Upload 2 files
Browse files- README.md +74 -0
- gitattributes +97 -0
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- quantized
|
| 4 |
+
- 2-bit
|
| 5 |
+
- 3-bit
|
| 6 |
+
- 4-bit
|
| 7 |
+
- 5-bit
|
| 8 |
+
- 6-bit
|
| 9 |
+
- 8-bit
|
| 10 |
+
- GGUF
|
| 11 |
+
- transformers
|
| 12 |
+
- safetensors
|
| 13 |
+
- mistral
|
| 14 |
+
- text-generation
|
| 15 |
+
- arxiv:2304.12244
|
| 16 |
+
- arxiv:2306.08568
|
| 17 |
+
- arxiv:2308.09583
|
| 18 |
+
- license:apache-2.0
|
| 19 |
+
- autotrain_compatible
|
| 20 |
+
- endpoints_compatible
|
| 21 |
+
- text-generation-inference
|
| 22 |
+
- region:us
|
| 23 |
+
- text-generation
|
| 24 |
+
model_name: WizardLM-2-8x22B-GGUF
|
| 25 |
+
base_model: microsoft/WizardLM-2-8x22B
|
| 26 |
+
inference: false
|
| 27 |
+
model_creator: microsoft
|
| 28 |
+
pipeline_tag: text-generation
|
| 29 |
+
quantized_by: MaziyarPanahi
|
| 30 |
+
---
|
| 31 |
+
# [MaziyarPanahi/WizardLM-2-8x22B-GGUF](https://huggingface.co/MaziyarPanahi/WizardLM-2-8x22B-GGUF)
|
| 32 |
+
- Model creator: [microsoft](https://huggingface.co/microsoft)
|
| 33 |
+
- Original model: [microsoft/WizardLM-2-8x22B](https://huggingface.co/microsoft/WizardLM-2-8x22B)
|
| 34 |
+
|
| 35 |
+
## Description
|
| 36 |
+
[MaziyarPanahi/WizardLM-2-8x22B-GGUF](https://huggingface.co/MaziyarPanahi/WizardLM-2-8x22B-GGUF) contains GGUF format model files for [microsoft/WizardLM-2-8x22B](https://huggingface.co/microsoft/WizardLM-2-8x22B).
|
| 37 |
+
|
| 38 |
+
## How to download
|
| 39 |
+
You can download only the quants you need instead of cloning the entire repository as follows:
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
```
|
| 43 |
+
huggingface-cli download MaziyarPanahi/WizardLM-2-8x22B-GGUF --local-dir . --include '*Q2_K*gguf'
|
| 44 |
+
```
|
| 45 |
+
|
| 46 |
+
On Windows:
|
| 47 |
+
|
| 48 |
+
```sh
|
| 49 |
+
huggingface-cli download MaziyarPanahi/WizardLM-2-8x22B-GGUF --local-dir . --include *Q4_K_S*gguf
|
| 50 |
+
```
|
| 51 |
+
|
| 52 |
+
## Load sharded model
|
| 53 |
+
|
| 54 |
+
`llama_load_model_from_file` will detect the number of files and will load additional tensors from the rest of files.
|
| 55 |
+
|
| 56 |
+
```sh
|
| 57 |
+
llama.cpp/main -m WizardLM-2-8x22B.Q2_K-00001-of-00005.gguf -p "Building a website can be done in 10 simple steps:\nStep 1:" -n 1024 -e
|
| 58 |
+
```
|
| 59 |
+
|
| 60 |
+
## Prompt template
|
| 61 |
+
|
| 62 |
+
```
|
| 63 |
+
{system_prompt}
|
| 64 |
+
USER: {prompt}
|
| 65 |
+
ASSISTANT: </s>
|
| 66 |
+
```
|
| 67 |
+
|
| 68 |
+
or
|
| 69 |
+
|
| 70 |
+
```
|
| 71 |
+
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful,
|
| 72 |
+
detailed, and polite answers to the user's questions. USER: Hi ASSISTANT: Hello.</s>
|
| 73 |
+
USER: {prompt} ASSISTANT: </s>......
|
| 74 |
+
```
|
gitattributes
ADDED
|
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
WizardLM-2-8x22B.Q2_K-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
WizardLM-2-8x22B.Q2_K-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
WizardLM-2-8x22B.Q2_K-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
WizardLM-2-8x22B.Q2_K-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
WizardLM-2-8x22B.Q2_K-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
WizardLM-2-8x22B.IQ3_XS-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
WizardLM-2-8x22B.IQ3_XS-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
WizardLM-2-8x22B.IQ3_XS-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
WizardLM-2-8x22B.IQ3_XS-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
WizardLM-2-8x22B.IQ3_XS-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
WizardLM-2-8x22B.Q3_K_S-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
WizardLM-2-8x22B.Q3_K_S-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
WizardLM-2-8x22B.Q3_K_S-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
WizardLM-2-8x22B.Q3_K_S-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
WizardLM-2-8x22B.Q3_K_S-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
WizardLM-2-8x22B.Q3_K_L-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
WizardLM-2-8x22B.Q3_K_L-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
WizardLM-2-8x22B.Q3_K_L-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
WizardLM-2-8x22B.Q3_K_L-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
WizardLM-2-8x22B.Q3_K_L-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
WizardLM-2-8x22B.Q3_K_M-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
WizardLM-2-8x22B.Q3_K_M-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 58 |
+
WizardLM-2-8x22B.Q3_K_M-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 59 |
+
WizardLM-2-8x22B.Q3_K_M-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 60 |
+
WizardLM-2-8x22B.Q3_K_M-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 61 |
+
WizardLM-2-8x22B.Q4_K_S-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 62 |
+
WizardLM-2-8x22B.Q4_K_S-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 63 |
+
WizardLM-2-8x22B.Q4_K_S-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 64 |
+
WizardLM-2-8x22B.Q4_K_S-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 65 |
+
WizardLM-2-8x22B.Q4_K_S-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 66 |
+
WizardLM-2-8x22B.IQ4_XS-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 67 |
+
WizardLM-2-8x22B.IQ4_XS-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 68 |
+
WizardLM-2-8x22B.IQ4_XS-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 69 |
+
WizardLM-2-8x22B.IQ4_XS-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 70 |
+
WizardLM-2-8x22B.IQ4_XS-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 71 |
+
WizardLM-2-8x22B.Q4_K_M-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 72 |
+
WizardLM-2-8x22B.Q4_K_M-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 73 |
+
WizardLM-2-8x22B.Q4_K_M-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 74 |
+
WizardLM-2-8x22B.Q4_K_M-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 75 |
+
WizardLM-2-8x22B.Q4_K_M-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 76 |
+
WizardLM-2-8x22B.Q5_K_M-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 77 |
+
WizardLM-2-8x22B.Q5_K_M-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 78 |
+
WizardLM-2-8x22B.Q5_K_M-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 79 |
+
WizardLM-2-8x22B.Q5_K_M-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 80 |
+
WizardLM-2-8x22B.Q5_K_M-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 81 |
+
WizardLM-2-8x22B.Q5_K_S-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 82 |
+
WizardLM-2-8x22B.Q5_K_S-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 83 |
+
WizardLM-2-8x22B.Q5_K_S-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 84 |
+
WizardLM-2-8x22B.Q5_K_S-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 85 |
+
WizardLM-2-8x22B.Q5_K_S-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 86 |
+
WizardLM-2-8x22B.Q6_K-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 87 |
+
WizardLM-2-8x22B.Q6_K-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 88 |
+
WizardLM-2-8x22B.Q6_K-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 89 |
+
WizardLM-2-8x22B.Q6_K-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 90 |
+
WizardLM-2-8x22B.Q6_K-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 91 |
+
WizardLM-2-8x22B.Q8_0-00001-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 92 |
+
WizardLM-2-8x22B.Q8_0-00002-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 93 |
+
WizardLM-2-8x22B.Q8_0-00003-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 94 |
+
WizardLM-2-8x22B.Q8_0-00004-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 95 |
+
WizardLM-2-8x22B.Q8_0-00005-of-00005.gguf filter=lfs diff=lfs merge=lfs -text
|
| 96 |
+
WizardLM-2-8x22B.IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 97 |
+
WizardLM-2-8x22B.IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text
|