Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Llama-3-Instruct-8B-CPO-v0.2-Q2_K.gguf +3 -0
- Llama-3-Instruct-8B-CPO-v0.2-Q3_K_L.gguf +3 -0
- Llama-3-Instruct-8B-CPO-v0.2-Q3_K_M.gguf +3 -0
- Llama-3-Instruct-8B-CPO-v0.2-Q3_K_S.gguf +3 -0
- Llama-3-Instruct-8B-CPO-v0.2-Q4_0.gguf +3 -0
- Llama-3-Instruct-8B-CPO-v0.2-Q4_K_M.gguf +3 -0
- Llama-3-Instruct-8B-CPO-v0.2-Q4_K_S.gguf +3 -0
- Llama-3-Instruct-8B-CPO-v0.2-Q5_0.gguf +3 -0
- Llama-3-Instruct-8B-CPO-v0.2-Q5_K_M.gguf +3 -0
- Llama-3-Instruct-8B-CPO-v0.2-Q5_K_S.gguf +3 -0
- Llama-3-Instruct-8B-CPO-v0.2-Q6_K.gguf +3 -0
- Llama-3-Instruct-8B-CPO-v0.2-Q8_0.gguf +3 -0
- README.md +73 -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 |
+
Llama-3-Instruct-8B-CPO-v0.2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Llama-3-Instruct-8B-CPO-v0.2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Llama-3-Instruct-8B-CPO-v0.2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Llama-3-Instruct-8B-CPO-v0.2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Llama-3-Instruct-8B-CPO-v0.2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Llama-3-Instruct-8B-CPO-v0.2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Llama-3-Instruct-8B-CPO-v0.2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Llama-3-Instruct-8B-CPO-v0.2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Llama-3-Instruct-8B-CPO-v0.2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Llama-3-Instruct-8B-CPO-v0.2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Llama-3-Instruct-8B-CPO-v0.2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Llama-3-Instruct-8B-CPO-v0.2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Llama-3-Instruct-8B-CPO-v0.2-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4476b488cf644a34d3e89c4045039d1cdb206f7be2639c15f0a56a796624b1ab
|
3 |
+
size 3179131488
|
Llama-3-Instruct-8B-CPO-v0.2-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20e3baa2053f210cdf9006037eaeebad4d15c31af17903258a634db1d9c58f80
|
3 |
+
size 4321956448
|
Llama-3-Instruct-8B-CPO-v0.2-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4ef729775c2cd1be374b1853a0122504abf7c41b14821e8036fc3f95515680d
|
3 |
+
size 4018917984
|
Llama-3-Instruct-8B-CPO-v0.2-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4af2325df5adc48c9da72f71a311f491b21b188145203529b4d4e1457378050b
|
3 |
+
size 3664499296
|
Llama-3-Instruct-8B-CPO-v0.2-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f8a38414e4c42881c4c3aa5dcd0212b11d16cf278bd458760cfb9ee436d9780
|
3 |
+
size 4661211744
|
Llama-3-Instruct-8B-CPO-v0.2-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77253d1220195028d3536ce9623496a8f14ed54fcad03fcf38520079bbaec024
|
3 |
+
size 4920734304
|
Llama-3-Instruct-8B-CPO-v0.2-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7602acb3cb3d5c209a23d31d6f46004345255d5ea4f739e3ac55c9449d3fb45
|
3 |
+
size 4692669024
|
Llama-3-Instruct-8B-CPO-v0.2-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a795c381660dc7616f2628f120b590e1f3e098671b840744d29b29b13e94e306
|
3 |
+
size 5599294048
|
Llama-3-Instruct-8B-CPO-v0.2-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b757831b3fb3e365e92c362cb54bf9063134548c2c6a46bc155798c07df5e3c6
|
3 |
+
size 5732987488
|
Llama-3-Instruct-8B-CPO-v0.2-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2c3d263d94e6f67ccf12da87ce5593e1445cd4ce1fc1f022edd0ad073558f4b
|
3 |
+
size 5599294048
|
Llama-3-Instruct-8B-CPO-v0.2-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e232b93d9c04f8be160ff088a8bc49eb5980649f6d61019a0b3ccd18b2712e72
|
3 |
+
size 6596006496
|
Llama-3-Instruct-8B-CPO-v0.2-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b1a8e0c9e6eb4b23a5394a894d402a0cefc8a816694ec8b095a660dfb99c2cb
|
3 |
+
size 8540770912
|
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: princeton-nlp/Llama-3-Instruct-8B-CPO-v0.2
|
3 |
+
tags:
|
4 |
+
- TensorBlock
|
5 |
+
- GGUF
|
6 |
+
---
|
7 |
+
|
8 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
9 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
10 |
+
</div>
|
11 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
12 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
13 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
14 |
+
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>
|
15 |
+
</p>
|
16 |
+
</div>
|
17 |
+
</div>
|
18 |
+
|
19 |
+
## princeton-nlp/Llama-3-Instruct-8B-CPO-v0.2 - GGUF
|
20 |
+
|
21 |
+
This repo contains GGUF format model files for [princeton-nlp/Llama-3-Instruct-8B-CPO-v0.2](https://huggingface.co/princeton-nlp/Llama-3-Instruct-8B-CPO-v0.2).
|
22 |
+
|
23 |
+
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).
|
24 |
+
|
25 |
+
## Prompt template
|
26 |
+
|
27 |
+
```
|
28 |
+
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
29 |
+
|
30 |
+
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
31 |
+
|
32 |
+
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
33 |
+
```
|
34 |
+
|
35 |
+
## Model file specification
|
36 |
+
|
37 |
+
| Filename | Quant type | File Size | Description |
|
38 |
+
| -------- | ---------- | --------- | ----------- |
|
39 |
+
| [Llama-3-Instruct-8B-CPO-v0.2-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3-Instruct-8B-CPO-v0.2-GGUF/tree/main/Llama-3-Instruct-8B-CPO-v0.2-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
|
40 |
+
| [Llama-3-Instruct-8B-CPO-v0.2-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-Instruct-8B-CPO-v0.2-GGUF/tree/main/Llama-3-Instruct-8B-CPO-v0.2-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
|
41 |
+
| [Llama-3-Instruct-8B-CPO-v0.2-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-Instruct-8B-CPO-v0.2-GGUF/tree/main/Llama-3-Instruct-8B-CPO-v0.2-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
|
42 |
+
| [Llama-3-Instruct-8B-CPO-v0.2-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3-Instruct-8B-CPO-v0.2-GGUF/tree/main/Llama-3-Instruct-8B-CPO-v0.2-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
|
43 |
+
| [Llama-3-Instruct-8B-CPO-v0.2-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3-Instruct-8B-CPO-v0.2-GGUF/tree/main/Llama-3-Instruct-8B-CPO-v0.2-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
44 |
+
| [Llama-3-Instruct-8B-CPO-v0.2-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-Instruct-8B-CPO-v0.2-GGUF/tree/main/Llama-3-Instruct-8B-CPO-v0.2-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
|
45 |
+
| [Llama-3-Instruct-8B-CPO-v0.2-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-Instruct-8B-CPO-v0.2-GGUF/tree/main/Llama-3-Instruct-8B-CPO-v0.2-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
|
46 |
+
| [Llama-3-Instruct-8B-CPO-v0.2-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3-Instruct-8B-CPO-v0.2-GGUF/tree/main/Llama-3-Instruct-8B-CPO-v0.2-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
47 |
+
| [Llama-3-Instruct-8B-CPO-v0.2-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-Instruct-8B-CPO-v0.2-GGUF/tree/main/Llama-3-Instruct-8B-CPO-v0.2-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
|
48 |
+
| [Llama-3-Instruct-8B-CPO-v0.2-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-Instruct-8B-CPO-v0.2-GGUF/tree/main/Llama-3-Instruct-8B-CPO-v0.2-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
|
49 |
+
| [Llama-3-Instruct-8B-CPO-v0.2-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3-Instruct-8B-CPO-v0.2-GGUF/tree/main/Llama-3-Instruct-8B-CPO-v0.2-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
|
50 |
+
| [Llama-3-Instruct-8B-CPO-v0.2-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3-Instruct-8B-CPO-v0.2-GGUF/tree/main/Llama-3-Instruct-8B-CPO-v0.2-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
|
51 |
+
|
52 |
+
|
53 |
+
## Downloading instruction
|
54 |
+
|
55 |
+
### Command line
|
56 |
+
|
57 |
+
Firstly, install Huggingface Client
|
58 |
+
|
59 |
+
```shell
|
60 |
+
pip install -U "huggingface_hub[cli]"
|
61 |
+
```
|
62 |
+
|
63 |
+
Then, downoad the individual model file the a local directory
|
64 |
+
|
65 |
+
```shell
|
66 |
+
huggingface-cli download tensorblock/Llama-3-Instruct-8B-CPO-v0.2-GGUF --include "Llama-3-Instruct-8B-CPO-v0.2-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
67 |
+
```
|
68 |
+
|
69 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
70 |
+
|
71 |
+
```shell
|
72 |
+
huggingface-cli download tensorblock/Llama-3-Instruct-8B-CPO-v0.2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
73 |
+
```
|