Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- LLaMA3-iterative-DPO-final-Q2_K.gguf +3 -0
- LLaMA3-iterative-DPO-final-Q3_K_L.gguf +3 -0
- LLaMA3-iterative-DPO-final-Q3_K_M.gguf +3 -0
- LLaMA3-iterative-DPO-final-Q3_K_S.gguf +3 -0
- LLaMA3-iterative-DPO-final-Q4_0.gguf +3 -0
- LLaMA3-iterative-DPO-final-Q4_K_M.gguf +3 -0
- LLaMA3-iterative-DPO-final-Q4_K_S.gguf +3 -0
- LLaMA3-iterative-DPO-final-Q5_0.gguf +3 -0
- LLaMA3-iterative-DPO-final-Q5_K_M.gguf +3 -0
- LLaMA3-iterative-DPO-final-Q5_K_S.gguf +3 -0
- LLaMA3-iterative-DPO-final-Q6_K.gguf +3 -0
- LLaMA3-iterative-DPO-final-Q8_0.gguf +3 -0
- README.md +74 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,15 @@ saved_model/**/* 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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
LLaMA3-iterative-DPO-final-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
LLaMA3-iterative-DPO-final-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
LLaMA3-iterative-DPO-final-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
LLaMA3-iterative-DPO-final-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
LLaMA3-iterative-DPO-final-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
LLaMA3-iterative-DPO-final-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
LLaMA3-iterative-DPO-final-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
LLaMA3-iterative-DPO-final-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
LLaMA3-iterative-DPO-final-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
LLaMA3-iterative-DPO-final-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
LLaMA3-iterative-DPO-final-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
LLaMA3-iterative-DPO-final-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
LLaMA3-iterative-DPO-final-Q2_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e5c024f234ab7165d848269dfb1be9172280530dc21abc7c227d585bf4d78cd
|
| 3 |
+
size 3179131328
|
LLaMA3-iterative-DPO-final-Q3_K_L.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7831babe0b6a65611d855a46124bc7f0f7acf4f2d51255470fde0b847cb96832
|
| 3 |
+
size 4321956288
|
LLaMA3-iterative-DPO-final-Q3_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8139f08a54d624b368098f4334f45c4cd5d4120d32faf1201e7aecf46d0800af
|
| 3 |
+
size 4018917824
|
LLaMA3-iterative-DPO-final-Q3_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f79e97ec42fb4091e59294aaa6bcfaf295e6469fd52e6df70efc8fd1155e9ad
|
| 3 |
+
size 3664499136
|
LLaMA3-iterative-DPO-final-Q4_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46a12c49862d48a898303333b6adc4c57f163605cbb5d8ee75b555469f12f4d1
|
| 3 |
+
size 4661211584
|
LLaMA3-iterative-DPO-final-Q4_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a32eee05f827dda949e0fe4527a74b9a66ad6763f7cebc87d99033dd34341a5f
|
| 3 |
+
size 4920734144
|
LLaMA3-iterative-DPO-final-Q4_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a9c9f8e9f251d67ab0ad0f50ed473848157b64c4486bb12f58aa53c64b3e8fa
|
| 3 |
+
size 4692668864
|
LLaMA3-iterative-DPO-final-Q5_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0782823ab913a07b4db9407daf1ec82eba173a96e7f28a2a5e24de3df6c360a4
|
| 3 |
+
size 5599293888
|
LLaMA3-iterative-DPO-final-Q5_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b39f322bd3ff82fa8859fa39eb1705dba32496f0134d5d0fd6497e7d2ea47610
|
| 3 |
+
size 5732987328
|
LLaMA3-iterative-DPO-final-Q5_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96c2f48dfadad0c3e810229e022e13698ab5f14d6d5f12c17629337f85156053
|
| 3 |
+
size 5599293888
|
LLaMA3-iterative-DPO-final-Q6_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d111713677fe53eb2a6c3692c05a1416147055b3ec6277e9b23111b89bc4e5a
|
| 3 |
+
size 6596006336
|
LLaMA3-iterative-DPO-final-Q8_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b36b9650f7a0030d6e29f6a7cae9ff04fbc2150b5cf6964ec7b2fe3efa465af
|
| 3 |
+
size 8540770752
|
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
tags:
|
| 4 |
+
- TensorBlock
|
| 5 |
+
- GGUF
|
| 6 |
+
base_model: RLHFlow/LLaMA3-iterative-DPO-final
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
| 10 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
| 11 |
+
</div>
|
| 12 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
| 13 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
| 14 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
| 15 |
+
Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
|
| 16 |
+
</p>
|
| 17 |
+
</div>
|
| 18 |
+
</div>
|
| 19 |
+
|
| 20 |
+
## RLHFlow/LLaMA3-iterative-DPO-final - GGUF
|
| 21 |
+
|
| 22 |
+
This repo contains GGUF format model files for [RLHFlow/LLaMA3-iterative-DPO-final](https://huggingface.co/RLHFlow/LLaMA3-iterative-DPO-final).
|
| 23 |
+
|
| 24 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
|
| 25 |
+
|
| 26 |
+
## Prompt template
|
| 27 |
+
|
| 28 |
+
```
|
| 29 |
+
<|start_header_id|>system<|end_header_id|>
|
| 30 |
+
{system_prompt}<|eot_id|>
|
| 31 |
+
<|start_header_id|>user<|end_header_id|>
|
| 32 |
+
{prompt}<|eot_id|>
|
| 33 |
+
<|start_header_id|>assistant<|end_header_id|>
|
| 34 |
+
```
|
| 35 |
+
|
| 36 |
+
## Model file specification
|
| 37 |
+
|
| 38 |
+
| Filename | Quant type | File Size | Description |
|
| 39 |
+
| -------- | ---------- | --------- | ----------- |
|
| 40 |
+
| [LLaMA3-iterative-DPO-final-Q2_K.gguf](https://huggingface.co/tensorblock/LLaMA3-iterative-DPO-final-GGUF/tree/main/LLaMA3-iterative-DPO-final-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
|
| 41 |
+
| [LLaMA3-iterative-DPO-final-Q3_K_S.gguf](https://huggingface.co/tensorblock/LLaMA3-iterative-DPO-final-GGUF/tree/main/LLaMA3-iterative-DPO-final-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
|
| 42 |
+
| [LLaMA3-iterative-DPO-final-Q3_K_M.gguf](https://huggingface.co/tensorblock/LLaMA3-iterative-DPO-final-GGUF/tree/main/LLaMA3-iterative-DPO-final-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
|
| 43 |
+
| [LLaMA3-iterative-DPO-final-Q3_K_L.gguf](https://huggingface.co/tensorblock/LLaMA3-iterative-DPO-final-GGUF/tree/main/LLaMA3-iterative-DPO-final-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
|
| 44 |
+
| [LLaMA3-iterative-DPO-final-Q4_0.gguf](https://huggingface.co/tensorblock/LLaMA3-iterative-DPO-final-GGUF/tree/main/LLaMA3-iterative-DPO-final-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
| 45 |
+
| [LLaMA3-iterative-DPO-final-Q4_K_S.gguf](https://huggingface.co/tensorblock/LLaMA3-iterative-DPO-final-GGUF/tree/main/LLaMA3-iterative-DPO-final-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
|
| 46 |
+
| [LLaMA3-iterative-DPO-final-Q4_K_M.gguf](https://huggingface.co/tensorblock/LLaMA3-iterative-DPO-final-GGUF/tree/main/LLaMA3-iterative-DPO-final-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
|
| 47 |
+
| [LLaMA3-iterative-DPO-final-Q5_0.gguf](https://huggingface.co/tensorblock/LLaMA3-iterative-DPO-final-GGUF/tree/main/LLaMA3-iterative-DPO-final-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
| 48 |
+
| [LLaMA3-iterative-DPO-final-Q5_K_S.gguf](https://huggingface.co/tensorblock/LLaMA3-iterative-DPO-final-GGUF/tree/main/LLaMA3-iterative-DPO-final-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
|
| 49 |
+
| [LLaMA3-iterative-DPO-final-Q5_K_M.gguf](https://huggingface.co/tensorblock/LLaMA3-iterative-DPO-final-GGUF/tree/main/LLaMA3-iterative-DPO-final-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
|
| 50 |
+
| [LLaMA3-iterative-DPO-final-Q6_K.gguf](https://huggingface.co/tensorblock/LLaMA3-iterative-DPO-final-GGUF/tree/main/LLaMA3-iterative-DPO-final-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
|
| 51 |
+
| [LLaMA3-iterative-DPO-final-Q8_0.gguf](https://huggingface.co/tensorblock/LLaMA3-iterative-DPO-final-GGUF/tree/main/LLaMA3-iterative-DPO-final-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
## Downloading instruction
|
| 55 |
+
|
| 56 |
+
### Command line
|
| 57 |
+
|
| 58 |
+
Firstly, install Huggingface Client
|
| 59 |
+
|
| 60 |
+
```shell
|
| 61 |
+
pip install -U "huggingface_hub[cli]"
|
| 62 |
+
```
|
| 63 |
+
|
| 64 |
+
Then, downoad the individual model file the a local directory
|
| 65 |
+
|
| 66 |
+
```shell
|
| 67 |
+
huggingface-cli download tensorblock/LLaMA3-iterative-DPO-final-GGUF --include "LLaMA3-iterative-DPO-final-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
| 68 |
+
```
|
| 69 |
+
|
| 70 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
| 71 |
+
|
| 72 |
+
```shell
|
| 73 |
+
huggingface-cli download tensorblock/LLaMA3-iterative-DPO-final-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
| 74 |
+
```
|