Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +79 -0
- h2o-danube3-4b-chat-Q2_K.gguf +3 -0
- h2o-danube3-4b-chat-Q3_K_L.gguf +3 -0
- h2o-danube3-4b-chat-Q3_K_M.gguf +3 -0
- h2o-danube3-4b-chat-Q3_K_S.gguf +3 -0
- h2o-danube3-4b-chat-Q4_0.gguf +3 -0
- h2o-danube3-4b-chat-Q4_K_M.gguf +3 -0
- h2o-danube3-4b-chat-Q4_K_S.gguf +3 -0
- h2o-danube3-4b-chat-Q5_0.gguf +3 -0
- h2o-danube3-4b-chat-Q5_K_M.gguf +3 -0
- h2o-danube3-4b-chat-Q5_K_S.gguf +3 -0
- h2o-danube3-4b-chat-Q6_K.gguf +3 -0
- h2o-danube3-4b-chat-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 |
+
h2o-danube3-4b-chat-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
h2o-danube3-4b-chat-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
h2o-danube3-4b-chat-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
h2o-danube3-4b-chat-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
h2o-danube3-4b-chat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
h2o-danube3-4b-chat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
h2o-danube3-4b-chat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
h2o-danube3-4b-chat-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
h2o-danube3-4b-chat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
h2o-danube3-4b-chat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
h2o-danube3-4b-chat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
h2o-danube3-4b-chat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
- TensorBlock
|
12 |
+
- GGUF
|
13 |
+
thumbnail: https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
|
14 |
+
pipeline_tag: text-generation
|
15 |
+
base_model: h2oai/h2o-danube3-4b-chat
|
16 |
+
---
|
17 |
+
|
18 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
19 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
20 |
+
</div>
|
21 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
22 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
23 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
24 |
+
Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
|
25 |
+
</p>
|
26 |
+
</div>
|
27 |
+
</div>
|
28 |
+
|
29 |
+
## h2oai/h2o-danube3-4b-chat - GGUF
|
30 |
+
|
31 |
+
This repo contains GGUF format model files for [h2oai/h2o-danube3-4b-chat](https://huggingface.co/h2oai/h2o-danube3-4b-chat).
|
32 |
+
|
33 |
+
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
|
34 |
+
|
35 |
+
## Prompt template
|
36 |
+
|
37 |
+
```
|
38 |
+
<|prompt|>{prompt}</s><|answer|>
|
39 |
+
```
|
40 |
+
|
41 |
+
## Model file specification
|
42 |
+
|
43 |
+
| Filename | Quant type | File Size | Description |
|
44 |
+
| -------- | ---------- | --------- | ----------- |
|
45 |
+
| [h2o-danube3-4b-chat-Q2_K.gguf](https://huggingface.co/tensorblock/h2o-danube3-4b-chat-GGUF/tree/main/h2o-danube3-4b-chat-Q2_K.gguf) | Q2_K | 1.410 GB | smallest, significant quality loss - not recommended for most purposes |
|
46 |
+
| [h2o-danube3-4b-chat-Q3_K_S.gguf](https://huggingface.co/tensorblock/h2o-danube3-4b-chat-GGUF/tree/main/h2o-danube3-4b-chat-Q3_K_S.gguf) | Q3_K_S | 1.631 GB | very small, high quality loss |
|
47 |
+
| [h2o-danube3-4b-chat-Q3_K_M.gguf](https://huggingface.co/tensorblock/h2o-danube3-4b-chat-GGUF/tree/main/h2o-danube3-4b-chat-Q3_K_M.gguf) | Q3_K_M | 1.808 GB | very small, high quality loss |
|
48 |
+
| [h2o-danube3-4b-chat-Q3_K_L.gguf](https://huggingface.co/tensorblock/h2o-danube3-4b-chat-GGUF/tree/main/h2o-danube3-4b-chat-Q3_K_L.gguf) | Q3_K_L | 1.964 GB | small, substantial quality loss |
|
49 |
+
| [h2o-danube3-4b-chat-Q4_0.gguf](https://huggingface.co/tensorblock/h2o-danube3-4b-chat-GGUF/tree/main/h2o-danube3-4b-chat-Q4_0.gguf) | Q4_0 | 2.106 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
50 |
+
| [h2o-danube3-4b-chat-Q4_K_S.gguf](https://huggingface.co/tensorblock/h2o-danube3-4b-chat-GGUF/tree/main/h2o-danube3-4b-chat-Q4_K_S.gguf) | Q4_K_S | 2.122 GB | small, greater quality loss |
|
51 |
+
| [h2o-danube3-4b-chat-Q4_K_M.gguf](https://huggingface.co/tensorblock/h2o-danube3-4b-chat-GGUF/tree/main/h2o-danube3-4b-chat-Q4_K_M.gguf) | Q4_K_M | 2.230 GB | medium, balanced quality - recommended |
|
52 |
+
| [h2o-danube3-4b-chat-Q5_0.gguf](https://huggingface.co/tensorblock/h2o-danube3-4b-chat-GGUF/tree/main/h2o-danube3-4b-chat-Q5_0.gguf) | Q5_0 | 2.553 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
53 |
+
| [h2o-danube3-4b-chat-Q5_K_S.gguf](https://huggingface.co/tensorblock/h2o-danube3-4b-chat-GGUF/tree/main/h2o-danube3-4b-chat-Q5_K_S.gguf) | Q5_K_S | 2.553 GB | large, low quality loss - recommended |
|
54 |
+
| [h2o-danube3-4b-chat-Q5_K_M.gguf](https://huggingface.co/tensorblock/h2o-danube3-4b-chat-GGUF/tree/main/h2o-danube3-4b-chat-Q5_K_M.gguf) | Q5_K_M | 2.617 GB | large, very low quality loss - recommended |
|
55 |
+
| [h2o-danube3-4b-chat-Q6_K.gguf](https://huggingface.co/tensorblock/h2o-danube3-4b-chat-GGUF/tree/main/h2o-danube3-4b-chat-Q6_K.gguf) | Q6_K | 3.028 GB | very large, extremely low quality loss |
|
56 |
+
| [h2o-danube3-4b-chat-Q8_0.gguf](https://huggingface.co/tensorblock/h2o-danube3-4b-chat-GGUF/tree/main/h2o-danube3-4b-chat-Q8_0.gguf) | Q8_0 | 3.922 GB | very large, extremely low quality loss - not recommended |
|
57 |
+
|
58 |
+
|
59 |
+
## Downloading instruction
|
60 |
+
|
61 |
+
### Command line
|
62 |
+
|
63 |
+
Firstly, install Huggingface Client
|
64 |
+
|
65 |
+
```shell
|
66 |
+
pip install -U "huggingface_hub[cli]"
|
67 |
+
```
|
68 |
+
|
69 |
+
Then, downoad the individual model file the a local directory
|
70 |
+
|
71 |
+
```shell
|
72 |
+
huggingface-cli download tensorblock/h2o-danube3-4b-chat-GGUF --include "h2o-danube3-4b-chat-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
73 |
+
```
|
74 |
+
|
75 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
76 |
+
|
77 |
+
```shell
|
78 |
+
huggingface-cli download tensorblock/h2o-danube3-4b-chat-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
79 |
+
```
|
h2o-danube3-4b-chat-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4954c7edfc17576fee836f0d33ade97af9cd674f218e0d84d1e0e66bd666021
|
3 |
+
size 1514406240
|
h2o-danube3-4b-chat-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea6642061cfa6c071f63b4536b60cac110ef985f6dcfd16c49ab8ee74a2b829e
|
3 |
+
size 2109107040
|
h2o-danube3-4b-chat-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e95214b8baa0b2d8a1866eb6172cc6c644e0d39d55f5ae5e2099335050b7c14f
|
3 |
+
size 1941683040
|
h2o-danube3-4b-chat-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97a161084a44b19a735fce2463eb17db8a6eb805deac4efe885f64399505375c
|
3 |
+
size 1751756640
|
h2o-danube3-4b-chat-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b0ecdb9d437cdf3ee8155bd9858b5ae72645304dfa9467165fb4c2883e8f6ad
|
3 |
+
size 2261593440
|
h2o-danube3-4b-chat-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76eeeae5ce16b1dc91e88932d6a720d441c27af1894149478373ad3aa2562364
|
3 |
+
size 2394649440
|
h2o-danube3-4b-chat-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbdeb8a9133046996ff7601bb66446f1a706b43c0bf3f8719af7e3d3e7113e3e
|
3 |
+
size 2278182240
|
h2o-danube3-4b-chat-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c250cbf58d7e44dcafcef88047c1991a2f007f12b8184a8a58e888a4441b0876
|
3 |
+
size 2741439840
|
h2o-danube3-4b-chat-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5c031339fdeb28c9beb13566a3ff99bc899cb9920600cfa789bd9c1cd562452
|
3 |
+
size 2809983840
|
h2o-danube3-4b-chat-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ca09cf8ba4a3ac18b0af5dd8a7b2735eff4600451f3908474f3aad3b4abe68c
|
3 |
+
size 2741439840
|
h2o-danube3-4b-chat-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad2c92f234855f7728b45b26a6c8cf912e1b690f3334fb7e0c123f401559a458
|
3 |
+
size 3251276640
|
h2o-danube3-4b-chat-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36f6de4e0b56168e795e24f0b545945963e8999f343a92388f5b45be126aefd1
|
3 |
+
size 4210739040
|