bartowski commited on
Commit
004380f
1 Parent(s): a5a72f9

Llamacpp quants

Browse files
.gitattributes CHANGED
@@ -33,3 +33,29 @@ 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
+ dolphin-2.9.3-Yi-1.5-34B-32k-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ dolphin-2.9.3-Yi-1.5-34B-32k-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
38
+ dolphin-2.9.3-Yi-1.5-34B-32k-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
39
+ dolphin-2.9.3-Yi-1.5-34B-32k-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
40
+ dolphin-2.9.3-Yi-1.5-34B-32k-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
41
+ dolphin-2.9.3-Yi-1.5-34B-32k-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
42
+ dolphin-2.9.3-Yi-1.5-34B-32k-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
43
+ dolphin-2.9.3-Yi-1.5-34B-32k-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
44
+ dolphin-2.9.3-Yi-1.5-34B-32k-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
45
+ dolphin-2.9.3-Yi-1.5-34B-32k-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
46
+ dolphin-2.9.3-Yi-1.5-34B-32k-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
47
+ dolphin-2.9.3-Yi-1.5-34B-32k-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
48
+ dolphin-2.9.3-Yi-1.5-34B-32k-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
49
+ dolphin-2.9.3-Yi-1.5-34B-32k-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
50
+ dolphin-2.9.3-Yi-1.5-34B-32k-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
51
+ dolphin-2.9.3-Yi-1.5-34B-32k-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
52
+ dolphin-2.9.3-Yi-1.5-34B-32k-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
53
+ dolphin-2.9.3-Yi-1.5-34B-32k-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
54
+ dolphin-2.9.3-Yi-1.5-34B-32k-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
55
+ dolphin-2.9.3-Yi-1.5-34B-32k-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
56
+ dolphin-2.9.3-Yi-1.5-34B-32k-Q8_0_L.gguf filter=lfs diff=lfs merge=lfs -text
57
+ dolphin-2.9.3-Yi-1.5-34B-32k-f32.gguf/dolphin-2.9.3-Yi-1.5-34B-32k-f32-00001-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
58
+ dolphin-2.9.3-Yi-1.5-34B-32k-f32.gguf/dolphin-2.9.3-Yi-1.5-34B-32k-f32-00002-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
59
+ dolphin-2.9.3-Yi-1.5-34B-32k-f32.gguf/dolphin-2.9.3-Yi-1.5-34B-32k-f32-00003-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
60
+ dolphin-2.9.3-Yi-1.5-34B-32k-f32.gguf/dolphin-2.9.3-Yi-1.5-34B-32k-f32-00004-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
61
+ dolphin-2.9.3-Yi-1.5-34B-32k.imatrix filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: 01-ai/Yi-1.5-34B-32k
4
+ tags:
5
+ - generated_from_trainer
6
+ - axolotl
7
+ datasets:
8
+ - cognitivecomputations/Dolphin-2.9
9
+ - teknium/OpenHermes-2.5
10
+ - m-a-p/CodeFeedback-Filtered-Instruction
11
+ - cognitivecomputations/dolphin-coder
12
+ - cognitivecomputations/samantha-data
13
+ - microsoft/orca-math-word-problems-200k
14
+ - Locutusque/function-calling-chatml
15
+ - internlm/Agent-FLAN
16
+ quantized_by: bartowski
17
+ pipeline_tag: text-generation
18
+ ---
19
+
20
+ ## Llamacpp imatrix Quantizations of dolphin-2.9.3-Yi-1.5-34B-32k
21
+
22
+ Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3197">b3197</a> for quantization.
23
+
24
+ Original model: https://huggingface.co/cognitivecomputations/dolphin-2.9.3-Yi-1.5-34B-32k
25
+
26
+ All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
27
+
28
+ ## Prompt format
29
+
30
+ ```
31
+ <|im_start|> system
32
+ {system_prompt}<|im_end|>
33
+ <|im_start|> user
34
+ {prompt}<|im_end|>
35
+ <|im_start|> assistant
36
+
37
+ ```
38
+
39
+ ## Download a file (not the whole branch) from below:
40
+
41
+ | Filename | Quant type | File Size | Description |
42
+ | -------- | ---------- | --------- | ----------- |
43
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-Q8_0_L.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-Q8_1.gguf) | Q8_0_L | 37.40GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Extremely high quality, generally unneeded but max available quant. |
44
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-Q8_0.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-Q8_0.gguf) | Q8_0 | 36.54GB | Extremely high quality, generally unneeded but max available quant. |
45
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-Q6_K_L.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-Q6_K_L.gguf) | Q6_K_L | 29.29GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Very high quality, near perfect, *recommended*. |
46
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-Q6_K.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-Q6_K.gguf) | Q6_K | 28.21GB | Very high quality, near perfect, *recommended*. |
47
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-Q5_K_L.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-Q5_K_L.gguf) | Q5_K_L | 25.46GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. High quality, *recommended*. |
48
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-Q5_K_M.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-Q5_K_M.gguf) | Q5_K_M | 24.32GB | High quality, *recommended*. |
49
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-Q5_K_S.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-Q5_K_S.gguf) | Q5_K_S | 23.70GB | High quality, *recommended*. |
50
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-Q4_K_L.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-Q4_K_L.gguf) | Q4_K_L | 21.85GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Good quality, uses about 4.83 bits per weight, *recommended*. |
51
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-Q4_K_M.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-Q4_K_M.gguf) | Q4_K_M | 20.65GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
52
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-Q4_K_S.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-Q4_K_S.gguf) | Q4_K_S | 19.59GB | Slightly lower quality with more space savings, *recommended*. |
53
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-IQ4_XS.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-IQ4_XS.gguf) | IQ4_XS | 18.47GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
54
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-Q3_K_XL.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF//main/dolphin-2.9.3-Yi-1.5-34B-32k-Q3_K_XL.gguf) | Q3_K_XL | | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Lower quality but usable, good for low RAM availability. |
55
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-Q3_K_L.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-Q3_K_L.gguf) | Q3_K_L | 18.13GB | Lower quality but usable, good for low RAM availability. |
56
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-Q3_K_M.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-Q3_K_M.gguf) | Q3_K_M | 16.65GB | Even lower quality. |
57
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-IQ3_M.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-IQ3_M.gguf) | IQ3_M | 15.56GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
58
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-Q3_K_S.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-Q3_K_S.gguf) | Q3_K_S | 14.96GB | Low quality, not recommended. |
59
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-IQ3_XS.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-IQ3_XS.gguf) | IQ3_XS | 14.23GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
60
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-IQ3_XXS.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-IQ3_XXS.gguf) | IQ3_XXS | 13.33GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
61
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-Q2_K.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-Q2_K.gguf) | Q2_K | 12.82GB | Very low quality but surprisingly usable. |
62
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-IQ2_M.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-IQ2_M.gguf) | IQ2_M | 11.79GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
63
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-IQ2_S.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-IQ2_S.gguf) | IQ2_S | 10.89GB | Very low quality, uses SOTA techniques to be usable. |
64
+ | [dolphin-2.9.3-Yi-1.5-34B-32k-IQ2_XS.gguf](https://huggingface.co/bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF/blob/main/dolphin-2.9.3-Yi-1.5-34B-32k-IQ2_XS.gguf) | IQ2_XS | 10.30GB | Very low quality, uses SOTA techniques to be usable. |
65
+
66
+ ## Downloading using huggingface-cli
67
+
68
+ First, make sure you have hugginface-cli installed:
69
+
70
+ ```
71
+ pip install -U "huggingface_hub[cli]"
72
+ ```
73
+
74
+ Then, you can target the specific file you want:
75
+
76
+ ```
77
+ huggingface-cli download bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF --include "dolphin-2.9.3-Yi-1.5-34B-32k-Q4_K_M.gguf" --local-dir ./
78
+ ```
79
+
80
+ If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
81
+
82
+ ```
83
+ huggingface-cli download bartowski/dolphin-2.9.3-Yi-1.5-34B-32k-GGUF --include "dolphin-2.9.3-Yi-1.5-34B-32k-Q8_0.gguf/*" --local-dir dolphin-2.9.3-Yi-1.5-34B-32k-Q8_0
84
+ ```
85
+
86
+ You can either specify a new local-dir (dolphin-2.9.3-Yi-1.5-34B-32k-Q8_0) or download them all in place (./)
87
+
88
+ ## Which file should I choose?
89
+
90
+ A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
91
+
92
+ The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
93
+
94
+ If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
95
+
96
+ If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
97
+
98
+ Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
99
+
100
+ If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
101
+
102
+ If you want to get more into the weeds, you can check out this extremely useful feature chart:
103
+
104
+ [llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
105
+
106
+ But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
107
+
108
+ These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
109
+
110
+ The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
111
+
112
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
dolphin-2.9.3-Yi-1.5-34B-32k-IQ2_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f39ed83c6094436ed1a801b608eabf904e834105f4ccc62a49a8a5cabd39c2f9
3
+ size 11794762464
dolphin-2.9.3-Yi-1.5-34B-32k-IQ2_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:286785e950351f038d50fb835df8875ec019f33a0067f7ccf6f1e9e5e4fc2698
3
+ size 10891021024
dolphin-2.9.3-Yi-1.5-34B-32k-IQ2_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:225f8a145ba92039c5e5f0dd6311546e82666577ac5440527d7b294ec2cf3361
3
+ size 10306542304
dolphin-2.9.3-Yi-1.5-34B-32k-IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d38d9363ed86ebd9240231b2779480cca46453d1f2e9e3cca216690c6f23f9
3
+ size 15564700384
dolphin-2.9.3-Yi-1.5-34B-32k-IQ3_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bccf12f742570dee04d174b18a951c3c45b78b4dd2924844dbe1c25b014edbd5
3
+ size 14234319584
dolphin-2.9.3-Yi-1.5-34B-32k-IQ3_XXS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4e9a49f75187e04f6a500da6df727615ef7f6751a53e4e4fdd1cb54a8316084
3
+ size 13333875424
dolphin-2.9.3-Yi-1.5-34B-32k-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aef2797346f1f8ee0bd368182f465ef8aa1336404f7797d38fb7289fcea3f39f
3
+ size 18475051744
dolphin-2.9.3-Yi-1.5-34B-32k-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:663b9433845a2568e1d683262f8c9ccdb0147cad3a7c103bece76268337976eb
3
+ size 12825234144
dolphin-2.9.3-Yi-1.5-34B-32k-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0be2b637c8eaec9b905abc27bd6478f15ba1c5b3bfe43fa7b178333d89de5af1
3
+ size 18139445984
dolphin-2.9.3-Yi-1.5-34B-32k-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fec525bd7ba8f094d00ef76d80e16fdb1d1276cc92a490319fab4b5fd6a1a4d
3
+ size 16654924512
dolphin-2.9.3-Yi-1.5-34B-32k-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ce9a1812bbe8bb4ef73216de711b617b1460536f9ea9a66a513ba1457bfde61
3
+ size 14960294624
dolphin-2.9.3-Yi-1.5-34B-32k-Q4_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f28dadc34dcfcd14e65296256a78b8ce2eb71afc54470a1824e101290e0fd18
3
+ size 21859351264
dolphin-2.9.3-Yi-1.5-34B-32k-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc0926e522298ff14d128ffea612bb1f24f3226ee8a990974efb12e204e1a34
3
+ size 20658711264
dolphin-2.9.3-Yi-1.5-34B-32k-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12bc117c8d2d51930958344cf11b819069eee6014c93d8d416e0e6830f56f3bc
3
+ size 19598650080
dolphin-2.9.3-Yi-1.5-34B-32k-Q5_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a79e7e41fe8677b7607ec5e5285fe12aadee3b0cc2eb5247f647d555d029714
3
+ size 25465141984
dolphin-2.9.3-Yi-1.5-34B-32k-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f5e48ef2ea20922e4a0f9c6e9347e3dfce7c047e6933ddb70d72ff332bd9cee
3
+ size 24321845984
dolphin-2.9.3-Yi-1.5-34B-32k-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ad59c3761d82e1e942e8215edc0bc4104603f4cb3dd7ed082c8bbc6b1849670
3
+ size 23707691744
dolphin-2.9.3-Yi-1.5-34B-32k-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce92e0e6436c0968ac86760decdd78a4bc301e79410d3e88bb90549834b5861b
3
+ size 28213926624
dolphin-2.9.3-Yi-1.5-34B-32k-Q6_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d65ff45f2266f790ec4fc50d014ba720d5762019534676b5fc3e2118f69bfdb
3
+ size 29296294624
dolphin-2.9.3-Yi-1.5-34B-32k-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c59f6c997f5d5fffbd4d2d1bb80a2be71c6cc2f183bc239d702729ae15b49c0
3
+ size 36542282464
dolphin-2.9.3-Yi-1.5-34B-32k-Q8_0_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb2e6def46e2d0c60599a86838cc8b12c410ca768e14f3bf6d4aaae30fd2e4db
3
+ size 37402442464
dolphin-2.9.3-Yi-1.5-34B-32k-f32.gguf/dolphin-2.9.3-Yi-1.5-34B-32k-f32-00001-of-00004.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b96f96eee3a0d97a5907a8058a38ad68a6fae3737167ee3d606add77788ca3b7
3
+ size 39976275840
dolphin-2.9.3-Yi-1.5-34B-32k-f32.gguf/dolphin-2.9.3-Yi-1.5-34B-32k-f32-00002-of-00004.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6df97ba9a45d10a276166d68c1bab48fb6b8a1b5d13c4a25e120182a2ce5493c
3
+ size 39960176160
dolphin-2.9.3-Yi-1.5-34B-32k-f32.gguf/dolphin-2.9.3-Yi-1.5-34B-32k-f32-00003-of-00004.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde6c48ef2efc1f04d40c64fbd7d187e19fced19ee0beec93e2074909e95e7b0
3
+ size 39578437024
dolphin-2.9.3-Yi-1.5-34B-32k-f32.gguf/dolphin-2.9.3-Yi-1.5-34B-32k-f32-00004-of-00004.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0162aba683c8fbea97557143fbe91da091aa3049352df4f60eeeca9dd42ec5c
3
+ size 18042290240
dolphin-2.9.3-Yi-1.5-34B-32k.imatrix ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac23ced2f04bdafb4f678e92f03f084871db01508cd17bc98265e9b58b6004d1
3
+ size 15251079