Hugging Face's logo

tensorblock
/
BioMistral-7B-DARE-GGUF

Text Generation
Transformers
GGUF
mergekit
Merge
dare
medical
biology
TensorBlock
GGUF
conversational
Model card Files
xet
Community
morriszms commited on
Commit
76a069a
·
verified ·
1 Parent(s): cce0d4c

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +12 -0
  2. BioMistral-7B-DARE-Q2_K.gguf +3 -0
  3. BioMistral-7B-DARE-Q3_K_L.gguf +3 -0
  4. BioMistral-7B-DARE-Q3_K_M.gguf +3 -0
  5. BioMistral-7B-DARE-Q3_K_S.gguf +3 -0
  6. BioMistral-7B-DARE-Q4_0.gguf +3 -0
  7. BioMistral-7B-DARE-Q4_K_M.gguf +3 -0
  8. BioMistral-7B-DARE-Q4_K_S.gguf +3 -0
  9. BioMistral-7B-DARE-Q5_0.gguf +3 -0
  10. BioMistral-7B-DARE-Q5_K_M.gguf +3 -0
  11. BioMistral-7B-DARE-Q5_K_S.gguf +3 -0
  12. BioMistral-7B-DARE-Q6_K.gguf +3 -0
  13. BioMistral-7B-DARE-Q8_0.gguf +3 -0
  14. README.md +94 -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
+ BioMistral-7B-DARE-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ BioMistral-7B-DARE-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ BioMistral-7B-DARE-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ BioMistral-7B-DARE-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ BioMistral-7B-DARE-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ BioMistral-7B-DARE-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ BioMistral-7B-DARE-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ BioMistral-7B-DARE-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ BioMistral-7B-DARE-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ BioMistral-7B-DARE-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ BioMistral-7B-DARE-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ BioMistral-7B-DARE-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
BioMistral-7B-DARE-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e40734b886ccdc2619c958b556f9ede8e9245a32158232ad567535c5d6d13d
3
+ size 2719243712
BioMistral-7B-DARE-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83cd63332d162bc4a62cd8a9a1da92e7d121ed5f0d4515d6e0ca2eff1e518f77
3
+ size 3822026176
BioMistral-7B-DARE-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c42bc3dd634f9589fa9077c962b4a25759ee5d6778b2788c5f1537d7e5cf542
3
+ size 3518987712
BioMistral-7B-DARE-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d739c5b111f68cfb200a3b2fdd9b4f8973f36faf9ce5878ddf9ddf7230f78a49
3
+ size 3164569024
BioMistral-7B-DARE-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d05ca45476ab16fd1ad51d634bb28061b74db50b9bbbfe1092cf9b7923ab9d5
3
+ size 4108918208
BioMistral-7B-DARE-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c57170425d61412055e7cca71aef2414e729293e4bef56b312ea92899355c44
3
+ size 4368440768
BioMistral-7B-DARE-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:001c725695b9090da5d78c19105e90f062bd554156fbb2d5b518dadface48b90
3
+ size 4140375488
BioMistral-7B-DARE-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73dfca1524e34c72376db4fbf7f9a7ba177d5c0112cf257f905de4eb0548678e
3
+ size 4997717440
BioMistral-7B-DARE-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6da35721d9523b890eb9a1e0393af426291441147037b82b03b8b6d7a7a09f50
3
+ size 5131410880
BioMistral-7B-DARE-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ed9b33067de50b7f3348c4a764b1c193f184b166e987509fe9780d7e178424
3
+ size 4997717440
BioMistral-7B-DARE-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efa3fb02e28607254d237daa66428ccbdc4053f07b618d3ce95d96982a66f917
3
+ size 5942066624
BioMistral-7B-DARE-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d03bf3a029587108fc5e1bc38a705187dcc650b6d683721ce3309120ebb97e22
3
+ size 7695859136
README.md ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: BioMistral/BioMistral-7B-DARE
3
+ library_name: transformers
4
+ tags:
5
+ - mergekit
6
+ - merge
7
+ - dare
8
+ - medical
9
+ - biology
10
+ - TensorBlock
11
+ - GGUF
12
+ license: apache-2.0
13
+ datasets:
14
+ - pubmed
15
+ language:
16
+ - en
17
+ - fr
18
+ - nl
19
+ - es
20
+ - it
21
+ - pl
22
+ - ro
23
+ - de
24
+ pipeline_tag: text-generation
25
+ ---
26
+
27
+ <div style="width: auto; margin-left: auto; margin-right: auto">
28
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
29
+ </div>
30
+ <div style="display: flex; justify-content: space-between; width: 100%;">
31
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
32
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
33
+ 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>
34
+ </p>
35
+ </div>
36
+ </div>
37
+
38
+ ## BioMistral/BioMistral-7B-DARE - GGUF
39
+
40
+ This repo contains GGUF format model files for [BioMistral/BioMistral-7B-DARE](https://huggingface.co/BioMistral/BioMistral-7B-DARE).
41
+
42
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
43
+
44
+ <div style="text-align: left; margin: 20px 0;">
45
+ <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;">
46
+ Run them on the TensorBlock client using your local machine ↗
47
+ </a>
48
+ </div>
49
+
50
+ ## Prompt template
51
+
52
+ ```
53
+ <s>[INST] {prompt} [/INST]
54
+ ```
55
+
56
+ ## Model file specification
57
+
58
+ | Filename | Quant type | File Size | Description |
59
+ | -------- | ---------- | --------- | ----------- |
60
+ | [BioMistral-7B-DARE-Q2_K.gguf](https://huggingface.co/tensorblock/BioMistral-7B-DARE-GGUF/blob/main/BioMistral-7B-DARE-Q2_K.gguf) | Q2_K | 2.719 GB | smallest, significant quality loss - not recommended for most purposes |
61
+ | [BioMistral-7B-DARE-Q3_K_S.gguf](https://huggingface.co/tensorblock/BioMistral-7B-DARE-GGUF/blob/main/BioMistral-7B-DARE-Q3_K_S.gguf) | Q3_K_S | 3.165 GB | very small, high quality loss |
62
+ | [BioMistral-7B-DARE-Q3_K_M.gguf](https://huggingface.co/tensorblock/BioMistral-7B-DARE-GGUF/blob/main/BioMistral-7B-DARE-Q3_K_M.gguf) | Q3_K_M | 3.519 GB | very small, high quality loss |
63
+ | [BioMistral-7B-DARE-Q3_K_L.gguf](https://huggingface.co/tensorblock/BioMistral-7B-DARE-GGUF/blob/main/BioMistral-7B-DARE-Q3_K_L.gguf) | Q3_K_L | 3.822 GB | small, substantial quality loss |
64
+ | [BioMistral-7B-DARE-Q4_0.gguf](https://huggingface.co/tensorblock/BioMistral-7B-DARE-GGUF/blob/main/BioMistral-7B-DARE-Q4_0.gguf) | Q4_0 | 4.109 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
65
+ | [BioMistral-7B-DARE-Q4_K_S.gguf](https://huggingface.co/tensorblock/BioMistral-7B-DARE-GGUF/blob/main/BioMistral-7B-DARE-Q4_K_S.gguf) | Q4_K_S | 4.140 GB | small, greater quality loss |
66
+ | [BioMistral-7B-DARE-Q4_K_M.gguf](https://huggingface.co/tensorblock/BioMistral-7B-DARE-GGUF/blob/main/BioMistral-7B-DARE-Q4_K_M.gguf) | Q4_K_M | 4.368 GB | medium, balanced quality - recommended |
67
+ | [BioMistral-7B-DARE-Q5_0.gguf](https://huggingface.co/tensorblock/BioMistral-7B-DARE-GGUF/blob/main/BioMistral-7B-DARE-Q5_0.gguf) | Q5_0 | 4.998 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
68
+ | [BioMistral-7B-DARE-Q5_K_S.gguf](https://huggingface.co/tensorblock/BioMistral-7B-DARE-GGUF/blob/main/BioMistral-7B-DARE-Q5_K_S.gguf) | Q5_K_S | 4.998 GB | large, low quality loss - recommended |
69
+ | [BioMistral-7B-DARE-Q5_K_M.gguf](https://huggingface.co/tensorblock/BioMistral-7B-DARE-GGUF/blob/main/BioMistral-7B-DARE-Q5_K_M.gguf) | Q5_K_M | 5.131 GB | large, very low quality loss - recommended |
70
+ | [BioMistral-7B-DARE-Q6_K.gguf](https://huggingface.co/tensorblock/BioMistral-7B-DARE-GGUF/blob/main/BioMistral-7B-DARE-Q6_K.gguf) | Q6_K | 5.942 GB | very large, extremely low quality loss |
71
+ | [BioMistral-7B-DARE-Q8_0.gguf](https://huggingface.co/tensorblock/BioMistral-7B-DARE-GGUF/blob/main/BioMistral-7B-DARE-Q8_0.gguf) | Q8_0 | 7.696 GB | very large, extremely low quality loss - not recommended |
72
+
73
+
74
+ ## Downloading instruction
75
+
76
+ ### Command line
77
+
78
+ Firstly, install Huggingface Client
79
+
80
+ ```shell
81
+ pip install -U "huggingface_hub[cli]"
82
+ ```
83
+
84
+ Then, downoad the individual model file the a local directory
85
+
86
+ ```shell
87
+ huggingface-cli download tensorblock/BioMistral-7B-DARE-GGUF --include "BioMistral-7B-DARE-Q2_K.gguf" --local-dir MY_LOCAL_DIR
88
+ ```
89
+
90
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
91
+
92
+ ```shell
93
+ huggingface-cli download tensorblock/BioMistral-7B-DARE-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
94
+ ```