Hugging Face's logo

bartowski
/
h2o-danube2-1.8b-chat-GGUF

Text Generation
Transformers
GGUF
English
gpt
llm
large language model
h2o-llmstudio
Inference Endpoints
Model card Files Community
bartowski commited on
Commit
35d4a58
•
1 Parent(s): 9717808

Llamacpp quants

Browse files
Files changed (18) hide show
  1. .gitattributes +16 -0
  2. README.md +44 -0
  3. h2o-danube2-1.8b-chat-IQ3_M.gguf +3 -0
  4. h2o-danube2-1.8b-chat-IQ3_S.gguf +3 -0
  5. h2o-danube2-1.8b-chat-IQ4_NL.gguf +3 -0
  6. h2o-danube2-1.8b-chat-IQ4_XS.gguf +3 -0
  7. h2o-danube2-1.8b-chat-Q2_K.gguf +3 -0
  8. h2o-danube2-1.8b-chat-Q3_K_L.gguf +3 -0
  9. h2o-danube2-1.8b-chat-Q3_K_M.gguf +3 -0
  10. h2o-danube2-1.8b-chat-Q3_K_S.gguf +3 -0
  11. h2o-danube2-1.8b-chat-Q4_0.gguf +3 -0
  12. h2o-danube2-1.8b-chat-Q4_K_M.gguf +3 -0
  13. h2o-danube2-1.8b-chat-Q4_K_S.gguf +3 -0
  14. h2o-danube2-1.8b-chat-Q5_0.gguf +3 -0
  15. h2o-danube2-1.8b-chat-Q5_K_M.gguf +3 -0
  16. h2o-danube2-1.8b-chat-Q5_K_S.gguf +3 -0
  17. h2o-danube2-1.8b-chat-Q6_K.gguf +3 -0
  18. h2o-danube2-1.8b-chat-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
+ h2o-danube2-1.8b-chat-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ h2o-danube2-1.8b-chat-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
38
+ h2o-danube2-1.8b-chat-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
39
+ h2o-danube2-1.8b-chat-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
40
+ h2o-danube2-1.8b-chat-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
41
+ h2o-danube2-1.8b-chat-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
42
+ h2o-danube2-1.8b-chat-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
43
+ h2o-danube2-1.8b-chat-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
44
+ h2o-danube2-1.8b-chat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
45
+ h2o-danube2-1.8b-chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
46
+ h2o-danube2-1.8b-chat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
47
+ h2o-danube2-1.8b-chat-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
48
+ h2o-danube2-1.8b-chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
49
+ h2o-danube2-1.8b-chat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
50
+ h2o-danube2-1.8b-chat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
51
+ h2o-danube2-1.8b-chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ library_name: transformers
5
+ license: apache-2.0
6
+ tags:
7
+ - gpt
8
+ - llm
9
+ - large language model
10
+ - h2o-llmstudio
11
+ thumbnail: >-
12
+ https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
13
+ pipeline_tag: text-generation
14
+ quantized_by: bartowski
15
+ ---
16
+
17
+ ## Llamacpp Quantizations of h2o-danube2-1.8b-chat
18
+
19
+ Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2589">b2589</a> for quantization.
20
+
21
+ Original model: https://huggingface.co/h2oai/h2o-danube2-1.8b-chat
22
+
23
+ Download a file (not the whole branch) from below:
24
+
25
+ | Filename | Quant type | File Size | Description |
26
+ | -------- | ---------- | --------- | ----------- |
27
+ | [h2o-danube2-1.8b-chat-Q8_0.gguf](https://huggingface.co/bartowski/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q8_0.gguf) | Q8_0 | 1.94GB | Extremely high quality, generally unneeded but max available quant. |
28
+ | [h2o-danube2-1.8b-chat-Q6_K.gguf](https://huggingface.co/bartowski/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q6_K.gguf) | Q6_K | 1.50GB | Very high quality, near perfect, *recommended*. |
29
+ | [h2o-danube2-1.8b-chat-Q5_K_M.gguf](https://huggingface.co/bartowski/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q5_K_M.gguf) | Q5_K_M | 1.30GB | High quality, very usable. |
30
+ | [h2o-danube2-1.8b-chat-Q5_K_S.gguf](https://huggingface.co/bartowski/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q5_K_S.gguf) | Q5_K_S | 1.27GB | High quality, very usable. |
31
+ | [h2o-danube2-1.8b-chat-Q5_0.gguf](https://huggingface.co/bartowski/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q5_0.gguf) | Q5_0 | 1.27GB | High quality, older format, generally not recommended. |
32
+ | [h2o-danube2-1.8b-chat-Q4_K_M.gguf](https://huggingface.co/bartowski/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q4_K_M.gguf) | Q4_K_M | 1.11GB | Good quality, uses about 4.83 bits per weight. |
33
+ | [h2o-danube2-1.8b-chat-Q4_K_S.gguf](https://huggingface.co/bartowski/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q4_K_S.gguf) | Q4_K_S | 1.05GB | Slightly lower quality with small space savings. |
34
+ | [h2o-danube2-1.8b-chat-IQ4_NL.gguf](https://huggingface.co/bartowski/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-IQ4_NL.gguf) | IQ4_NL | 1.06GB | Decent quality, similar to Q4_K_S, new method of quanting, |
35
+ | [h2o-danube2-1.8b-chat-IQ4_XS.gguf](https://huggingface.co/bartowski/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-IQ4_XS.gguf) | IQ4_XS | 1.01GB | Decent quality, new method with similar performance to Q4. |
36
+ | [h2o-danube2-1.8b-chat-Q4_0.gguf](https://huggingface.co/bartowski/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q4_0.gguf) | Q4_0 | 1.05GB | Decent quality, older format, generally not recommended. |
37
+ | [h2o-danube2-1.8b-chat-Q3_K_L.gguf](https://huggingface.co/bartowski/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q3_K_L.gguf) | Q3_K_L | .98GB | Lower quality but usable, good for low RAM availability. |
38
+ | [h2o-danube2-1.8b-chat-Q3_K_M.gguf](https://huggingface.co/bartowski/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q3_K_M.gguf) | Q3_K_M | .90GB | Even lower quality. |
39
+ | [h2o-danube2-1.8b-chat-IQ3_M.gguf](https://huggingface.co/bartowski/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-IQ3_M.gguf) | IQ3_M | .85GB | Medium-low quality, new method with decent performance. |
40
+ | [h2o-danube2-1.8b-chat-IQ3_S.gguf](https://huggingface.co/bartowski/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-IQ3_S.gguf) | IQ3_S | .82GB | Lower quality, new method with decent performance, recommended over Q3 quants. |
41
+ | [h2o-danube2-1.8b-chat-Q3_K_S.gguf](https://huggingface.co/bartowski/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q3_K_S.gguf) | Q3_K_S | .82GB | Low quality, not recommended. |
42
+ | [h2o-danube2-1.8b-chat-Q2_K.gguf](https://huggingface.co/bartowski/h2o-danube2-1.8b-chat-GGUF/blob/main/h2o-danube2-1.8b-chat-Q2_K.gguf) | Q2_K | .71GB | Extremely low quality, *not* recommended.
43
+
44
+ Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
h2o-danube2-1.8b-chat-IQ3_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1db4749e47cc080bfbcd0f284eb0a7c979e8082f646dbf86c26f2a8c1be9f23
3
+ size 853185632
h2o-danube2-1.8b-chat-IQ3_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f58644910c3a8f44f26c88e30e4ce423ae3a35defeda4139b135f2d9350075f
3
+ size 825245792
h2o-danube2-1.8b-chat-IQ4_NL.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37de8d7857a2a25916b11aa2692476caea872c71dcbaa81c37ea6d505d862c70
3
+ size 1063883872
h2o-danube2-1.8b-chat-IQ4_XS.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:723db56dd292aa655221aa1007d7648bcc97c37af5d58960177a28e05475a6aa
3
+ size 1012110432
h2o-danube2-1.8b-chat-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b338907df671addd08566e344b057716917a4bb4474ec03c4fef2c36cbe67588
3
+ size 710696032
h2o-danube2-1.8b-chat-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b5acc73e5a239aadd09ed04a52e001354fb8223d5eba3fbe2b5f228f9b7eaa
3
+ size 980197472
h2o-danube2-1.8b-chat-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f677ce24a83de873868a53429b24d7230162e8e4f5b4795b9e912ff97fbfd69
3
+ size 905158752
h2o-danube2-1.8b-chat-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90699255017e580869258d89dbb908610ab3966be7b568b3012263620dcbe73e
3
+ size 820023392
h2o-danube2-1.8b-chat-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a456e1186086668a0a01a070806a09b55ad823df81381167a1b113941191fc6
3
+ size 1052333152
h2o-danube2-1.8b-chat-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e3e4521da367b3704ffaff420f95796abab4ff859434f774d2f36af037e4a4
3
+ size 1112144992
h2o-danube2-1.8b-chat-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e46e02aa107825462b53350f0690c8c185baa8f5b93af30271fd1365e642937
3
+ size 1059787872
h2o-danube2-1.8b-chat-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d2dd52f60b0f801f0a6bd0ec5a6c99f9eaaccdc5b2593235868142c089c3aa0
3
+ size 1270977632
h2o-danube2-1.8b-chat-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2478f0a6e7f9ec966ef76edefebb22e2b4147cd547cc970c4a9951747fe8682
3
+ size 1301789792
h2o-danube2-1.8b-chat-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d1c4337501771e860a9e531680e8381f44bc618d324f0922ba7184adc96a83a
3
+ size 1270977632
h2o-danube2-1.8b-chat-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:497df9f0014af7c36fdf8e9d2da327c5c7aa8f7c95d70d6d10ff5460ee7660b3
3
+ size 1503287392
h2o-danube2-1.8b-chat-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5914026ba039b17b32c1cf3385ca0c54ca239d25ca31096ec9518d772105d33b
3
+ size 1946751072