Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- LongWriter-llama3.1-8b-Q2_K.gguf +3 -0
- LongWriter-llama3.1-8b-Q3_K_L.gguf +3 -0
- LongWriter-llama3.1-8b-Q3_K_M.gguf +3 -0
- LongWriter-llama3.1-8b-Q3_K_S.gguf +3 -0
- LongWriter-llama3.1-8b-Q4_0.gguf +3 -0
- LongWriter-llama3.1-8b-Q4_K_M.gguf +3 -0
- LongWriter-llama3.1-8b-Q4_K_S.gguf +3 -0
- LongWriter-llama3.1-8b-Q5_0.gguf +3 -0
- LongWriter-llama3.1-8b-Q5_K_M.gguf +3 -0
- LongWriter-llama3.1-8b-Q5_K_S.gguf +3 -0
- LongWriter-llama3.1-8b-Q6_K.gguf +3 -0
- LongWriter-llama3.1-8b-Q8_0.gguf +3 -0
- README.md +79 -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 |
+
LongWriter-llama3.1-8b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
LongWriter-llama3.1-8b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
LongWriter-llama3.1-8b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
LongWriter-llama3.1-8b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
LongWriter-llama3.1-8b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
LongWriter-llama3.1-8b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
LongWriter-llama3.1-8b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
LongWriter-llama3.1-8b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
LongWriter-llama3.1-8b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
LongWriter-llama3.1-8b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
LongWriter-llama3.1-8b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
LongWriter-llama3.1-8b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
LongWriter-llama3.1-8b-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbd5dd02ddd95d86dac138201f3062ad9c07244d630c1f519a4a779f52649609
|
3 |
+
size 3179131424
|
LongWriter-llama3.1-8b-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e98b149f4a21ed4dd674e23f23a41542bf256729de0ba26a90545b986577d878
|
3 |
+
size 4321956384
|
LongWriter-llama3.1-8b-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7f3df87b7b7c91cb0158a9b71c5514a2d343ef193103dbe1258bcf39d55cb09
|
3 |
+
size 4018917920
|
LongWriter-llama3.1-8b-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:718234a6579c2ced8b8ed0ef0ff414757c616e89a956a635eda46c7a1fecfc0d
|
3 |
+
size 3664499232
|
LongWriter-llama3.1-8b-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6383d81d57fd21840521992cb576a503d0d6754b0fcacf1553c44aa5db5b8bf1
|
3 |
+
size 4661211680
|
LongWriter-llama3.1-8b-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ec9d04303b18b21eb7bc68c25849931526e6b7b1e8a9308b39174a43da5f615
|
3 |
+
size 4920734240
|
LongWriter-llama3.1-8b-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc5cac9f18df373dbfe3baa4cfe7f09bd077e4779e4453989db65b413bb59363
|
3 |
+
size 4692668960
|
LongWriter-llama3.1-8b-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:981991152d006dfa7929e3a9a8fae98ad8949beda3b563f008db461f2a579a49
|
3 |
+
size 5599293984
|
LongWriter-llama3.1-8b-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:283f39e63d33f5f0e3b33e590a21f2755855d65dcb600ad348ac523d675fb1bd
|
3 |
+
size 5732987424
|
LongWriter-llama3.1-8b-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35810a366cb12a697ea33659bc6cdfcad381dd9901f463d8655555cbcac7239f
|
3 |
+
size 5599293984
|
LongWriter-llama3.1-8b-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fa93d414adf93fcd3dfe2cd936929dc4693714196e3758fbd60671d62966e5e
|
3 |
+
size 6596006432
|
LongWriter-llama3.1-8b-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85d6eb22f8489b61aa4f23756a4547467addf7c198c0d8d282f209a1b6f128f2
|
3 |
+
size 8540770848
|
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- zh
|
5 |
+
library_name: transformers
|
6 |
+
tags:
|
7 |
+
- Long Context
|
8 |
+
- chatglm
|
9 |
+
- llama
|
10 |
+
- TensorBlock
|
11 |
+
- GGUF
|
12 |
+
datasets:
|
13 |
+
- THUDM/LongWriter-6k
|
14 |
+
license: llama3.1
|
15 |
+
base_model: THUDM/LongWriter-llama3.1-8b
|
16 |
+
---
|
17 |
+
|
18 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
19 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
20 |
+
</div>
|
21 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
22 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
23 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
24 |
+
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>
|
25 |
+
</p>
|
26 |
+
</div>
|
27 |
+
</div>
|
28 |
+
|
29 |
+
## THUDM/LongWriter-llama3.1-8b - GGUF
|
30 |
+
|
31 |
+
This repo contains GGUF format model files for [THUDM/LongWriter-llama3.1-8b](https://huggingface.co/THUDM/LongWriter-llama3.1-8b).
|
32 |
+
|
33 |
+
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).
|
34 |
+
|
35 |
+
## Prompt template
|
36 |
+
|
37 |
+
```
|
38 |
+
|
39 |
+
```
|
40 |
+
|
41 |
+
## Model file specification
|
42 |
+
|
43 |
+
| Filename | Quant type | File Size | Description |
|
44 |
+
| -------- | ---------- | --------- | ----------- |
|
45 |
+
| [LongWriter-llama3.1-8b-Q2_K.gguf](https://huggingface.co/tensorblock/LongWriter-llama3.1-8b-GGUF/tree/main/LongWriter-llama3.1-8b-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
|
46 |
+
| [LongWriter-llama3.1-8b-Q3_K_S.gguf](https://huggingface.co/tensorblock/LongWriter-llama3.1-8b-GGUF/tree/main/LongWriter-llama3.1-8b-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
|
47 |
+
| [LongWriter-llama3.1-8b-Q3_K_M.gguf](https://huggingface.co/tensorblock/LongWriter-llama3.1-8b-GGUF/tree/main/LongWriter-llama3.1-8b-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
|
48 |
+
| [LongWriter-llama3.1-8b-Q3_K_L.gguf](https://huggingface.co/tensorblock/LongWriter-llama3.1-8b-GGUF/tree/main/LongWriter-llama3.1-8b-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
|
49 |
+
| [LongWriter-llama3.1-8b-Q4_0.gguf](https://huggingface.co/tensorblock/LongWriter-llama3.1-8b-GGUF/tree/main/LongWriter-llama3.1-8b-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
50 |
+
| [LongWriter-llama3.1-8b-Q4_K_S.gguf](https://huggingface.co/tensorblock/LongWriter-llama3.1-8b-GGUF/tree/main/LongWriter-llama3.1-8b-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
|
51 |
+
| [LongWriter-llama3.1-8b-Q4_K_M.gguf](https://huggingface.co/tensorblock/LongWriter-llama3.1-8b-GGUF/tree/main/LongWriter-llama3.1-8b-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
|
52 |
+
| [LongWriter-llama3.1-8b-Q5_0.gguf](https://huggingface.co/tensorblock/LongWriter-llama3.1-8b-GGUF/tree/main/LongWriter-llama3.1-8b-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
53 |
+
| [LongWriter-llama3.1-8b-Q5_K_S.gguf](https://huggingface.co/tensorblock/LongWriter-llama3.1-8b-GGUF/tree/main/LongWriter-llama3.1-8b-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
|
54 |
+
| [LongWriter-llama3.1-8b-Q5_K_M.gguf](https://huggingface.co/tensorblock/LongWriter-llama3.1-8b-GGUF/tree/main/LongWriter-llama3.1-8b-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
|
55 |
+
| [LongWriter-llama3.1-8b-Q6_K.gguf](https://huggingface.co/tensorblock/LongWriter-llama3.1-8b-GGUF/tree/main/LongWriter-llama3.1-8b-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
|
56 |
+
| [LongWriter-llama3.1-8b-Q8_0.gguf](https://huggingface.co/tensorblock/LongWriter-llama3.1-8b-GGUF/tree/main/LongWriter-llama3.1-8b-Q8_0.gguf) | Q8_0 | 7.954 GB | very large, extremely low quality loss - not recommended |
|
57 |
+
|
58 |
+
|
59 |
+
## Downloading instruction
|
60 |
+
|
61 |
+
### Command line
|
62 |
+
|
63 |
+
Firstly, install Huggingface Client
|
64 |
+
|
65 |
+
```shell
|
66 |
+
pip install -U "huggingface_hub[cli]"
|
67 |
+
```
|
68 |
+
|
69 |
+
Then, downoad the individual model file the a local directory
|
70 |
+
|
71 |
+
```shell
|
72 |
+
huggingface-cli download tensorblock/LongWriter-llama3.1-8b-GGUF --include "LongWriter-llama3.1-8b-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
73 |
+
```
|
74 |
+
|
75 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
76 |
+
|
77 |
+
```shell
|
78 |
+
huggingface-cli download tensorblock/LongWriter-llama3.1-8b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
79 |
+
```
|