Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- OLMo-2-0325-32B-Instruct-Q2_K.gguf +3 -0
- OLMo-2-0325-32B-Instruct-Q3_K_L.gguf +3 -0
- OLMo-2-0325-32B-Instruct-Q3_K_M.gguf +3 -0
- OLMo-2-0325-32B-Instruct-Q3_K_S.gguf +3 -0
- OLMo-2-0325-32B-Instruct-Q4_0.gguf +3 -0
- OLMo-2-0325-32B-Instruct-Q4_K_M.gguf +3 -0
- OLMo-2-0325-32B-Instruct-Q4_K_S.gguf +3 -0
- OLMo-2-0325-32B-Instruct-Q5_0.gguf +3 -0
- OLMo-2-0325-32B-Instruct-Q5_K_M.gguf +3 -0
- OLMo-2-0325-32B-Instruct-Q5_K_S.gguf +3 -0
- OLMo-2-0325-32B-Instruct-Q6_K.gguf +3 -0
- OLMo-2-0325-32B-Instruct-Q8_0.gguf +3 -0
- README.md +86 -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 |
+
OLMo-2-0325-32B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
OLMo-2-0325-32B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
OLMo-2-0325-32B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
OLMo-2-0325-32B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
OLMo-2-0325-32B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
OLMo-2-0325-32B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
OLMo-2-0325-32B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
OLMo-2-0325-32B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
OLMo-2-0325-32B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
OLMo-2-0325-32B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
OLMo-2-0325-32B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
OLMo-2-0325-32B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
OLMo-2-0325-32B-Instruct-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8e1e70c7298775013ebcf4b54f8c12ce0aa9230e41f344f240600df156cdf81
|
3 |
+
size 12006375584
|
OLMo-2-0325-32B-Instruct-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8feea5cc1ad855200438c7f03c7478f4af6b8f270439ed76de376500a33844e7
|
3 |
+
size 16913465504
|
OLMo-2-0325-32B-Instruct-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22f1ddcad96a0548b276052e2a1021c55ada6be67030e9cd7c23bb5c38ea7da3
|
3 |
+
size 15601434784
|
OLMo-2-0325-32B-Instruct-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c38add88c260ba4283bc5c2f1071b08217c93d0a7f4d9115ec97f77f1bc8038
|
3 |
+
size 14058717344
|
OLMo-2-0325-32B-Instruct-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84e98a2dc89ba961bf8e5a5a2f37443716adafb0b1a5616869dc7dc872d4b352
|
3 |
+
size 18271453344
|
OLMo-2-0325-32B-Instruct-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a30e61478919048e34b2f06aacf2b2e83aba349cabbe5ca6d32a1a19a8e68305
|
3 |
+
size 19482558624
|
OLMo-2-0325-32B-Instruct-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:294b9435c52ca4e0fd2c2eefb184a96e558d1524cc1c46eb3142ef40c3e5d2a6
|
3 |
+
size 18415632544
|
OLMo-2-0325-32B-Instruct-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52ee67d420c50df3d191482cdfd1ce6e1f0e3bbb715f8697b32ee50eb9c659ea
|
3 |
+
size 22236381344
|
OLMo-2-0325-32B-Instruct-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:230574c952ae05a47be5df2daaf4741cbd600ba696fbeaa80891adfc8521299f
|
3 |
+
size 22860284064
|
OLMo-2-0325-32B-Instruct-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a5cad9968f5aa0458a3853e6c787d0645dd089bf0d209813bbd7c6bbd1e2980
|
3 |
+
size 22236381344
|
OLMo-2-0325-32B-Instruct-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a39f4d0ab6b7e9b8c7ab586946140777dc0688314b3012c1b8be4cc87aaf425
|
3 |
+
size 26449117344
|
OLMo-2-0325-32B-Instruct-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c211e7708164d91c6fa8405b21e98c7276c093c395f6bea6a4df597ef06d945d
|
3 |
+
size 34255601824
|
README.md
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
datasets:
|
6 |
+
- allenai/RLVR-GSM-MATH-IF-Mixed-Constraints
|
7 |
+
base_model: allenai/OLMo-2-0325-32B-Instruct
|
8 |
+
pipeline_tag: text-generation
|
9 |
+
library_name: transformers
|
10 |
+
tags:
|
11 |
+
- TensorBlock
|
12 |
+
- GGUF
|
13 |
+
---
|
14 |
+
|
15 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
16 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
17 |
+
</div>
|
18 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
19 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
20 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
21 |
+
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>
|
22 |
+
</p>
|
23 |
+
</div>
|
24 |
+
</div>
|
25 |
+
|
26 |
+
## allenai/OLMo-2-0325-32B-Instruct - GGUF
|
27 |
+
|
28 |
+
This repo contains GGUF format model files for [allenai/OLMo-2-0325-32B-Instruct](https://huggingface.co/allenai/OLMo-2-0325-32B-Instruct).
|
29 |
+
|
30 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4882](https://github.com/ggml-org/llama.cpp/commit/be7c3034108473beda214fd1d7c98fd6a7a3bdf5).
|
31 |
+
|
32 |
+
<div style="text-align: left; margin: 20px 0;">
|
33 |
+
<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;">
|
34 |
+
Run them on the TensorBlock client using your local machine ↗
|
35 |
+
</a>
|
36 |
+
</div>
|
37 |
+
|
38 |
+
## Prompt template
|
39 |
+
|
40 |
+
```
|
41 |
+
<|system|>
|
42 |
+
{system_prompt}
|
43 |
+
<|user|>
|
44 |
+
{prompt}
|
45 |
+
<|assistant|>
|
46 |
+
```
|
47 |
+
|
48 |
+
## Model file specification
|
49 |
+
|
50 |
+
| Filename | Quant type | File Size | Description |
|
51 |
+
| -------- | ---------- | --------- | ----------- |
|
52 |
+
| [OLMo-2-0325-32B-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/OLMo-2-0325-32B-Instruct-GGUF/blob/main/OLMo-2-0325-32B-Instruct-Q2_K.gguf) | Q2_K | 12.006 GB | smallest, significant quality loss - not recommended for most purposes |
|
53 |
+
| [OLMo-2-0325-32B-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/OLMo-2-0325-32B-Instruct-GGUF/blob/main/OLMo-2-0325-32B-Instruct-Q3_K_S.gguf) | Q3_K_S | 14.059 GB | very small, high quality loss |
|
54 |
+
| [OLMo-2-0325-32B-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/OLMo-2-0325-32B-Instruct-GGUF/blob/main/OLMo-2-0325-32B-Instruct-Q3_K_M.gguf) | Q3_K_M | 15.601 GB | very small, high quality loss |
|
55 |
+
| [OLMo-2-0325-32B-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/OLMo-2-0325-32B-Instruct-GGUF/blob/main/OLMo-2-0325-32B-Instruct-Q3_K_L.gguf) | Q3_K_L | 16.913 GB | small, substantial quality loss |
|
56 |
+
| [OLMo-2-0325-32B-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/OLMo-2-0325-32B-Instruct-GGUF/blob/main/OLMo-2-0325-32B-Instruct-Q4_0.gguf) | Q4_0 | 18.271 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
57 |
+
| [OLMo-2-0325-32B-Instruct-Q4_K_S.gguf](https://huggingface.co/tensorblock/OLMo-2-0325-32B-Instruct-GGUF/blob/main/OLMo-2-0325-32B-Instruct-Q4_K_S.gguf) | Q4_K_S | 18.416 GB | small, greater quality loss |
|
58 |
+
| [OLMo-2-0325-32B-Instruct-Q4_K_M.gguf](https://huggingface.co/tensorblock/OLMo-2-0325-32B-Instruct-GGUF/blob/main/OLMo-2-0325-32B-Instruct-Q4_K_M.gguf) | Q4_K_M | 19.483 GB | medium, balanced quality - recommended |
|
59 |
+
| [OLMo-2-0325-32B-Instruct-Q5_0.gguf](https://huggingface.co/tensorblock/OLMo-2-0325-32B-Instruct-GGUF/blob/main/OLMo-2-0325-32B-Instruct-Q5_0.gguf) | Q5_0 | 22.236 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
60 |
+
| [OLMo-2-0325-32B-Instruct-Q5_K_S.gguf](https://huggingface.co/tensorblock/OLMo-2-0325-32B-Instruct-GGUF/blob/main/OLMo-2-0325-32B-Instruct-Q5_K_S.gguf) | Q5_K_S | 22.236 GB | large, low quality loss - recommended |
|
61 |
+
| [OLMo-2-0325-32B-Instruct-Q5_K_M.gguf](https://huggingface.co/tensorblock/OLMo-2-0325-32B-Instruct-GGUF/blob/main/OLMo-2-0325-32B-Instruct-Q5_K_M.gguf) | Q5_K_M | 22.860 GB | large, very low quality loss - recommended |
|
62 |
+
| [OLMo-2-0325-32B-Instruct-Q6_K.gguf](https://huggingface.co/tensorblock/OLMo-2-0325-32B-Instruct-GGUF/blob/main/OLMo-2-0325-32B-Instruct-Q6_K.gguf) | Q6_K | 26.449 GB | very large, extremely low quality loss |
|
63 |
+
| [OLMo-2-0325-32B-Instruct-Q8_0.gguf](https://huggingface.co/tensorblock/OLMo-2-0325-32B-Instruct-GGUF/blob/main/OLMo-2-0325-32B-Instruct-Q8_0.gguf) | Q8_0 | 34.256 GB | very large, extremely low quality loss - not recommended |
|
64 |
+
|
65 |
+
|
66 |
+
## Downloading instruction
|
67 |
+
|
68 |
+
### Command line
|
69 |
+
|
70 |
+
Firstly, install Huggingface Client
|
71 |
+
|
72 |
+
```shell
|
73 |
+
pip install -U "huggingface_hub[cli]"
|
74 |
+
```
|
75 |
+
|
76 |
+
Then, downoad the individual model file the a local directory
|
77 |
+
|
78 |
+
```shell
|
79 |
+
huggingface-cli download tensorblock/OLMo-2-0325-32B-Instruct-GGUF --include "OLMo-2-0325-32B-Instruct-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
80 |
+
```
|
81 |
+
|
82 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
83 |
+
|
84 |
+
```shell
|
85 |
+
huggingface-cli download tensorblock/OLMo-2-0325-32B-Instruct-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
86 |
+
```
|