GGUF
TensorBlock
GGUF
Inference Endpoints
morriszms commited on
Commit
3073f7e
1 Parent(s): 92d1384

Upload folder using huggingface_hub

Browse files
.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
+ Viking-33B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Viking-33B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Viking-33B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Viking-33B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Viking-33B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Viking-33B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Viking-33B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Viking-33B-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Viking-33B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Viking-33B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Viking-33B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Viking-33B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - cerebras/SlimPajama-627B
5
+ - bigcode/starcoderdata
6
+ - mc4
7
+ language:
8
+ - fi
9
+ - en
10
+ - da
11
+ - sv
12
+ - 'no'
13
+ - nn
14
+ - is
15
+ tags:
16
+ - TensorBlock
17
+ - GGUF
18
+ base_model: LumiOpen/Viking-33B
19
+ ---
20
+
21
+ <div style="width: auto; margin-left: auto; margin-right: auto">
22
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
23
+ </div>
24
+ <div style="display: flex; justify-content: space-between; width: 100%;">
25
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
26
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
27
+ 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>
28
+ </p>
29
+ </div>
30
+ </div>
31
+
32
+ ## LumiOpen/Viking-33B - GGUF
33
+
34
+ This repo contains GGUF format model files for [LumiOpen/Viking-33B](https://huggingface.co/LumiOpen/Viking-33B).
35
+
36
+ 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).
37
+
38
+ <div style="text-align: left; margin: 20px 0;">
39
+ <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;">
40
+ Run them on the TensorBlock client using your local machine ↗
41
+ </a>
42
+ </div>
43
+
44
+ ## Prompt template
45
+
46
+ ```
47
+
48
+ ```
49
+
50
+ ## Model file specification
51
+
52
+ | Filename | Quant type | File Size | Description |
53
+ | -------- | ---------- | --------- | ----------- |
54
+ | [Viking-33B-Q2_K.gguf](https://huggingface.co/tensorblock/Viking-33B-GGUF/blob/main/Viking-33B-Q2_K.gguf) | Q2_K | 12.561 GB | smallest, significant quality loss - not recommended for most purposes |
55
+ | [Viking-33B-Q3_K_S.gguf](https://huggingface.co/tensorblock/Viking-33B-GGUF/blob/main/Viking-33B-Q3_K_S.gguf) | Q3_K_S | 14.606 GB | very small, high quality loss |
56
+ | [Viking-33B-Q3_K_M.gguf](https://huggingface.co/tensorblock/Viking-33B-GGUF/blob/main/Viking-33B-Q3_K_M.gguf) | Q3_K_M | 16.191 GB | very small, high quality loss |
57
+ | [Viking-33B-Q3_K_L.gguf](https://huggingface.co/tensorblock/Viking-33B-GGUF/blob/main/Viking-33B-Q3_K_L.gguf) | Q3_K_L | 17.573 GB | small, substantial quality loss |
58
+ | [Viking-33B-Q4_0.gguf](https://huggingface.co/tensorblock/Viking-33B-GGUF/blob/main/Viking-33B-Q4_0.gguf) | Q4_0 | 18.879 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
59
+ | [Viking-33B-Q4_K_S.gguf](https://huggingface.co/tensorblock/Viking-33B-GGUF/blob/main/Viking-33B-Q4_K_S.gguf) | Q4_K_S | 19.012 GB | small, greater quality loss |
60
+ | [Viking-33B-Q4_K_M.gguf](https://huggingface.co/tensorblock/Viking-33B-GGUF/blob/main/Viking-33B-Q4_K_M.gguf) | Q4_K_M | 19.992 GB | medium, balanced quality - recommended |
61
+ | [Viking-33B-Q5_0.gguf](https://huggingface.co/tensorblock/Viking-33B-GGUF/blob/main/Viking-33B-Q5_0.gguf) | Q5_0 | 22.902 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
62
+ | [Viking-33B-Q5_K_S.gguf](https://huggingface.co/tensorblock/Viking-33B-GGUF/blob/main/Viking-33B-Q5_K_S.gguf) | Q5_K_S | 22.902 GB | large, low quality loss - recommended |
63
+ | [Viking-33B-Q5_K_M.gguf](https://huggingface.co/tensorblock/Viking-33B-GGUF/blob/main/Viking-33B-Q5_K_M.gguf) | Q5_K_M | 23.475 GB | large, very low quality loss - recommended |
64
+ | [Viking-33B-Q6_K.gguf](https://huggingface.co/tensorblock/Viking-33B-GGUF/blob/main/Viking-33B-Q6_K.gguf) | Q6_K | 27.175 GB | very large, extremely low quality loss |
65
+ | [Viking-33B-Q8_0.gguf](https://huggingface.co/tensorblock/Viking-33B-GGUF/blob/main/Viking-33B-Q8_0.gguf) | Q8_0 | 35.196 GB | very large, extremely low quality loss - not recommended |
66
+
67
+
68
+ ## Downloading instruction
69
+
70
+ ### Command line
71
+
72
+ Firstly, install Huggingface Client
73
+
74
+ ```shell
75
+ pip install -U "huggingface_hub[cli]"
76
+ ```
77
+
78
+ Then, downoad the individual model file the a local directory
79
+
80
+ ```shell
81
+ huggingface-cli download tensorblock/Viking-33B-GGUF --include "Viking-33B-Q2_K.gguf" --local-dir MY_LOCAL_DIR
82
+ ```
83
+
84
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
85
+
86
+ ```shell
87
+ huggingface-cli download tensorblock/Viking-33B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
88
+ ```
Viking-33B-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a179dd4ba3dd3f7211a8775958fe79d753370ff1d4932de25aaf2778e044c22
3
+ size 12560994336
Viking-33B-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:562e595eb39aae68653922bf7566869695efe9e367f6edf4942b8151a60ef920
3
+ size 17572859936
Viking-33B-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4788b145b1879d5e276e128fb6e221dcd5f1c0b8380221c2a203f4bbf5959064
3
+ size 16191098912
Viking-33B-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5b51be239e4ee92a1d12bada566d88f81d5125e9a7586f84454a145f0e67e06
3
+ size 14605652000
Viking-33B-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc15516eeda11286eecbc094fd5fe4f1408c1f8a7696e6cd714972423fce8fc2
3
+ size 18879385632
Viking-33B-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49469c5baada6bafc398ba562b24b3477d8156fdd6a30b3ecdacc8af30164e13
3
+ size 19992088608
Viking-33B-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4ae1e0f86d5247b6a5d3cb25c73472081019ab6b22b765cc241fa409fd33d5b
3
+ size 19011506208
Viking-33B-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b883d007e9eb0229fd31db619733238a246e04ebead9db33d9c836470ab16f6b
3
+ size 22901723168
Viking-33B-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4225bb46d4ac1e733f6201a36036f304d6e7b8c2c70eff84a7805c514e14b820
3
+ size 23474933792
Viking-33B-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac8ead0889a8a608107f8d5d14f1d3112b262453afb379f939c06d26408d73c5
3
+ size 22901723168
Viking-33B-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9be78ed097ab36e4c830d351bb76498f9c3a6b9535bc88249720e20099aefcc3
3
+ size 27175456800
Viking-33B-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f471d89d4126b732ebe91234895de7012b9bae7404ba53c4a32fa05d3f06dfb
3
+ size 35196276768