Hugging Face's logo

tensorblock
/
romulus-mistral-nemo-12b-simpo-GGUF

GGUF
Generated from Trainer
TensorBlock
GGUF
Inference Endpoints
conversational
Model card Files Community
morriszms commited on
Commit
af36c27
·
verified ·
1 Parent(s): 190d553

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. README.md +78 -0
  3. romulus-mistral-nemo-12b-simpo-Q2_K.gguf +3 -0
  4. romulus-mistral-nemo-12b-simpo-Q3_K_L.gguf +3 -0
  5. romulus-mistral-nemo-12b-simpo-Q3_K_M.gguf +3 -0
  6. romulus-mistral-nemo-12b-simpo-Q3_K_S.gguf +3 -0
  7. romulus-mistral-nemo-12b-simpo-Q4_0.gguf +3 -0
  8. romulus-mistral-nemo-12b-simpo-Q4_K_M.gguf +3 -0
  9. romulus-mistral-nemo-12b-simpo-Q4_K_S.gguf +3 -0
  10. romulus-mistral-nemo-12b-simpo-Q5_0.gguf +3 -0
  11. romulus-mistral-nemo-12b-simpo-Q5_K_M.gguf +3 -0
  12. romulus-mistral-nemo-12b-simpo-Q5_K_S.gguf +3 -0
  13. romulus-mistral-nemo-12b-simpo-Q6_K.gguf +3 -0
  14. romulus-mistral-nemo-12b-simpo-Q8_0.gguf +3 -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
+ romulus-mistral-nemo-12b-simpo-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ romulus-mistral-nemo-12b-simpo-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ romulus-mistral-nemo-12b-simpo-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ romulus-mistral-nemo-12b-simpo-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ romulus-mistral-nemo-12b-simpo-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ romulus-mistral-nemo-12b-simpo-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ romulus-mistral-nemo-12b-simpo-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ romulus-mistral-nemo-12b-simpo-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ romulus-mistral-nemo-12b-simpo-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ romulus-mistral-nemo-12b-simpo-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ romulus-mistral-nemo-12b-simpo-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ romulus-mistral-nemo-12b-simpo-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: axolotl-ai-co/romulus-mistral-nemo-12b-simpo
3
+ tags:
4
+ - generated_from_trainer
5
+ - TensorBlock
6
+ - GGUF
7
+ license: apache-2.0
8
+ model-index:
9
+ - name: outputs/simpo-out
10
+ results: []
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
+ ## axolotl-ai-co/romulus-mistral-nemo-12b-simpo - GGUF
25
+
26
+ This repo contains GGUF format model files for [axolotl-ai-co/romulus-mistral-nemo-12b-simpo](https://huggingface.co/axolotl-ai-co/romulus-mistral-nemo-12b-simpo).
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
+ ## Prompt template
31
+
32
+ ```
33
+ <|im_start|>system
34
+ {system_prompt}<|im_end|>
35
+ <|im_start|>user
36
+ {prompt}<|im_end|>
37
+ <|im_start|>assistant
38
+ ```
39
+
40
+ ## Model file specification
41
+
42
+ | Filename | Quant type | File Size | Description |
43
+ | -------- | ---------- | --------- | ----------- |
44
+ | [romulus-mistral-nemo-12b-simpo-Q2_K.gguf](https://huggingface.co/tensorblock/romulus-mistral-nemo-12b-simpo-GGUF/tree/main/romulus-mistral-nemo-12b-simpo-Q2_K.gguf) | Q2_K | 4.462 GB | smallest, significant quality loss - not recommended for most purposes |
45
+ | [romulus-mistral-nemo-12b-simpo-Q3_K_S.gguf](https://huggingface.co/tensorblock/romulus-mistral-nemo-12b-simpo-GGUF/tree/main/romulus-mistral-nemo-12b-simpo-Q3_K_S.gguf) | Q3_K_S | 5.154 GB | very small, high quality loss |
46
+ | [romulus-mistral-nemo-12b-simpo-Q3_K_M.gguf](https://huggingface.co/tensorblock/romulus-mistral-nemo-12b-simpo-GGUF/tree/main/romulus-mistral-nemo-12b-simpo-Q3_K_M.gguf) | Q3_K_M | 5.665 GB | very small, high quality loss |
47
+ | [romulus-mistral-nemo-12b-simpo-Q3_K_L.gguf](https://huggingface.co/tensorblock/romulus-mistral-nemo-12b-simpo-GGUF/tree/main/romulus-mistral-nemo-12b-simpo-Q3_K_L.gguf) | Q3_K_L | 6.111 GB | small, substantial quality loss |
48
+ | [romulus-mistral-nemo-12b-simpo-Q4_0.gguf](https://huggingface.co/tensorblock/romulus-mistral-nemo-12b-simpo-GGUF/tree/main/romulus-mistral-nemo-12b-simpo-Q4_0.gguf) | Q4_0 | 6.586 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
49
+ | [romulus-mistral-nemo-12b-simpo-Q4_K_S.gguf](https://huggingface.co/tensorblock/romulus-mistral-nemo-12b-simpo-GGUF/tree/main/romulus-mistral-nemo-12b-simpo-Q4_K_S.gguf) | Q4_K_S | 6.631 GB | small, greater quality loss |
50
+ | [romulus-mistral-nemo-12b-simpo-Q4_K_M.gguf](https://huggingface.co/tensorblock/romulus-mistral-nemo-12b-simpo-GGUF/tree/main/romulus-mistral-nemo-12b-simpo-Q4_K_M.gguf) | Q4_K_M | 6.964 GB | medium, balanced quality - recommended |
51
+ | [romulus-mistral-nemo-12b-simpo-Q5_0.gguf](https://huggingface.co/tensorblock/romulus-mistral-nemo-12b-simpo-GGUF/tree/main/romulus-mistral-nemo-12b-simpo-Q5_0.gguf) | Q5_0 | 7.934 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
52
+ | [romulus-mistral-nemo-12b-simpo-Q5_K_S.gguf](https://huggingface.co/tensorblock/romulus-mistral-nemo-12b-simpo-GGUF/tree/main/romulus-mistral-nemo-12b-simpo-Q5_K_S.gguf) | Q5_K_S | 7.934 GB | large, low quality loss - recommended |
53
+ | [romulus-mistral-nemo-12b-simpo-Q5_K_M.gguf](https://huggingface.co/tensorblock/romulus-mistral-nemo-12b-simpo-GGUF/tree/main/romulus-mistral-nemo-12b-simpo-Q5_K_M.gguf) | Q5_K_M | 8.128 GB | large, very low quality loss - recommended |
54
+ | [romulus-mistral-nemo-12b-simpo-Q6_K.gguf](https://huggingface.co/tensorblock/romulus-mistral-nemo-12b-simpo-GGUF/tree/main/romulus-mistral-nemo-12b-simpo-Q6_K.gguf) | Q6_K | 9.366 GB | very large, extremely low quality loss |
55
+ | [romulus-mistral-nemo-12b-simpo-Q8_0.gguf](https://huggingface.co/tensorblock/romulus-mistral-nemo-12b-simpo-GGUF/tree/main/romulus-mistral-nemo-12b-simpo-Q8_0.gguf) | Q8_0 | 12.128 GB | very large, extremely low quality loss - not recommended |
56
+
57
+
58
+ ## Downloading instruction
59
+
60
+ ### Command line
61
+
62
+ Firstly, install Huggingface Client
63
+
64
+ ```shell
65
+ pip install -U "huggingface_hub[cli]"
66
+ ```
67
+
68
+ Then, downoad the individual model file the a local directory
69
+
70
+ ```shell
71
+ huggingface-cli download tensorblock/romulus-mistral-nemo-12b-simpo-GGUF --include "romulus-mistral-nemo-12b-simpo-Q2_K.gguf" --local-dir MY_LOCAL_DIR
72
+ ```
73
+
74
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
75
+
76
+ ```shell
77
+ huggingface-cli download tensorblock/romulus-mistral-nemo-12b-simpo-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
78
+ ```
romulus-mistral-nemo-12b-simpo-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fc12d26f6bff38c9a9baa174c9a03e80045859d43b14d2c4d2980739e5ecd1f
3
+ size 4791047392
romulus-mistral-nemo-12b-simpo-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bb3ad0649d1a66e38fa2b3cff2bf2cbf46d5bea549db64eac6d1b99aff2b19d
3
+ size 6561502432
romulus-mistral-nemo-12b-simpo-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da249ee56863c9ec311f2a0a67d8be730fc0b2292cc12ab49e4caa63046cdf0e
3
+ size 6083089632
romulus-mistral-nemo-12b-simpo-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3511b2b2f355d7a06e68c2fcebcf56e91e374f059b294a580797334ef71da3a3
3
+ size 5534225632
romulus-mistral-nemo-12b-simpo-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:841e536bdbc2ad090afa0cb0ca940c31ee6d17fb792d6a91a404c49177f28503
3
+ size 7071700192
romulus-mistral-nemo-12b-simpo-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f8fab2a1ce7c56c99eeed929c73543aaad5d04321b103d2aa00b1f01c2555b8
3
+ size 7477204192
romulus-mistral-nemo-12b-simpo-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d650e22f196b5cb471ec1e046fea78811c8081131dbe3d5c74ea72539867a8ba
3
+ size 7120196832
romulus-mistral-nemo-12b-simpo-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a96776042ddd36866ddf44ce40efd6618d7fec3e7d428abdfdba4e0977c5392
3
+ size 8518735072
romulus-mistral-nemo-12b-simpo-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:269fab01e07eb58ac216c7ad349df42b7780f0267403b89636a758054b761019
3
+ size 8727631072
romulus-mistral-nemo-12b-simpo-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1975803d065fa5810795cd55b3fbd9e0feece7e3dff09b497733ef98af744e71
3
+ size 8518735072
romulus-mistral-nemo-12b-simpo-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e7867f0691478e396c98d1385e3914286bbe94c9fb12e9ef4b322b46004262
3
+ size 10056209632
romulus-mistral-nemo-12b-simpo-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:521e6a4fd770d785a4b456362a523681877fea770d9e063e8eee8fb53cd5f16e
3
+ size 13022368992