Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Marco-LLM-AR-V2-Q2_K.gguf +3 -0
- Marco-LLM-AR-V2-Q3_K_L.gguf +3 -0
- Marco-LLM-AR-V2-Q3_K_M.gguf +3 -0
- Marco-LLM-AR-V2-Q3_K_S.gguf +3 -0
- Marco-LLM-AR-V2-Q4_0.gguf +3 -0
- Marco-LLM-AR-V2-Q4_K_M.gguf +3 -0
- Marco-LLM-AR-V2-Q4_K_S.gguf +3 -0
- Marco-LLM-AR-V2-Q5_0.gguf +3 -0
- Marco-LLM-AR-V2-Q5_K_M.gguf +3 -0
- Marco-LLM-AR-V2-Q5_K_S.gguf +3 -0
- Marco-LLM-AR-V2-Q6_K.gguf +3 -0
- Marco-LLM-AR-V2-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 |
+
Marco-LLM-AR-V2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Marco-LLM-AR-V2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Marco-LLM-AR-V2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Marco-LLM-AR-V2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Marco-LLM-AR-V2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Marco-LLM-AR-V2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Marco-LLM-AR-V2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Marco-LLM-AR-V2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Marco-LLM-AR-V2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Marco-LLM-AR-V2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Marco-LLM-AR-V2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Marco-LLM-AR-V2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Marco-LLM-AR-V2-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7732f45464b034f9425b7c0f9cc557deb2731f7c2646a9d6ce8a1d44bdcc1cdc
|
3 |
+
size 3015940096
|
Marco-LLM-AR-V2-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1562d43bc38bd87149d40145fb77cf60ce647e05dd09b2df3a146de75c197b1a
|
3 |
+
size 4088459264
|
Marco-LLM-AR-V2-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6021ba3064b87a4c07ebbb3e2b79dc5738448909e48d66e1fd2f5ab6f64e1d31
|
3 |
+
size 3808391168
|
Marco-LLM-AR-V2-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b9dc79c00bf94c79b0d4607a190ab90732be9a0f2f432f725f3102727f3fc0c
|
3 |
+
size 3492368384
|
Marco-LLM-AR-V2-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:462a29d712314e77e9e1c4be516b520869837cfbe691ae1bb4c42e084116aa48
|
3 |
+
size 4431390720
|
Marco-LLM-AR-V2-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1263f43b43efa22c1cd2696672d0f09c08b3335263c80598d2dd17db8d12b08
|
3 |
+
size 4683073536
|
Marco-LLM-AR-V2-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd06f5b69b1872aee28b49a3cafe5b323af5c10339d2b33a4fcd2b73b50add36
|
3 |
+
size 4457768960
|
Marco-LLM-AR-V2-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4f4173ca956981e88c438664313400b6355d39daf0a9b8c25846c39839ddeb3
|
3 |
+
size 5315176448
|
Marco-LLM-AR-V2-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23025ed52924b69e80e880d7812ac40b6154ec089ab90410cd19b0e7919ca764
|
3 |
+
size 5444831232
|
Marco-LLM-AR-V2-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf938b7a2786667e457f75a2f7b99ec0ce9b0c9241c97418869cb6e2fb4a2457
|
3 |
+
size 5315176448
|
Marco-LLM-AR-V2-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ea12741650a729f5faec959aa2172572fb9ff419476b3e78007b44040acc5a2
|
3 |
+
size 6254198784
|
Marco-LLM-AR-V2-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a2e6b9514e16ded1367888df566bc050318da01319a0f218990994391c192b9
|
3 |
+
size 8098525184
|
README.md
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- ar
|
4 |
+
pipeline_tag: text-generation
|
5 |
+
tags:
|
6 |
+
- pretrained
|
7 |
+
- TensorBlock
|
8 |
+
- GGUF
|
9 |
+
license: apache-2.0
|
10 |
+
base_model: AIDC-AI/Marco-LLM-AR-V2
|
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 |
+
## AIDC-AI/Marco-LLM-AR-V2 - GGUF
|
25 |
+
|
26 |
+
This repo contains GGUF format model files for [AIDC-AI/Marco-LLM-AR-V2](https://huggingface.co/AIDC-AI/Marco-LLM-AR-V2).
|
27 |
+
|
28 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4823](https://github.com/ggml-org/llama.cpp/commit/5bbe6a9fe9a8796a9389c85accec89dbc4d91e39).
|
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 |
+
<|im_start|>system
|
40 |
+
{system_prompt}<|im_end|>
|
41 |
+
<|im_start|>user
|
42 |
+
{prompt}<|im_end|>
|
43 |
+
<|im_start|>assistant
|
44 |
+
```
|
45 |
+
|
46 |
+
## Model file specification
|
47 |
+
|
48 |
+
| Filename | Quant type | File Size | Description |
|
49 |
+
| -------- | ---------- | --------- | ----------- |
|
50 |
+
| [Marco-LLM-AR-V2-Q2_K.gguf](https://huggingface.co/tensorblock/Marco-LLM-AR-V2-GGUF/blob/main/Marco-LLM-AR-V2-Q2_K.gguf) | Q2_K | 3.016 GB | smallest, significant quality loss - not recommended for most purposes |
|
51 |
+
| [Marco-LLM-AR-V2-Q3_K_S.gguf](https://huggingface.co/tensorblock/Marco-LLM-AR-V2-GGUF/blob/main/Marco-LLM-AR-V2-Q3_K_S.gguf) | Q3_K_S | 3.492 GB | very small, high quality loss |
|
52 |
+
| [Marco-LLM-AR-V2-Q3_K_M.gguf](https://huggingface.co/tensorblock/Marco-LLM-AR-V2-GGUF/blob/main/Marco-LLM-AR-V2-Q3_K_M.gguf) | Q3_K_M | 3.808 GB | very small, high quality loss |
|
53 |
+
| [Marco-LLM-AR-V2-Q3_K_L.gguf](https://huggingface.co/tensorblock/Marco-LLM-AR-V2-GGUF/blob/main/Marco-LLM-AR-V2-Q3_K_L.gguf) | Q3_K_L | 4.088 GB | small, substantial quality loss |
|
54 |
+
| [Marco-LLM-AR-V2-Q4_0.gguf](https://huggingface.co/tensorblock/Marco-LLM-AR-V2-GGUF/blob/main/Marco-LLM-AR-V2-Q4_0.gguf) | Q4_0 | 4.431 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
55 |
+
| [Marco-LLM-AR-V2-Q4_K_S.gguf](https://huggingface.co/tensorblock/Marco-LLM-AR-V2-GGUF/blob/main/Marco-LLM-AR-V2-Q4_K_S.gguf) | Q4_K_S | 4.458 GB | small, greater quality loss |
|
56 |
+
| [Marco-LLM-AR-V2-Q4_K_M.gguf](https://huggingface.co/tensorblock/Marco-LLM-AR-V2-GGUF/blob/main/Marco-LLM-AR-V2-Q4_K_M.gguf) | Q4_K_M | 4.683 GB | medium, balanced quality - recommended |
|
57 |
+
| [Marco-LLM-AR-V2-Q5_0.gguf](https://huggingface.co/tensorblock/Marco-LLM-AR-V2-GGUF/blob/main/Marco-LLM-AR-V2-Q5_0.gguf) | Q5_0 | 5.315 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
58 |
+
| [Marco-LLM-AR-V2-Q5_K_S.gguf](https://huggingface.co/tensorblock/Marco-LLM-AR-V2-GGUF/blob/main/Marco-LLM-AR-V2-Q5_K_S.gguf) | Q5_K_S | 5.315 GB | large, low quality loss - recommended |
|
59 |
+
| [Marco-LLM-AR-V2-Q5_K_M.gguf](https://huggingface.co/tensorblock/Marco-LLM-AR-V2-GGUF/blob/main/Marco-LLM-AR-V2-Q5_K_M.gguf) | Q5_K_M | 5.445 GB | large, very low quality loss - recommended |
|
60 |
+
| [Marco-LLM-AR-V2-Q6_K.gguf](https://huggingface.co/tensorblock/Marco-LLM-AR-V2-GGUF/blob/main/Marco-LLM-AR-V2-Q6_K.gguf) | Q6_K | 6.254 GB | very large, extremely low quality loss |
|
61 |
+
| [Marco-LLM-AR-V2-Q8_0.gguf](https://huggingface.co/tensorblock/Marco-LLM-AR-V2-GGUF/blob/main/Marco-LLM-AR-V2-Q8_0.gguf) | Q8_0 | 8.099 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/Marco-LLM-AR-V2-GGUF --include "Marco-LLM-AR-V2-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/Marco-LLM-AR-V2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
84 |
+
```
|