bartowski commited on
Commit
28f5190
1 Parent(s): 0a66c86

Llamacpp quants

Browse files
.gitattributes CHANGED
@@ -33,3 +33,19 @@ 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
+ Aethora-7b-V1-e-1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Aethora-7b-V1-e-1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Aethora-7b-V1-e-1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Aethora-7b-V1-e-1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Aethora-7b-V1-e-1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Aethora-7b-V1-e-1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Aethora-7b-V1-e-1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Aethora-7b-V1-e-1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Aethora-7b-V1-e-1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Aethora-7b-V1-e-1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Aethora-7b-V1-e-1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Aethora-7b-V1-e-1-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Aethora-7b-V1-e-1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
49
+ Aethora-7b-V1-e-1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
50
+ Aethora-7b-V1-e-1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
51
+ Aethora-7b-V1-e-1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Aethora-7b-V1-e-1-IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65a11ca01e4a07aabf82a90f77ca310791f9d4ab35545b1fd19353de217b0c2a
3
+ size 3284891872
Aethora-7b-V1-e-1-IQ3_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccb4261ba32681523478c7c9b539c170606a0f27b4be2dcf46f8204118f71f92
3
+ size 3182393568
Aethora-7b-V1-e-1-IQ4_NL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d64204a24033cf95c6e572b2b1cd16808ade31ec177227e9a7cd94ca015b3de4
3
+ size 4155054304
Aethora-7b-V1-e-1-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d56b5cc4a352f8ae3503ed7024c9a33a7251de6b434bd34c21c79f92d206024c
3
+ size 3944388832
Aethora-7b-V1-e-1-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0072867a66c8de7ff90c9f4d862d20888c2ff05e70f1c1fedde93ff1bd135e7d
3
+ size 2719242464
Aethora-7b-V1-e-1-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38e79bcaae84d658ba664d2b225f4f777851e0cbbde0cce4fbc28309c0090771
3
+ size 3822024928
Aethora-7b-V1-e-1-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3782bce72076c13541f2b4e943313113bc071b8f9c602f144ad3e89669abb389
3
+ size 3518986464
Aethora-7b-V1-e-1-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c97e2a99921d2dbcfce27f685bee39f1a66dd223dd9c8cab646474990c5b80bb
3
+ size 3164567776
Aethora-7b-V1-e-1-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8b2328c5299764270398d35720ddf03e7e54bfcef4d0077e5598b09ccc249bd
3
+ size 4108916960
Aethora-7b-V1-e-1-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28d9f45994152891295260e798f2e65c5ef6b319f474841db61281b178102935
3
+ size 4368439520
Aethora-7b-V1-e-1-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4e04691624873ecbff31e3df46f64bc1249c384d442f07032b070395db133c2
3
+ size 4140374240
Aethora-7b-V1-e-1-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57f1e19cc62e5ec2dfee62f0a7025fde8ef943606e379a829233009c1b0bb97d
3
+ size 4997716192
Aethora-7b-V1-e-1-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d0e1229e8abfb73376af2f907bcbec6af6a0f9d4a46b3e7b677a8650e65124
3
+ size 5131409632
Aethora-7b-V1-e-1-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c079864f6e4ab310b79934a9fbab2c32c0df689f89d2ae0d11e6b86796891751
3
+ size 4997716192
Aethora-7b-V1-e-1-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40006dd55f025730a8f39bfe51b421248de6b8eab649d1d5d13b10f7704a263f
3
+ size 5942065376
Aethora-7b-V1-e-1-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a90a6d11da54f5fc38b7a6b0c25650993af4185c732ac4fa4661e12391c6e251
3
+ size 7695857888
README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mistralai/Mistral-7B-Instruct-v0.2
3
+ quantized_by: bartowski
4
+ pipeline_tag: text-generation
5
+ ---
6
+
7
+ ## Llamacpp Quantizations of Aethora-7b-V1-e-1
8
+
9
+ Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2536">b2536</a> for quantization.
10
+
11
+ Original model: https://huggingface.co/TheSkullery/Aethora-7b-V1-e-1
12
+
13
+ Download a file (not the whole branch) from below:
14
+
15
+ | Filename | Quant type | File Size | Description |
16
+ | -------- | ---------- | --------- | ----------- |
17
+ | [Aethora-7b-V1-e-1-Q8_0.gguf](https://huggingface.co/bartowski/Aethora-7b-V1-e-1-GGUF/blob/main/Aethora-7b-V1-e-1-Q8_0.gguf) | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. |
18
+ | [Aethora-7b-V1-e-1-Q6_K.gguf](https://huggingface.co/bartowski/Aethora-7b-V1-e-1-GGUF/blob/main/Aethora-7b-V1-e-1-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. |
19
+ | [Aethora-7b-V1-e-1-Q5_K_M.gguf](https://huggingface.co/bartowski/Aethora-7b-V1-e-1-GGUF/blob/main/Aethora-7b-V1-e-1-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, very usable. |
20
+ | [Aethora-7b-V1-e-1-Q5_K_S.gguf](https://huggingface.co/bartowski/Aethora-7b-V1-e-1-GGUF/blob/main/Aethora-7b-V1-e-1-Q5_K_S.gguf) | Q5_K_S | 4.99GB | High quality, very usable. |
21
+ | [Aethora-7b-V1-e-1-Q5_0.gguf](https://huggingface.co/bartowski/Aethora-7b-V1-e-1-GGUF/blob/main/Aethora-7b-V1-e-1-Q5_0.gguf) | Q5_0 | 4.99GB | High quality, older format, generally not recommended. |
22
+ | [Aethora-7b-V1-e-1-Q4_K_M.gguf](https://huggingface.co/bartowski/Aethora-7b-V1-e-1-GGUF/blob/main/Aethora-7b-V1-e-1-Q4_K_M.gguf) | Q4_K_M | 4.36GB | Good quality, uses about 4.83 bits per weight. |
23
+ | [Aethora-7b-V1-e-1-Q4_K_S.gguf](https://huggingface.co/bartowski/Aethora-7b-V1-e-1-GGUF/blob/main/Aethora-7b-V1-e-1-Q4_K_S.gguf) | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. |
24
+ | [Aethora-7b-V1-e-1-IQ4_NL.gguf](https://huggingface.co/bartowski/Aethora-7b-V1-e-1-GGUF/blob/main/Aethora-7b-V1-e-1-IQ4_NL.gguf) | IQ4_NL | 4.15GB | Decent quality, similar to Q4_K_S, new method of quanting, |
25
+ | [Aethora-7b-V1-e-1-IQ4_XS.gguf](https://huggingface.co/bartowski/Aethora-7b-V1-e-1-GGUF/blob/main/Aethora-7b-V1-e-1-IQ4_XS.gguf) | IQ4_XS | 3.94GB | Decent quality, new method with similar performance to Q4. |
26
+ | [Aethora-7b-V1-e-1-Q4_0.gguf](https://huggingface.co/bartowski/Aethora-7b-V1-e-1-GGUF/blob/main/Aethora-7b-V1-e-1-Q4_0.gguf) | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. |
27
+ | [Aethora-7b-V1-e-1-Q3_K_L.gguf](https://huggingface.co/bartowski/Aethora-7b-V1-e-1-GGUF/blob/main/Aethora-7b-V1-e-1-Q3_K_L.gguf) | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. |
28
+ | [Aethora-7b-V1-e-1-Q3_K_M.gguf](https://huggingface.co/bartowski/Aethora-7b-V1-e-1-GGUF/blob/main/Aethora-7b-V1-e-1-Q3_K_M.gguf) | Q3_K_M | 3.51GB | Even lower quality. |
29
+ | [Aethora-7b-V1-e-1-IQ3_M.gguf](https://huggingface.co/bartowski/Aethora-7b-V1-e-1-GGUF/blob/main/Aethora-7b-V1-e-1-IQ3_M.gguf) | IQ3_M | 3.28GB | Medium-low quality, new method with decent performance. |
30
+ | [Aethora-7b-V1-e-1-IQ3_S.gguf](https://huggingface.co/bartowski/Aethora-7b-V1-e-1-GGUF/blob/main/Aethora-7b-V1-e-1-IQ3_S.gguf) | IQ3_S | 3.18GB | Lower quality, new method with decent performance, recommended over Q3 quants. |
31
+ | [Aethora-7b-V1-e-1-Q3_K_S.gguf](https://huggingface.co/bartowski/Aethora-7b-V1-e-1-GGUF/blob/main/Aethora-7b-V1-e-1-Q3_K_S.gguf) | Q3_K_S | 3.16GB | Low quality, not recommended. |
32
+ | [Aethora-7b-V1-e-1-Q2_K.gguf](https://huggingface.co/bartowski/Aethora-7b-V1-e-1-GGUF/blob/main/Aethora-7b-V1-e-1-Q2_K.gguf) | Q2_K | 2.71GB | Extremely low quality, *not* recommended.
33
+
34
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski