Upload folder using huggingface_hub
Browse files- .gitattributes +15 -0
- Llama-3-70B-Instruct-Gradient-1048k-Q2_K.gguf +3 -0
- Llama-3-70B-Instruct-Gradient-1048k-Q3_K_L.gguf +3 -0
- Llama-3-70B-Instruct-Gradient-1048k-Q3_K_M.gguf +3 -0
- Llama-3-70B-Instruct-Gradient-1048k-Q3_K_S.gguf +3 -0
- Llama-3-70B-Instruct-Gradient-1048k-Q4_0.gguf +3 -0
- Llama-3-70B-Instruct-Gradient-1048k-Q4_K_M.gguf +3 -0
- Llama-3-70B-Instruct-Gradient-1048k-Q4_K_S.gguf +3 -0
- Llama-3-70B-Instruct-Gradient-1048k-Q5_0.gguf +3 -0
- Llama-3-70B-Instruct-Gradient-1048k-Q5_K_M.gguf +3 -0
- Llama-3-70B-Instruct-Gradient-1048k-Q5_K_S.gguf +3 -0
- Llama-3-70B-Instruct-Gradient-1048k-Q6_K/Llama-3-70B-Instruct-Gradient-1048k-Q6_K-00001-of-00002.gguf +3 -0
- Llama-3-70B-Instruct-Gradient-1048k-Q6_K/Llama-3-70B-Instruct-Gradient-1048k-Q6_K-00002-of-00002.gguf +3 -0
- Llama-3-70B-Instruct-Gradient-1048k-Q8_0/Llama-3-70B-Instruct-Gradient-1048k-Q8_0-00001-of-00003.gguf +3 -0
- Llama-3-70B-Instruct-Gradient-1048k-Q8_0/Llama-3-70B-Instruct-Gradient-1048k-Q8_0-00002-of-00003.gguf +3 -0
- Llama-3-70B-Instruct-Gradient-1048k-Q8_0/Llama-3-70B-Instruct-Gradient-1048k-Q8_0-00003-of-00003.gguf +3 -0
- README.md +85 -0
.gitattributes
CHANGED
@@ -33,3 +33,18 @@ 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-3-70B-Instruct-Gradient-1048k-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Llama-3-70B-Instruct-Gradient-1048k-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Llama-3-70B-Instruct-Gradient-1048k-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Llama-3-70B-Instruct-Gradient-1048k-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Llama-3-70B-Instruct-Gradient-1048k-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Llama-3-70B-Instruct-Gradient-1048k-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Llama-3-70B-Instruct-Gradient-1048k-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Llama-3-70B-Instruct-Gradient-1048k-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Llama-3-70B-Instruct-Gradient-1048k-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Llama-3-70B-Instruct-Gradient-1048k-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Llama-3-70B-Instruct-Gradient-1048k-Q6_K/Llama-3-70B-Instruct-Gradient-1048k-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Llama-3-70B-Instruct-Gradient-1048k-Q6_K/Llama-3-70B-Instruct-Gradient-1048k-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
|
48 |
+
Llama-3-70B-Instruct-Gradient-1048k-Q8_0/Llama-3-70B-Instruct-Gradient-1048k-Q8_0-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
|
49 |
+
Llama-3-70B-Instruct-Gradient-1048k-Q8_0/Llama-3-70B-Instruct-Gradient-1048k-Q8_0-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
|
50 |
+
Llama-3-70B-Instruct-Gradient-1048k-Q8_0/Llama-3-70B-Instruct-Gradient-1048k-Q8_0-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
|
Llama-3-70B-Instruct-Gradient-1048k-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e92c3e8cc2bca2baff8da02bd8d3087906038cd8b25d087929ca582be231827
|
3 |
+
size 26375108544
|
Llama-3-70B-Instruct-Gradient-1048k-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebb14700940f0f168cae3d63f0abd11749c2ab13e0d78146eb0f11717adfcdb7
|
3 |
+
size 37140592576
|
Llama-3-70B-Instruct-Gradient-1048k-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fc8979a530c6d6bc591a7722a7cae770822be7d0a4d32fbcdd0a4b9dc485039
|
3 |
+
size 34267494336
|
Llama-3-70B-Instruct-Gradient-1048k-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:183dc05eac4675fec2e39c2518d78705be38b6723da664c7792ad6188a60f044
|
3 |
+
size 30912051136
|
Llama-3-70B-Instruct-Gradient-1048k-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2c90dc86deb715fe0b1d12f377a2242d63d17ea7b9c2ad7d8b12faaf438324c
|
3 |
+
size 39969732544
|
Llama-3-70B-Instruct-Gradient-1048k-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7abc4f91fcfe3483801420811ab2b9c1c587a4188dd4ae836387fc040f6c7386
|
3 |
+
size 42520393664
|
Llama-3-70B-Instruct-Gradient-1048k-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68e58dfc3275d4106da15e119aae1aac3890f354ece983d045e3776eaa9d7c22
|
3 |
+
size 40347219904
|
Llama-3-70B-Instruct-Gradient-1048k-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d01468705b7c73cce52d719de4ff934006e2f592d95827d18093e5de7a94150e
|
3 |
+
size 48657446848
|
Llama-3-70B-Instruct-Gradient-1048k-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ec3502befe12a0f36830cfb0d3ee77711c3786e5e847dd6a34e03628216bc54
|
3 |
+
size 49949816768
|
Llama-3-70B-Instruct-Gradient-1048k-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba730bcdf9fd2f464e9c96d64c498f2821b7c002f96575e009f92d4c805155de
|
3 |
+
size 48657446848
|
Llama-3-70B-Instruct-Gradient-1048k-Q6_K/Llama-3-70B-Instruct-Gradient-1048k-Q6_K-00001-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eed03773e5d50467821ad302ee352d2c46faa7a6c09ae4bae684a0453ff560c0
|
3 |
+
size 34847470560
|
Llama-3-70B-Instruct-Gradient-1048k-Q6_K/Llama-3-70B-Instruct-Gradient-1048k-Q6_K-00002-of-00002.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0905e1d3fed62eb1bae2ffdb9e067ec51d8c59eaf6aa2a6b8732aec90e45653
|
3 |
+
size 23040672928
|
Llama-3-70B-Instruct-Gradient-1048k-Q8_0/Llama-3-70B-Instruct-Gradient-1048k-Q8_0-00001-of-00003.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bf37687df095844f61bfb58fadb9b1fd1a159900a7828e752b776dcd47e44ca
|
3 |
+
size 34980011008
|
Llama-3-70B-Instruct-Gradient-1048k-Q8_0/Llama-3-70B-Instruct-Gradient-1048k-Q8_0-00002-of-00003.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bc451ab702e58c3109e2511c4201938bfb2a6d9623947d929493946a7e12176
|
3 |
+
size 34949976384
|
Llama-3-70B-Instruct-Gradient-1048k-Q8_0/Llama-3-70B-Instruct-Gradient-1048k-Q8_0-00003-of-00003.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79f4d5078f34093c7e7eccb49ac2500b247bbb7bcb2dbbab3b237c5c07bc8244
|
3 |
+
size 5045062560
|
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
tags:
|
6 |
+
- meta
|
7 |
+
- llama-3
|
8 |
+
- TensorBlock
|
9 |
+
- GGUF
|
10 |
+
license: llama3
|
11 |
+
base_model: gradientai/Llama-3-70B-Instruct-Gradient-1048k
|
12 |
+
---
|
13 |
+
|
14 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
15 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
16 |
+
</div>
|
17 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
18 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
19 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
20 |
+
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>
|
21 |
+
</p>
|
22 |
+
</div>
|
23 |
+
</div>
|
24 |
+
|
25 |
+
## gradientai/Llama-3-70B-Instruct-Gradient-1048k - GGUF
|
26 |
+
|
27 |
+
This repo contains GGUF format model files for [gradientai/Llama-3-70B-Instruct-Gradient-1048k](https://huggingface.co/gradientai/Llama-3-70B-Instruct-Gradient-1048k).
|
28 |
+
|
29 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
|
30 |
+
|
31 |
+
<div style="text-align: left; margin: 20px 0;">
|
32 |
+
<a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
|
33 |
+
Run them on the TensorBlock client using your local machine ↗
|
34 |
+
</a>
|
35 |
+
</div>
|
36 |
+
|
37 |
+
## Prompt template
|
38 |
+
|
39 |
+
```
|
40 |
+
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
41 |
+
|
42 |
+
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
43 |
+
|
44 |
+
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
45 |
+
```
|
46 |
+
|
47 |
+
## Model file specification
|
48 |
+
|
49 |
+
| Filename | Quant type | File Size | Description |
|
50 |
+
| -------- | ---------- | --------- | ----------- |
|
51 |
+
| [Llama-3-70B-Instruct-Gradient-1048k-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Instruct-Gradient-1048k-GGUF/blob/main/Llama-3-70B-Instruct-Gradient-1048k-Q2_K.gguf) | Q2_K | 26.375 GB | smallest, significant quality loss - not recommended for most purposes |
|
52 |
+
| [Llama-3-70B-Instruct-Gradient-1048k-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Instruct-Gradient-1048k-GGUF/blob/main/Llama-3-70B-Instruct-Gradient-1048k-Q3_K_S.gguf) | Q3_K_S | 30.912 GB | very small, high quality loss |
|
53 |
+
| [Llama-3-70B-Instruct-Gradient-1048k-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Instruct-Gradient-1048k-GGUF/blob/main/Llama-3-70B-Instruct-Gradient-1048k-Q3_K_M.gguf) | Q3_K_M | 34.267 GB | very small, high quality loss |
|
54 |
+
| [Llama-3-70B-Instruct-Gradient-1048k-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Instruct-Gradient-1048k-GGUF/blob/main/Llama-3-70B-Instruct-Gradient-1048k-Q3_K_L.gguf) | Q3_K_L | 37.141 GB | small, substantial quality loss |
|
55 |
+
| [Llama-3-70B-Instruct-Gradient-1048k-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Instruct-Gradient-1048k-GGUF/blob/main/Llama-3-70B-Instruct-Gradient-1048k-Q4_0.gguf) | Q4_0 | 39.970 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
56 |
+
| [Llama-3-70B-Instruct-Gradient-1048k-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Instruct-Gradient-1048k-GGUF/blob/main/Llama-3-70B-Instruct-Gradient-1048k-Q4_K_S.gguf) | Q4_K_S | 40.347 GB | small, greater quality loss |
|
57 |
+
| [Llama-3-70B-Instruct-Gradient-1048k-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Instruct-Gradient-1048k-GGUF/blob/main/Llama-3-70B-Instruct-Gradient-1048k-Q4_K_M.gguf) | Q4_K_M | 42.520 GB | medium, balanced quality - recommended |
|
58 |
+
| [Llama-3-70B-Instruct-Gradient-1048k-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Instruct-Gradient-1048k-GGUF/blob/main/Llama-3-70B-Instruct-Gradient-1048k-Q5_0.gguf) | Q5_0 | 48.657 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
59 |
+
| [Llama-3-70B-Instruct-Gradient-1048k-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Instruct-Gradient-1048k-GGUF/blob/main/Llama-3-70B-Instruct-Gradient-1048k-Q5_K_S.gguf) | Q5_K_S | 48.657 GB | large, low quality loss - recommended |
|
60 |
+
| [Llama-3-70B-Instruct-Gradient-1048k-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3-70B-Instruct-Gradient-1048k-GGUF/blob/main/Llama-3-70B-Instruct-Gradient-1048k-Q5_K_M.gguf) | Q5_K_M | 49.950 GB | large, very low quality loss - recommended |
|
61 |
+
| [Llama-3-70B-Instruct-Gradient-1048k-Q6_K](https://huggingface.co/tensorblock/Llama-3-70B-Instruct-Gradient-1048k-GGUF/blob/main/Llama-3-70B-Instruct-Gradient-1048k-Q6_K) | Q6_K | 57.888 GB | very large, extremely low quality loss |
|
62 |
+
| [Llama-3-70B-Instruct-Gradient-1048k-Q8_0](https://huggingface.co/tensorblock/Llama-3-70B-Instruct-Gradient-1048k-GGUF/blob/main/Llama-3-70B-Instruct-Gradient-1048k-Q8_0) | Q8_0 | 74.975 GB | very large, extremely low quality loss - not recommended |
|
63 |
+
|
64 |
+
|
65 |
+
## Downloading instruction
|
66 |
+
|
67 |
+
### Command line
|
68 |
+
|
69 |
+
Firstly, install Huggingface Client
|
70 |
+
|
71 |
+
```shell
|
72 |
+
pip install -U "huggingface_hub[cli]"
|
73 |
+
```
|
74 |
+
|
75 |
+
Then, downoad the individual model file the a local directory
|
76 |
+
|
77 |
+
```shell
|
78 |
+
huggingface-cli download tensorblock/Llama-3-70B-Instruct-Gradient-1048k-GGUF --include "Llama-3-70B-Instruct-Gradient-1048k-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
79 |
+
```
|
80 |
+
|
81 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
82 |
+
|
83 |
+
```shell
|
84 |
+
huggingface-cli download tensorblock/Llama-3-70B-Instruct-Gradient-1048k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
85 |
+
```
|