lzlv_70b_fp16_hf.Q3_K_M.gguf| Q3_K_M | 3 | 33.27 GB| |
|
| lzlv_70b_fp16_hf.Q4_K_S.gguf | Q4_K_S | 4 | 39.25 GB| |
|
| lzlv_70b_fp16_hf.Q4_K_M.gguf | Q4_K_M | 4 | 41.42 GB| |
|
| lzlv_70b_fp16_hf.Q5_K_S.gguf | Q5_K_S | 5 | 47.46 GB| |
|
| lzlv_70b_fp16_hf.Q5_K_M.gguf | Q5_K_M | 5 | 48.75 GB| |
|
| lzlv_70b_fp16_hf.Q6_K.gguf | Q6_K | 6 | 56.59 GB | |
|
| lzlv_70b_fp16_hf.Q8_0.gguf | Q8_0 | 8 | 73.29 GB | |
|
|
|
Note: HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files. |
