Hugging Face's logo

tensorblock
/
Moxoff-Phi3Mini-ORPO-GGUF

Transformers
GGUF
English
orpo
phi3
chatml
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
17222f9
•
1 Parent(s): 72d7a89

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. Moxoff-Phi3Mini-ORPO-Q2_K.gguf +3 -0
  3. Moxoff-Phi3Mini-ORPO-Q3_K_L.gguf +3 -0
  4. Moxoff-Phi3Mini-ORPO-Q3_K_M.gguf +3 -0
  5. Moxoff-Phi3Mini-ORPO-Q3_K_S.gguf +3 -0
  6. Moxoff-Phi3Mini-ORPO-Q4_0.gguf +3 -0
  7. Moxoff-Phi3Mini-ORPO-Q4_K_M.gguf +3 -0
  8. Moxoff-Phi3Mini-ORPO-Q4_K_S.gguf +3 -0
  9. Moxoff-Phi3Mini-ORPO-Q5_0.gguf +3 -0
  10. Moxoff-Phi3Mini-ORPO-Q5_K_M.gguf +3 -0
  11. Moxoff-Phi3Mini-ORPO-Q5_K_S.gguf +3 -0
  12. Moxoff-Phi3Mini-ORPO-Q6_K.gguf +3 -0
  13. Moxoff-Phi3Mini-ORPO-Q8_0.gguf +3 -0
  14. README.md +83 -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
+ Moxoff-Phi3Mini-ORPO-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Moxoff-Phi3Mini-ORPO-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Moxoff-Phi3Mini-ORPO-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Moxoff-Phi3Mini-ORPO-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Moxoff-Phi3Mini-ORPO-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Moxoff-Phi3Mini-ORPO-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Moxoff-Phi3Mini-ORPO-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Moxoff-Phi3Mini-ORPO-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Moxoff-Phi3Mini-ORPO-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Moxoff-Phi3Mini-ORPO-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Moxoff-Phi3Mini-ORPO-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Moxoff-Phi3Mini-ORPO-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Moxoff-Phi3Mini-ORPO-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f14c613659330df3cb3af1230f7ee19fca20a9580677b8116e4e9be8d99c29dc
3
+ size 1416015840
Moxoff-Phi3Mini-ORPO-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a0e4b6692d5d13a5ca0ad5325aa60a1b40d19dc53585bc04bb6710759b382f4
3
+ size 2087392576
Moxoff-Phi3Mini-ORPO-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b5d05f6fdc8a53623a932e52541dcfabe657d57dd78cfe3a49059d896d777a3
3
+ size 1955272000
Moxoff-Phi3Mini-ORPO-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbb04cf84d9395d91d603f7c5cacfdb8ba3a01a9f1fdb58df6c2b4c27a1f3222
3
+ size 1681593664
Moxoff-Phi3Mini-ORPO-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a26a902964105a33e1265f09e3a71c2075dc1b842daa22f4d701306c4f34a4b
3
+ size 2175950528
Moxoff-Phi3Mini-ORPO-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e9bc2f576117f160d7841dbedc1de72b668a4a1b04742f6db7b72927da189b3
3
+ size 2393005760
Moxoff-Phi3Mini-ORPO-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93eaffc2f511c12e7b7eddbcd2a259d1ea738b5cb1fe05568cd99a13bd8b2715
3
+ size 2188533440
Moxoff-Phi3Mini-ORPO-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36a10d0362fce9972e7be8057e6a28008645f3923abc6ed51ee4dd2bce8e713c
3
+ size 2641227584
Moxoff-Phi3Mini-ORPO-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a4b2b7a380b3d673dd3eb4414ab310b8887b2e6745a18310d11d89bc5d7649e
3
+ size 2815029056
Moxoff-Phi3Mini-ORPO-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2527ca080494d4489dc41c0f66e1115225f3b437e926d12ddc5e08d9bb256e49
3
+ size 2641227584
Moxoff-Phi3Mini-ORPO-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04ade79725b29bf64366f1cea1eb7b8a4ec3bc38b638b77620fce86bd01ee2cd
3
+ size 3135584480
Moxoff-Phi3Mini-ORPO-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d36d2dc1944c1b693f744959c6fa93d3a83701a73a2698103a39e7f3f59f14e
3
+ size 4060874912
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ language:
4
+ - en
5
+ library_name: transformers
6
+ tags:
7
+ - orpo
8
+ - phi3
9
+ - chatml
10
+ - TensorBlock
11
+ - GGUF
12
+ datasets: argilla/ultrafeedback-binarized-preferences-cleaned
13
+ metrics:
14
+ - hellaswag
15
+ - arc_challenge
16
+ - m_mmlu 5 shot
17
+ base_model: MoxoffSpA/Moxoff-Phi3Mini-ORPO
18
+ ---
19
+
20
+ <div style="width: auto; margin-left: auto; margin-right: auto">
21
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
22
+ </div>
23
+ <div style="display: flex; justify-content: space-between; width: 100%;">
24
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
25
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
26
+ 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>
27
+ </p>
28
+ </div>
29
+ </div>
30
+
31
+ ## MoxoffSpA/Moxoff-Phi3Mini-ORPO - GGUF
32
+
33
+ This repo contains GGUF format model files for [MoxoffSpA/Moxoff-Phi3Mini-ORPO](https://huggingface.co/MoxoffSpA/Moxoff-Phi3Mini-ORPO).
34
+
35
+ 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).
36
+
37
+ ## Prompt template
38
+
39
+ ```
40
+ <s><|user|>
41
+ {prompt}<|end|>
42
+ <|assistant|>
43
+ ```
44
+
45
+ ## Model file specification
46
+
47
+ | Filename | Quant type | File Size | Description |
48
+ | -------- | ---------- | --------- | ----------- |
49
+ | [Moxoff-Phi3Mini-ORPO-Q2_K.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-ORPO-GGUF/tree/main/Moxoff-Phi3Mini-ORPO-Q2_K.gguf) | Q2_K | 1.319 GB | smallest, significant quality loss - not recommended for most purposes |
50
+ | [Moxoff-Phi3Mini-ORPO-Q3_K_S.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-ORPO-GGUF/tree/main/Moxoff-Phi3Mini-ORPO-Q3_K_S.gguf) | Q3_K_S | 1.566 GB | very small, high quality loss |
51
+ | [Moxoff-Phi3Mini-ORPO-Q3_K_M.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-ORPO-GGUF/tree/main/Moxoff-Phi3Mini-ORPO-Q3_K_M.gguf) | Q3_K_M | 1.821 GB | very small, high quality loss |
52
+ | [Moxoff-Phi3Mini-ORPO-Q3_K_L.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-ORPO-GGUF/tree/main/Moxoff-Phi3Mini-ORPO-Q3_K_L.gguf) | Q3_K_L | 1.944 GB | small, substantial quality loss |
53
+ | [Moxoff-Phi3Mini-ORPO-Q4_0.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-ORPO-GGUF/tree/main/Moxoff-Phi3Mini-ORPO-Q4_0.gguf) | Q4_0 | 2.027 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
54
+ | [Moxoff-Phi3Mini-ORPO-Q4_K_S.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-ORPO-GGUF/tree/main/Moxoff-Phi3Mini-ORPO-Q4_K_S.gguf) | Q4_K_S | 2.038 GB | small, greater quality loss |
55
+ | [Moxoff-Phi3Mini-ORPO-Q4_K_M.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-ORPO-GGUF/tree/main/Moxoff-Phi3Mini-ORPO-Q4_K_M.gguf) | Q4_K_M | 2.229 GB | medium, balanced quality - recommended |
56
+ | [Moxoff-Phi3Mini-ORPO-Q5_0.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-ORPO-GGUF/tree/main/Moxoff-Phi3Mini-ORPO-Q5_0.gguf) | Q5_0 | 2.460 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
57
+ | [Moxoff-Phi3Mini-ORPO-Q5_K_S.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-ORPO-GGUF/tree/main/Moxoff-Phi3Mini-ORPO-Q5_K_S.gguf) | Q5_K_S | 2.460 GB | large, low quality loss - recommended |
58
+ | [Moxoff-Phi3Mini-ORPO-Q5_K_M.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-ORPO-GGUF/tree/main/Moxoff-Phi3Mini-ORPO-Q5_K_M.gguf) | Q5_K_M | 2.622 GB | large, very low quality loss - recommended |
59
+ | [Moxoff-Phi3Mini-ORPO-Q6_K.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-ORPO-GGUF/tree/main/Moxoff-Phi3Mini-ORPO-Q6_K.gguf) | Q6_K | 2.920 GB | very large, extremely low quality loss |
60
+ | [Moxoff-Phi3Mini-ORPO-Q8_0.gguf](https://huggingface.co/tensorblock/Moxoff-Phi3Mini-ORPO-GGUF/tree/main/Moxoff-Phi3Mini-ORPO-Q8_0.gguf) | Q8_0 | 3.782 GB | very large, extremely low quality loss - not recommended |
61
+
62
+
63
+ ## Downloading instruction
64
+
65
+ ### Command line
66
+
67
+ Firstly, install Huggingface Client
68
+
69
+ ```shell
70
+ pip install -U "huggingface_hub[cli]"
71
+ ```
72
+
73
+ Then, downoad the individual model file the a local directory
74
+
75
+ ```shell
76
+ huggingface-cli download tensorblock/Moxoff-Phi3Mini-ORPO-GGUF --include "Moxoff-Phi3Mini-ORPO-Q2_K.gguf" --local-dir MY_LOCAL_DIR
77
+ ```
78
+
79
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
80
+
81
+ ```shell
82
+ huggingface-cli download tensorblock/Moxoff-Phi3Mini-ORPO-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
83
+ ```