Llamacpp quants
Browse files- .gitattributes +16 -0
- README.md +42 -0
- blossom-v5-9b-IQ3_M.gguf +3 -0
- blossom-v5-9b-IQ3_S.gguf +3 -0
- blossom-v5-9b-IQ4_NL.gguf +3 -0
- blossom-v5-9b-IQ4_XS.gguf +3 -0
- blossom-v5-9b-Q2_K.gguf +3 -0
- blossom-v5-9b-Q3_K_L.gguf +3 -0
- blossom-v5-9b-Q3_K_M.gguf +3 -0
- blossom-v5-9b-Q3_K_S.gguf +3 -0
- blossom-v5-9b-Q4_0.gguf +3 -0
- blossom-v5-9b-Q4_K_M.gguf +3 -0
- blossom-v5-9b-Q4_K_S.gguf +3 -0
- blossom-v5-9b-Q5_0.gguf +3 -0
- blossom-v5-9b-Q5_K_M.gguf +3 -0
- blossom-v5-9b-Q5_K_S.gguf +3 -0
- blossom-v5-9b-Q6_K.gguf +3 -0
- blossom-v5-9b-Q8_0.gguf +3 -0
.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 |
+
blossom-v5-9b-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
blossom-v5-9b-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
blossom-v5-9b-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
blossom-v5-9b-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
blossom-v5-9b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
blossom-v5-9b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
blossom-v5-9b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
blossom-v5-9b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
blossom-v5-9b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
blossom-v5-9b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
blossom-v5-9b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
blossom-v5-9b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
48 |
+
blossom-v5-9b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
49 |
+
blossom-v5-9b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
50 |
+
blossom-v5-9b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
51 |
+
blossom-v5-9b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- Azure99/blossom-chat-v3
|
5 |
+
- Azure99/blossom-math-v4
|
6 |
+
- Azure99/blossom-wizard-v3
|
7 |
+
- Azure99/blossom-orca-v3
|
8 |
+
language:
|
9 |
+
- zh
|
10 |
+
- en
|
11 |
+
quantized_by: bartowski
|
12 |
+
pipeline_tag: text-generation
|
13 |
+
---
|
14 |
+
|
15 |
+
## Llamacpp Quantizations of blossom-v5-9b
|
16 |
+
|
17 |
+
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2440">b2440</a> for quantization.
|
18 |
+
|
19 |
+
Original model: https://huggingface.co/Azure99/blossom-v5-9b
|
20 |
+
|
21 |
+
Download a file (not the whole branch) from below:
|
22 |
+
|
23 |
+
| Filename | Quant type | File Size | Description |
|
24 |
+
| -------- | ---------- | --------- | ----------- |
|
25 |
+
| [blossom-v5-9b-Q8_0.gguf](https://huggingface.co/bartowski/blossom-v5-9b-GGUF/blob/main/blossom-v5-9b-Q8_0.gguf) | Q8_0 | 9.38GB | Extremely high quality, generally unneeded but max available quant. |
|
26 |
+
| [blossom-v5-9b-Q6_K.gguf](https://huggingface.co/bartowski/blossom-v5-9b-GGUF/blob/main/blossom-v5-9b-Q6_K.gguf) | Q6_K | 7.24GB | Very high quality, near perfect, *recommended*. |
|
27 |
+
| [blossom-v5-9b-Q5_K_M.gguf](https://huggingface.co/bartowski/blossom-v5-9b-GGUF/blob/main/blossom-v5-9b-Q5_K_M.gguf) | Q5_K_M | 6.25GB | High quality, very usable. |
|
28 |
+
| [blossom-v5-9b-Q5_K_S.gguf](https://huggingface.co/bartowski/blossom-v5-9b-GGUF/blob/main/blossom-v5-9b-Q5_K_S.gguf) | Q5_K_S | 6.10GB | High quality, very usable. |
|
29 |
+
| [blossom-v5-9b-Q5_0.gguf](https://huggingface.co/bartowski/blossom-v5-9b-GGUF/blob/main/blossom-v5-9b-Q5_0.gguf) | Q5_0 | 6.10GB | High quality, older format, generally not recommended. |
|
30 |
+
| [blossom-v5-9b-Q4_K_M.gguf](https://huggingface.co/bartowski/blossom-v5-9b-GGUF/blob/main/blossom-v5-9b-Q4_K_M.gguf) | Q4_K_M | 5.32GB | Good quality, similar to 4.25 bpw. |
|
31 |
+
| [blossom-v5-9b-Q4_K_S.gguf](https://huggingface.co/bartowski/blossom-v5-9b-GGUF/blob/main/blossom-v5-9b-Q4_K_S.gguf) | Q4_K_S | 5.07GB | Slightly lower quality with small space savings. |
|
32 |
+
| [blossom-v5-9b-IQ4_NL.gguf](https://huggingface.co/bartowski/blossom-v5-9b-GGUF/blob/main/blossom-v5-9b-IQ4_NL.gguf) | IQ4_NL | 5.08GB | Good quality, similar to Q4_K_S, new method of quanting, |
|
33 |
+
| [blossom-v5-9b-IQ4_XS.gguf](https://huggingface.co/bartowski/blossom-v5-9b-GGUF/blob/main/blossom-v5-9b-IQ4_XS.gguf) | IQ4_XS | 4.82GB | Decent quality, new method with similar performance to Q4. |
|
34 |
+
| [blossom-v5-9b-Q4_0.gguf](https://huggingface.co/bartowski/blossom-v5-9b-GGUF/blob/main/blossom-v5-9b-Q4_0.gguf) | Q4_0 | 5.03GB | Decent quality, older format, generally not recommended. |
|
35 |
+
| [blossom-v5-9b-IQ3_M.gguf](https://huggingface.co/bartowski/blossom-v5-9b-GGUF/blob/main/blossom-v5-9b-IQ3_M.gguf) | IQ3_M | 4.05GB | Medium-low quality, new method with decent performance. |
|
36 |
+
| [blossom-v5-9b-IQ3_S.gguf](https://huggingface.co/bartowski/blossom-v5-9b-GGUF/blob/main/blossom-v5-9b-IQ3_S.gguf) | IQ3_S | 3.91GB | Lower quality, new method with decent performance, recommended over Q3 quants. |
|
37 |
+
| [blossom-v5-9b-Q3_K_L.gguf](https://huggingface.co/bartowski/blossom-v5-9b-GGUF/blob/main/blossom-v5-9b-Q3_K_L.gguf) | Q3_K_L | 4.69GB | Lower quality but usable, good for low RAM availability. |
|
38 |
+
| [blossom-v5-9b-Q3_K_M.gguf](https://huggingface.co/bartowski/blossom-v5-9b-GGUF/blob/main/blossom-v5-9b-Q3_K_M.gguf) | Q3_K_M | 4.32GB | Even lower quality. |
|
39 |
+
| [blossom-v5-9b-Q3_K_S.gguf](https://huggingface.co/bartowski/blossom-v5-9b-GGUF/blob/main/blossom-v5-9b-Q3_K_S.gguf) | Q3_K_S | 3.89GB | Low quality, not recommended. |
|
40 |
+
| [blossom-v5-9b-Q2_K.gguf](https://huggingface.co/bartowski/blossom-v5-9b-GGUF/blob/main/blossom-v5-9b-Q2_K.gguf) | Q2_K | 3.35GB | Extremely low quality, *not* recommended.
|
41 |
+
|
42 |
+
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
blossom-v5-9b-IQ3_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b1c5a25f3724e1dc733d54f47b10fdd9cb5bc230e980be2677003bcb7a87777
|
3 |
+
size 4055461664
|
blossom-v5-9b-IQ3_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9e36a8f5031313190006088bde5132afa7a90de88f9354e1f587199f47052c4
|
3 |
+
size 3912576800
|
blossom-v5-9b-IQ4_NL.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae5190014c6ec400f79bf0b66f71284740bc87d30147ece524c45d40e6624e8c
|
3 |
+
size 5083393824
|
blossom-v5-9b-IQ4_XS.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63ed706869c0b81bb490cf160adb4ca7c8b7a449d07f9e7c0d7f6cfeef0e1218
|
3 |
+
size 4827279136
|
blossom-v5-9b-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27ae54d9c8b03120c639f1a8cb341dec16c19cccdb9403ea5a67015aff5b474f
|
3 |
+
size 3354324768
|
blossom-v5-9b-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:932e6a81ac8104c9b7bc114fdec6eacf38128373a89a4a3166f20c1a155fb846
|
3 |
+
size 4690751264
|
blossom-v5-9b-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31751a4bb0841ce39cebae5570bc35c5aca93260ac51aa097a0e253ac7d07d92
|
3 |
+
size 4324405024
|
blossom-v5-9b-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:160bb095bb117283fa916793c1b78c5a83af5f82ba1b21c825b6c997aed52f3e
|
3 |
+
size 3899207456
|
blossom-v5-9b-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d2733530a04eddc824635329b75531dca3b35b1e5879bf832f8fee6961c0a0e
|
3 |
+
size 5036994336
|
blossom-v5-9b-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7189c08b811204733dd346384145f1efd985d2fc2e324fd6cdf18ce453dd4846
|
3 |
+
size 5328957216
|
blossom-v5-9b-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52c374ba5ec96257d763c4dfb62a181f467e55483f56c83f1316600de79d4e73
|
3 |
+
size 5071859488
|
blossom-v5-9b-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e458e309fcb511aa6e4d4f6b73e3d2dcdfd0f059dac1073f6fae93159dd8024f
|
3 |
+
size 6107852576
|
blossom-v5-9b-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d53a33a116a37eafbafa5ed4503e1d168cb7d090ec82499422ef82e0657655e
|
3 |
+
size 6258257696
|
blossom-v5-9b-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2694c70280b2b5f0cc81b39e217d35923a13dac75527e69bdf808e5dce5aa609
|
3 |
+
size 6107852576
|
blossom-v5-9b-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae0309afdbe9d38bf373181fb0267dcb7cdc07f3a710fb444050d6117f14e311
|
3 |
+
size 7245639456
|
blossom-v5-9b-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a101dfc70475930c199c2b025e8ef71d99d98ef0091a1d0365628c99345c2e40
|
3 |
+
size 9383915296
|