Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- AMD-OLMo-1B-SFT-DPO-Q2_K.gguf +3 -0
- AMD-OLMo-1B-SFT-DPO-Q3_K_L.gguf +3 -0
- AMD-OLMo-1B-SFT-DPO-Q3_K_M.gguf +3 -0
- AMD-OLMo-1B-SFT-DPO-Q3_K_S.gguf +3 -0
- AMD-OLMo-1B-SFT-DPO-Q4_0.gguf +3 -0
- AMD-OLMo-1B-SFT-DPO-Q4_K_M.gguf +3 -0
- AMD-OLMo-1B-SFT-DPO-Q4_K_S.gguf +3 -0
- AMD-OLMo-1B-SFT-DPO-Q5_0.gguf +3 -0
- AMD-OLMo-1B-SFT-DPO-Q5_K_M.gguf +3 -0
- AMD-OLMo-1B-SFT-DPO-Q5_K_S.gguf +3 -0
- AMD-OLMo-1B-SFT-DPO-Q6_K.gguf +3 -0
- AMD-OLMo-1B-SFT-DPO-Q8_0.gguf +3 -0
- README.md +84 -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 |
+
AMD-OLMo-1B-SFT-DPO-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
AMD-OLMo-1B-SFT-DPO-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
AMD-OLMo-1B-SFT-DPO-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
AMD-OLMo-1B-SFT-DPO-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
AMD-OLMo-1B-SFT-DPO-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
AMD-OLMo-1B-SFT-DPO-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
AMD-OLMo-1B-SFT-DPO-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
AMD-OLMo-1B-SFT-DPO-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
AMD-OLMo-1B-SFT-DPO-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
AMD-OLMo-1B-SFT-DPO-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
AMD-OLMo-1B-SFT-DPO-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
AMD-OLMo-1B-SFT-DPO-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
AMD-OLMo-1B-SFT-DPO-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:639a01b3d5a74f2cba608910682e36154fba6028dca27e84a27b858efa13a3ec
|
3 |
+
size 479503168
|
AMD-OLMo-1B-SFT-DPO-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04f3e6c1b09807eb09987525437d61c21c42b50979db31033633e6d3475216ec
|
3 |
+
size 651469632
|
AMD-OLMo-1B-SFT-DPO-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dafe9e29ce751ff2a697c7239dcb0ae9746359e5db4fcd012c06cca17e49c1e0
|
3 |
+
size 604283712
|
AMD-OLMo-1B-SFT-DPO-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60dc84c094061163f23f3c7cf54f2030f0c0ab719f4abb03fc4a99299bd4cffc
|
3 |
+
size 547660608
|
AMD-OLMo-1B-SFT-DPO-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eac0b6cf0feb1d1d60a42b6af5ba50a45536ab1990bb0233a081b4f23e8adc6f
|
3 |
+
size 690266944
|
AMD-OLMo-1B-SFT-DPO-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b5235695b5f24a80f4713c5de6b2707fce621423c54dcb9ba48b7f3e9879130
|
3 |
+
size 733520704
|
AMD-OLMo-1B-SFT-DPO-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8f72eccc111562b5273a4484c83c94cc1fe43f80daa6a67e3eee737c6362509
|
3 |
+
size 696558400
|
AMD-OLMo-1B-SFT-DPO-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a88a478e65b0504cc7e60636d572aac02184dae64706dfedb56dd46d1c2ffa90
|
3 |
+
size 824484672
|
AMD-OLMo-1B-SFT-DPO-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b99263b69ab0d74d35192bee630b98a89f40e4daf44224f1ce78f5e48663fa67
|
3 |
+
size 846766912
|
AMD-OLMo-1B-SFT-DPO-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d07e268426505137aa7d70825c12be133c2a81ddd4b12fbf651201eff6d23846
|
3 |
+
size 824484672
|
AMD-OLMo-1B-SFT-DPO-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d7b34ca1228802509f360d1e043389825eb6c002f619a6c75f05faf65cb9b8d
|
3 |
+
size 967091008
|
AMD-OLMo-1B-SFT-DPO-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25b415711446be2f6c7f34e24490ae1f29c86fd37737189bdbef0ecad51b4ad3
|
3 |
+
size 1252088640
|
README.md
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- allenai/dolma
|
5 |
+
pipeline_tag: text-generation
|
6 |
+
library_name: transformers
|
7 |
+
tags:
|
8 |
+
- TensorBlock
|
9 |
+
- GGUF
|
10 |
+
base_model: amd/AMD-OLMo-1B-SFT-DPO
|
11 |
+
---
|
12 |
+
|
13 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
14 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
15 |
+
</div>
|
16 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
17 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
18 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
19 |
+
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>
|
20 |
+
</p>
|
21 |
+
</div>
|
22 |
+
</div>
|
23 |
+
|
24 |
+
## amd/AMD-OLMo-1B-SFT-DPO - GGUF
|
25 |
+
|
26 |
+
This repo contains GGUF format model files for [amd/AMD-OLMo-1B-SFT-DPO](https://huggingface.co/amd/AMD-OLMo-1B-SFT-DPO).
|
27 |
+
|
28 |
+
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).
|
29 |
+
|
30 |
+
<div style="text-align: left; margin: 20px 0;">
|
31 |
+
<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;">
|
32 |
+
Run them on the TensorBlock client using your local machine ↗
|
33 |
+
</a>
|
34 |
+
</div>
|
35 |
+
|
36 |
+
## Prompt template
|
37 |
+
|
38 |
+
```
|
39 |
+
<|system|>
|
40 |
+
{system_prompt}
|
41 |
+
<|user|>
|
42 |
+
{prompt}
|
43 |
+
<|assistant|>
|
44 |
+
```
|
45 |
+
|
46 |
+
## Model file specification
|
47 |
+
|
48 |
+
| Filename | Quant type | File Size | Description |
|
49 |
+
| -------- | ---------- | --------- | ----------- |
|
50 |
+
| [AMD-OLMo-1B-SFT-DPO-Q2_K.gguf](https://huggingface.co/tensorblock/AMD-OLMo-1B-SFT-DPO-GGUF/blob/main/AMD-OLMo-1B-SFT-DPO-Q2_K.gguf) | Q2_K | 0.480 GB | smallest, significant quality loss - not recommended for most purposes |
|
51 |
+
| [AMD-OLMo-1B-SFT-DPO-Q3_K_S.gguf](https://huggingface.co/tensorblock/AMD-OLMo-1B-SFT-DPO-GGUF/blob/main/AMD-OLMo-1B-SFT-DPO-Q3_K_S.gguf) | Q3_K_S | 0.548 GB | very small, high quality loss |
|
52 |
+
| [AMD-OLMo-1B-SFT-DPO-Q3_K_M.gguf](https://huggingface.co/tensorblock/AMD-OLMo-1B-SFT-DPO-GGUF/blob/main/AMD-OLMo-1B-SFT-DPO-Q3_K_M.gguf) | Q3_K_M | 0.604 GB | very small, high quality loss |
|
53 |
+
| [AMD-OLMo-1B-SFT-DPO-Q3_K_L.gguf](https://huggingface.co/tensorblock/AMD-OLMo-1B-SFT-DPO-GGUF/blob/main/AMD-OLMo-1B-SFT-DPO-Q3_K_L.gguf) | Q3_K_L | 0.651 GB | small, substantial quality loss |
|
54 |
+
| [AMD-OLMo-1B-SFT-DPO-Q4_0.gguf](https://huggingface.co/tensorblock/AMD-OLMo-1B-SFT-DPO-GGUF/blob/main/AMD-OLMo-1B-SFT-DPO-Q4_0.gguf) | Q4_0 | 0.690 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
55 |
+
| [AMD-OLMo-1B-SFT-DPO-Q4_K_S.gguf](https://huggingface.co/tensorblock/AMD-OLMo-1B-SFT-DPO-GGUF/blob/main/AMD-OLMo-1B-SFT-DPO-Q4_K_S.gguf) | Q4_K_S | 0.697 GB | small, greater quality loss |
|
56 |
+
| [AMD-OLMo-1B-SFT-DPO-Q4_K_M.gguf](https://huggingface.co/tensorblock/AMD-OLMo-1B-SFT-DPO-GGUF/blob/main/AMD-OLMo-1B-SFT-DPO-Q4_K_M.gguf) | Q4_K_M | 0.734 GB | medium, balanced quality - recommended |
|
57 |
+
| [AMD-OLMo-1B-SFT-DPO-Q5_0.gguf](https://huggingface.co/tensorblock/AMD-OLMo-1B-SFT-DPO-GGUF/blob/main/AMD-OLMo-1B-SFT-DPO-Q5_0.gguf) | Q5_0 | 0.824 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
58 |
+
| [AMD-OLMo-1B-SFT-DPO-Q5_K_S.gguf](https://huggingface.co/tensorblock/AMD-OLMo-1B-SFT-DPO-GGUF/blob/main/AMD-OLMo-1B-SFT-DPO-Q5_K_S.gguf) | Q5_K_S | 0.824 GB | large, low quality loss - recommended |
|
59 |
+
| [AMD-OLMo-1B-SFT-DPO-Q5_K_M.gguf](https://huggingface.co/tensorblock/AMD-OLMo-1B-SFT-DPO-GGUF/blob/main/AMD-OLMo-1B-SFT-DPO-Q5_K_M.gguf) | Q5_K_M | 0.847 GB | large, very low quality loss - recommended |
|
60 |
+
| [AMD-OLMo-1B-SFT-DPO-Q6_K.gguf](https://huggingface.co/tensorblock/AMD-OLMo-1B-SFT-DPO-GGUF/blob/main/AMD-OLMo-1B-SFT-DPO-Q6_K.gguf) | Q6_K | 0.967 GB | very large, extremely low quality loss |
|
61 |
+
| [AMD-OLMo-1B-SFT-DPO-Q8_0.gguf](https://huggingface.co/tensorblock/AMD-OLMo-1B-SFT-DPO-GGUF/blob/main/AMD-OLMo-1B-SFT-DPO-Q8_0.gguf) | Q8_0 | 1.252 GB | very large, extremely low quality loss - not recommended |
|
62 |
+
|
63 |
+
|
64 |
+
## Downloading instruction
|
65 |
+
|
66 |
+
### Command line
|
67 |
+
|
68 |
+
Firstly, install Huggingface Client
|
69 |
+
|
70 |
+
```shell
|
71 |
+
pip install -U "huggingface_hub[cli]"
|
72 |
+
```
|
73 |
+
|
74 |
+
Then, downoad the individual model file the a local directory
|
75 |
+
|
76 |
+
```shell
|
77 |
+
huggingface-cli download tensorblock/AMD-OLMo-1B-SFT-DPO-GGUF --include "AMD-OLMo-1B-SFT-DPO-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
78 |
+
```
|
79 |
+
|
80 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
81 |
+
|
82 |
+
```shell
|
83 |
+
huggingface-cli download tensorblock/AMD-OLMo-1B-SFT-DPO-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
84 |
+
```
|