Hugging Face's logo

tensorblock
/
Chocolatine-3B-Instruct-DPO-v1.2-GGUF

Text Generation
Transformers
GGUF
French
English
french
chocolatine
TensorBlock
GGUF
conversational
Model card Files
xet
 Community
morriszms commited on
Commit
8d5070b
·
verified ·
1 Parent(s): 5065fea

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. Chocolatine-3B-Instruct-DPO-v1.2-Q2_K.gguf +3 -0
  3. Chocolatine-3B-Instruct-DPO-v1.2-Q3_K_L.gguf +3 -0
  4. Chocolatine-3B-Instruct-DPO-v1.2-Q3_K_M.gguf +3 -0
  5. Chocolatine-3B-Instruct-DPO-v1.2-Q3_K_S.gguf +3 -0
  6. Chocolatine-3B-Instruct-DPO-v1.2-Q4_0.gguf +3 -0
  7. Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M.gguf +3 -0
  8. Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_S.gguf +3 -0
  9. Chocolatine-3B-Instruct-DPO-v1.2-Q5_0.gguf +3 -0
  10. Chocolatine-3B-Instruct-DPO-v1.2-Q5_K_M.gguf +3 -0
  11. Chocolatine-3B-Instruct-DPO-v1.2-Q5_K_S.gguf +3 -0
  12. Chocolatine-3B-Instruct-DPO-v1.2-Q6_K.gguf +3 -0
  13. Chocolatine-3B-Instruct-DPO-v1.2-Q8_0.gguf +3 -0
  14. README.md +89 -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
+ Chocolatine-3B-Instruct-DPO-v1.2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Chocolatine-3B-Instruct-DPO-v1.2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Chocolatine-3B-Instruct-DPO-v1.2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Chocolatine-3B-Instruct-DPO-v1.2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Chocolatine-3B-Instruct-DPO-v1.2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Chocolatine-3B-Instruct-DPO-v1.2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Chocolatine-3B-Instruct-DPO-v1.2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Chocolatine-3B-Instruct-DPO-v1.2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Chocolatine-3B-Instruct-DPO-v1.2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Chocolatine-3B-Instruct-DPO-v1.2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Chocolatine-3B-Instruct-DPO-v1.2-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f11ef723945ac739652ba8b9739d0d7d4a15304167c4b7cd617beb91b266c62
3
+ size 1416204352
Chocolatine-3B-Instruct-DPO-v1.2-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2d89573f7f1de4d6bacafde9e15557dd7673e70d117760ae5c2420105ba5b20
3
+ size 2087597632
Chocolatine-3B-Instruct-DPO-v1.2-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:172c95310240c9f6749ec92d543eda64ce2f36358923e0c9f549e7d7be372463
3
+ size 1955477056
Chocolatine-3B-Instruct-DPO-v1.2-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6ae761505bd2879af47a2f156b195c6253da27bd9939b4e48aa728518b1f851
3
+ size 1681798720
Chocolatine-3B-Instruct-DPO-v1.2-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:276655a11f53c5375b45ce143080cdaf9bc13ff39e8539fdc3abf73fbb3e8283
3
+ size 2176177216
Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2caa261079283bb3c2c983c23645d212fd298f282adf66ff4e52f0adc367cefa
3
+ size 2393232448
Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37d6b36f340cdf0295b8668fef6c729d8e637912ee3aceb0bccd6d086ac84553
3
+ size 2188760128
Chocolatine-3B-Instruct-DPO-v1.2-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f79be16996a446b2462b77e00b29a744c32b2a044b081ce95d4dcecae5aa800b
3
+ size 2641474624
Chocolatine-3B-Instruct-DPO-v1.2-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f67781ce92e7c54fc7ef3ee5a015719f8a380f9c17eb96af57b342c10c6619e4
3
+ size 2815276096
Chocolatine-3B-Instruct-DPO-v1.2-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:163c774dbb4044ee8605d3c634fa89004f4bf7435e8dc944e129b85212c2bfa9
3
+ size 2641474624
Chocolatine-3B-Instruct-DPO-v1.2-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88ba1e3b87864fcc5e2bd4c0218c0f8d2e464a8f38af1d9464f77f267810a50e
3
+ size 3135853120
Chocolatine-3B-Instruct-DPO-v1.2-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dcdfd223200a32ae9772ebd286a351ac08eee5efe1ed9349f23af2d615125fc
3
+ size 4061222464
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ language:
5
+ - fr
6
+ - en
7
+ tags:
8
+ - french
9
+ - chocolatine
10
+ - TensorBlock
11
+ - GGUF
12
+ datasets:
13
+ - jpacifico/french-orca-dpo-pairs-revised
14
+ pipeline_tag: text-generation
15
+ base_model: jpacifico/Chocolatine-3B-Instruct-DPO-v1.2
16
+ ---
17
+
18
+ <div style="width: auto; margin-left: auto; margin-right: auto">
19
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
20
+ </div>
21
+ <div style="display: flex; justify-content: space-between; width: 100%;">
22
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
23
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
24
+ 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>
25
+ </p>
26
+ </div>
27
+ </div>
28
+
29
+ ## jpacifico/Chocolatine-3B-Instruct-DPO-v1.2 - GGUF
30
+
31
+ This repo contains GGUF format model files for [jpacifico/Chocolatine-3B-Instruct-DPO-v1.2](https://huggingface.co/jpacifico/Chocolatine-3B-Instruct-DPO-v1.2).
32
+
33
+ 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).
34
+
35
+ <div style="text-align: left; margin: 20px 0;">
36
+ <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;">
37
+ Run them on the TensorBlock client using your local machine ↗
38
+ </a>
39
+ </div>
40
+
41
+ ## Prompt template
42
+
43
+ ```
44
+ <|system|>
45
+ {system_prompt}<|end|>
46
+ <|user|>
47
+ {prompt}<|end|>
48
+ <|assistant|>
49
+ ```
50
+
51
+ ## Model file specification
52
+
53
+ | Filename | Quant type | File Size | Description |
54
+ | -------- | ---------- | --------- | ----------- |
55
+ | [Chocolatine-3B-Instruct-DPO-v1.2-Q2_K.gguf](https://huggingface.co/tensorblock/Chocolatine-3B-Instruct-DPO-v1.2-GGUF/blob/main/Chocolatine-3B-Instruct-DPO-v1.2-Q2_K.gguf) | Q2_K | 1.416 GB | smallest, significant quality loss - not recommended for most purposes |
56
+ | [Chocolatine-3B-Instruct-DPO-v1.2-Q3_K_S.gguf](https://huggingface.co/tensorblock/Chocolatine-3B-Instruct-DPO-v1.2-GGUF/blob/main/Chocolatine-3B-Instruct-DPO-v1.2-Q3_K_S.gguf) | Q3_K_S | 1.682 GB | very small, high quality loss |
57
+ | [Chocolatine-3B-Instruct-DPO-v1.2-Q3_K_M.gguf](https://huggingface.co/tensorblock/Chocolatine-3B-Instruct-DPO-v1.2-GGUF/blob/main/Chocolatine-3B-Instruct-DPO-v1.2-Q3_K_M.gguf) | Q3_K_M | 1.955 GB | very small, high quality loss |
58
+ | [Chocolatine-3B-Instruct-DPO-v1.2-Q3_K_L.gguf](https://huggingface.co/tensorblock/Chocolatine-3B-Instruct-DPO-v1.2-GGUF/blob/main/Chocolatine-3B-Instruct-DPO-v1.2-Q3_K_L.gguf) | Q3_K_L | 2.088 GB | small, substantial quality loss |
59
+ | [Chocolatine-3B-Instruct-DPO-v1.2-Q4_0.gguf](https://huggingface.co/tensorblock/Chocolatine-3B-Instruct-DPO-v1.2-GGUF/blob/main/Chocolatine-3B-Instruct-DPO-v1.2-Q4_0.gguf) | Q4_0 | 2.176 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
60
+ | [Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_S.gguf](https://huggingface.co/tensorblock/Chocolatine-3B-Instruct-DPO-v1.2-GGUF/blob/main/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_S.gguf) | Q4_K_S | 2.189 GB | small, greater quality loss |
61
+ | [Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M.gguf](https://huggingface.co/tensorblock/Chocolatine-3B-Instruct-DPO-v1.2-GGUF/blob/main/Chocolatine-3B-Instruct-DPO-v1.2-Q4_K_M.gguf) | Q4_K_M | 2.393 GB | medium, balanced quality - recommended |
62
+ | [Chocolatine-3B-Instruct-DPO-v1.2-Q5_0.gguf](https://huggingface.co/tensorblock/Chocolatine-3B-Instruct-DPO-v1.2-GGUF/blob/main/Chocolatine-3B-Instruct-DPO-v1.2-Q5_0.gguf) | Q5_0 | 2.641 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
63
+ | [Chocolatine-3B-Instruct-DPO-v1.2-Q5_K_S.gguf](https://huggingface.co/tensorblock/Chocolatine-3B-Instruct-DPO-v1.2-GGUF/blob/main/Chocolatine-3B-Instruct-DPO-v1.2-Q5_K_S.gguf) | Q5_K_S | 2.641 GB | large, low quality loss - recommended |
64
+ | [Chocolatine-3B-Instruct-DPO-v1.2-Q5_K_M.gguf](https://huggingface.co/tensorblock/Chocolatine-3B-Instruct-DPO-v1.2-GGUF/blob/main/Chocolatine-3B-Instruct-DPO-v1.2-Q5_K_M.gguf) | Q5_K_M | 2.815 GB | large, very low quality loss - recommended |
65
+ | [Chocolatine-3B-Instruct-DPO-v1.2-Q6_K.gguf](https://huggingface.co/tensorblock/Chocolatine-3B-Instruct-DPO-v1.2-GGUF/blob/main/Chocolatine-3B-Instruct-DPO-v1.2-Q6_K.gguf) | Q6_K | 3.136 GB | very large, extremely low quality loss |
66
+ | [Chocolatine-3B-Instruct-DPO-v1.2-Q8_0.gguf](https://huggingface.co/tensorblock/Chocolatine-3B-Instruct-DPO-v1.2-GGUF/blob/main/Chocolatine-3B-Instruct-DPO-v1.2-Q8_0.gguf) | Q8_0 | 4.061 GB | very large, extremely low quality loss - not recommended |
67
+
68
+
69
+ ## Downloading instruction
70
+
71
+ ### Command line
72
+
73
+ Firstly, install Huggingface Client
74
+
75
+ ```shell
76
+ pip install -U "huggingface_hub[cli]"
77
+ ```
78
+
79
+ Then, downoad the individual model file the a local directory
80
+
81
+ ```shell
82
+ huggingface-cli download tensorblock/Chocolatine-3B-Instruct-DPO-v1.2-GGUF --include "Chocolatine-3B-Instruct-DPO-v1.2-Q2_K.gguf" --local-dir MY_LOCAL_DIR
83
+ ```
84
+
85
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
86
+
87
+ ```shell
88
+ huggingface-cli download tensorblock/Chocolatine-3B-Instruct-DPO-v1.2-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
89
+ ```