Llamacpp quants
Browse files- .gitattributes +12 -0
- README.md +46 -0
- airoboros-34b-3.2-Q2_K.gguf +3 -0
- airoboros-34b-3.2-Q3_K_L.gguf +3 -0
- airoboros-34b-3.2-Q3_K_M.gguf +3 -0
- airoboros-34b-3.2-Q3_K_S.gguf +3 -0
- airoboros-34b-3.2-Q4_0.gguf +3 -0
- airoboros-34b-3.2-Q4_K_M.gguf +3 -0
- airoboros-34b-3.2-Q4_K_S.gguf +3 -0
- airoboros-34b-3.2-Q5_0.gguf +3 -0
- airoboros-34b-3.2-Q5_K_M.gguf +3 -0
- airoboros-34b-3.2-Q5_K_S.gguf +3 -0
- airoboros-34b-3.2-Q6_K.gguf +3 -0
- airoboros-34b-3.2-Q8_0.gguf +3 -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 |
+
airoboros-34b-3.2-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
airoboros-34b-3.2-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
airoboros-34b-3.2-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
airoboros-34b-3.2-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
airoboros-34b-3.2-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
airoboros-34b-3.2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
airoboros-34b-3.2-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
airoboros-34b-3.2-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
airoboros-34b-3.2-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
airoboros-34b-3.2-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
airoboros-34b-3.2-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
airoboros-34b-3.2-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
license_name: yi-license
|
4 |
+
license_link: https://huggingface.co/01-ai/Yi-34B-200K/blob/main/LICENSE
|
5 |
+
base_model: 01-ai/yi-34b-200k
|
6 |
+
datasets:
|
7 |
+
- jondurbin/airoboros-3.2
|
8 |
+
- bluemoon-fandom-1-1-rp-cleaned
|
9 |
+
- boolq
|
10 |
+
- jondurbin/gutenberg-dpo-v0.1
|
11 |
+
- LDJnr/Capybara
|
12 |
+
- jondurbin/cinematika-v0.1
|
13 |
+
- glaiveai/glaive-function-calling-v2
|
14 |
+
- grimulkan/LimaRP-augmented
|
15 |
+
- piqa
|
16 |
+
- Vezora/Tested-22k-Python-Alpaca
|
17 |
+
- mattpscott/airoboros-summarization
|
18 |
+
- unalignment/toxic-dpo-v0.2
|
19 |
+
quantized_by: bartowski
|
20 |
+
pipeline_tag: text-generation
|
21 |
+
---
|
22 |
+
|
23 |
+
## Llamacpp Quantizations of airoboros-34b-3.2
|
24 |
+
|
25 |
+
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2334">b2334</a> for quantization.
|
26 |
+
|
27 |
+
Original model: https://huggingface.co/jondurbin/airoboros-34b-3.2
|
28 |
+
|
29 |
+
Download a file (not the whole branch) from below:
|
30 |
+
|
31 |
+
| Filename | Quant type | File Size | Description |
|
32 |
+
| -------- | ---------- | --------- | ----------- |
|
33 |
+
| [airoboros-34b-3.2-Q8_0.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q8_0.gguf) | Q8_0 | 36.54GB | Extremely high quality, generally unneeded but max available quant. |
|
34 |
+
| [airoboros-34b-3.2-Q6_K.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q6_K.gguf) | Q6_K | 28.21GB | Very high quality, near perfect, *recommended*. |
|
35 |
+
| [airoboros-34b-3.2-Q5_K_M.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q5_K_M.gguf) | Q5_K_M | 24.32GB | High quality, very usable. |
|
36 |
+
| [airoboros-34b-3.2-Q5_K_S.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q5_K_S.gguf) | Q5_K_S | 23.70GB | High quality, very usable. |
|
37 |
+
| [airoboros-34b-3.2-Q5_0.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q5_0.gguf) | Q5_0 | 23.70GB | High quality, older format, generally not recommended. |
|
38 |
+
| [airoboros-34b-3.2-Q4_K_M.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q4_K_M.gguf) | Q4_K_M | 20.65GB | Good quality, similar to 4.25 bpw. |
|
39 |
+
| [airoboros-34b-3.2-Q4_K_S.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q4_K_S.gguf) | Q4_K_S | 19.59GB | Slightly lower quality with small space savings. |
|
40 |
+
| [airoboros-34b-3.2-Q4_0.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q4_0.gguf) | Q4_0 | 19.46GB | Decent quality, older format, generally not recommended. |
|
41 |
+
| [airoboros-34b-3.2-Q3_K_L.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q3_K_L.gguf) | Q3_K_L | 18.13GB | Lower quality but usable, good for low RAM availability. |
|
42 |
+
| [airoboros-34b-3.2-Q3_K_M.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q3_K_M.gguf) | Q3_K_M | 16.65GB | Even lower quality. |
|
43 |
+
| [airoboros-34b-3.2-Q3_K_S.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q3_K_S.gguf) | Q3_K_S | 14.96GB | Low quality, not recommended. |
|
44 |
+
| [airoboros-34b-3.2-Q2_K.gguf](https://huggingface.co/bartowski/airoboros-34b-3.2-GGUF/blob/main/airoboros-34b-3.2-Q2_K.gguf) | Q2_K | 12.82GB | Extremely low quality, *not* recommended.
|
45 |
+
|
46 |
+
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
airoboros-34b-3.2-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ce1cb6736f0255c717918c7f949d54052125263184c264eaee3a85b9524c4a9
|
3 |
+
size 12825234080
|
airoboros-34b-3.2-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75b92b3a4242ba629cc039cdc3d2ad375a912a9ba7b0b005f8c1c8bb6e74e876
|
3 |
+
size 18139445920
|
airoboros-34b-3.2-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f45a70a0c2b197172e70e6a2b618ed721b3939cc363d4e52a3e0db85abce8a7
|
3 |
+
size 16654924448
|
airoboros-34b-3.2-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b49fa20dcf223fc681e06068dc870af68384615f99c8f74e0fea1be9835353a
|
3 |
+
size 14960294560
|
airoboros-34b-3.2-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b366321ddf3ab5611a7d599bd12ca5916e311509d86bd1e19cd9f01e12254b4
|
3 |
+
size 19466529440
|
airoboros-34b-3.2-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65fdf95748add41a934e1b13e0d8d268cefaef7166c6634fd6f6c9ed04fb24c2
|
3 |
+
size 20658711200
|
airoboros-34b-3.2-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c14b79a68173cb9d8060eb68eb876c6bdf3e278eeac81775208b887fed8462f0
|
3 |
+
size 19598650016
|
airoboros-34b-3.2-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85efbe041e37783ebcb7d2637406be1106df44ca32781ae3872d5966a92e1dc5
|
3 |
+
size 23707691680
|
airoboros-34b-3.2-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b2b4db971ccbc0b520549bfa73bb92f2790615676f6b54b78777a0c70efa940
|
3 |
+
size 24321845920
|
airoboros-34b-3.2-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72c2823fd254ebab6108b9694f51bc0b5ff5f1154ee4dc9776b4322fef9c6246
|
3 |
+
size 23707691680
|
airoboros-34b-3.2-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b731ff22859a1b3cd79cb88c84af853e59f0ec804a6df2368e6abd51e6b7c9ac
|
3 |
+
size 28213926560
|
airoboros-34b-3.2-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8866146ef05675a2322af42957a79ec32795bf6d548e45e2ad068d9a1f397499
|
3 |
+
size 36542282400
|