Generated README.md
Browse files
README.md
CHANGED
@@ -4,8 +4,15 @@ language:
|
|
4 |
- en
|
5 |
pipeline_tag: text-generation
|
6 |
tags:
|
7 |
-
- llm
|
8 |
- ggml
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
# GGML converted versions of [Mosaic's](https://huggingface.co/mosaicml) MPT Models
|
11 |
|
@@ -15,20 +22,24 @@ This model was trained by [MosaicML](https://www.mosaicml.com).
|
|
15 |
MPT-7B is part of the family of MosaicPretrainedTransformer (MPT) models, which use a modified transformer architecture optimized for efficient training and inference.
|
16 |
|
17 |
## Converted Models:
|
18 |
-
| Name
|
19 |
-
|
20 |
-
| [mpt-7b-f16.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-f16.bin)
|
21 |
-
| [mpt-7b-q4_0.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-q4_0.bin)
|
22 |
-
| [mpt-7b-q4_0-ggjt.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-q4_0-ggjt.bin)
|
23 |
-
| [mpt-7b-chat-
|
24 |
-
| [mpt-7b-
|
25 |
-
| [mpt-7b-
|
26 |
-
| [mpt-7b-instruct-
|
27 |
-
| [mpt-7b-instruct-q4_0.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-instruct-q4_0.bin)
|
28 |
-
| [mpt-7b-instruct-
|
29 |
-
| [mpt-7b-
|
30 |
-
| [mpt-7b-
|
31 |
-
| [mpt-7b-
|
|
|
|
|
|
|
|
|
32 |
|
33 |
⚠️Caution⚠️: mpt-7b-storywriter is still under development!
|
34 |
|
@@ -53,7 +64,8 @@ print(model.generate("The meaning of life is"))
|
|
53 |
|
54 |
#### Installation
|
55 |
```
|
56 |
-
git clone --recurse-submodules
|
|
|
57 |
cargo build --release
|
58 |
```
|
59 |
|
|
|
4 |
- en
|
5 |
pipeline_tag: text-generation
|
6 |
tags:
|
7 |
+
- llm-rs
|
8 |
- ggml
|
9 |
+
datasets:
|
10 |
+
- mc4
|
11 |
+
- c4
|
12 |
+
- togethercomputer/RedPajama-Data-1T
|
13 |
+
- bigcode/the-stack
|
14 |
+
- allenai/s2orc
|
15 |
+
inference: false
|
16 |
---
|
17 |
# GGML converted versions of [Mosaic's](https://huggingface.co/mosaicml) MPT Models
|
18 |
|
|
|
22 |
MPT-7B is part of the family of MosaicPretrainedTransformer (MPT) models, which use a modified transformer architecture optimized for efficient training and inference.
|
23 |
|
24 |
## Converted Models:
|
25 |
+
| Name | Based on | Type | Container | GGML Version |
|
26 |
+
|:------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:-------|:------------|:---------------|
|
27 |
+
| [mpt-7b-chat-f16.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-chat-f16.bin) | [mosaicml/mpt-7b-chat](https://huggingface.co/mosaicml/mpt-7b-chat) | F16 | GGML | V3 |
|
28 |
+
| [mpt-7b-chat-q4_0.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-chat-q4_0.bin) | [mosaicml/mpt-7b-chat](https://huggingface.co/mosaicml/mpt-7b-chat) | Q4_0 | GGML | V3 |
|
29 |
+
| [mpt-7b-chat-q4_0-ggjt.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-chat-q4_0-ggjt.bin) | [mosaicml/mpt-7b-chat](https://huggingface.co/mosaicml/mpt-7b-chat) | Q4_0 | GGJT | V3 |
|
30 |
+
| [mpt-7b-chat-q5_1-ggjt.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-chat-q5_1-ggjt.bin) | [mosaicml/mpt-7b-chat](https://huggingface.co/mosaicml/mpt-7b-chat) | Q5_1 | GGJT | V3 |
|
31 |
+
| [mpt-7b-f16.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-f16.bin) | [mosaicml/mpt-7b](https://huggingface.co/mosaicml/mpt-7b) | F16 | GGML | V3 |
|
32 |
+
| [mpt-7b-instruct-f16.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-instruct-f16.bin) | [mosaicml/mpt-7b-instruct](https://huggingface.co/mosaicml/mpt-7b-instruct) | F16 | GGML | V3 |
|
33 |
+
| [mpt-7b-instruct-q4_0.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-instruct-q4_0.bin) | [mosaicml/mpt-7b-instruct](https://huggingface.co/mosaicml/mpt-7b-instruct) | Q4_0 | GGML | V3 |
|
34 |
+
| [mpt-7b-instruct-q4_0-ggjt.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-instruct-q4_0-ggjt.bin) | [mosaicml/mpt-7b-instruct](https://huggingface.co/mosaicml/mpt-7b-instruct) | Q4_0 | GGJT | V3 |
|
35 |
+
| [mpt-7b-instruct-q5_1-ggjt.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-instruct-q5_1-ggjt.bin) | [mosaicml/mpt-7b-instruct](https://huggingface.co/mosaicml/mpt-7b-instruct) | Q5_1 | GGJT | V3 |
|
36 |
+
| [mpt-7b-q4_0.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-q4_0.bin) | [mosaicml/mpt-7b](https://huggingface.co/mosaicml/mpt-7b) | Q4_0 | GGML | V3 |
|
37 |
+
| [mpt-7b-q4_0-ggjt.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-q4_0-ggjt.bin) | [mosaicml/mpt-7b](https://huggingface.co/mosaicml/mpt-7b) | Q4_0 | GGJT | V3 |
|
38 |
+
| [mpt-7b-q5_1-ggjt.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-q5_1-ggjt.bin) | [mosaicml/mpt-7b](https://huggingface.co/mosaicml/mpt-7b) | Q5_1 | GGJT | V3 |
|
39 |
+
| [mpt-7b-storywriter-f16.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-storywriter-f16.bin) | [mosaicml/mpt-7b-storywriter](https://huggingface.co/mosaicml/mpt-7b-storywriter) | F16 | GGML | V3 |
|
40 |
+
| [mpt-7b-storywriter-q4_0.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-storywriter-q4_0.bin) | [mosaicml/mpt-7b-storywriter](https://huggingface.co/mosaicml/mpt-7b-storywriter) | Q4_0 | GGML | V3 |
|
41 |
+
| [mpt-7b-storywriter-q4_0-ggjt.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-storywriter-q4_0-ggjt.bin) | [mosaicml/mpt-7b-storywriter](https://huggingface.co/mosaicml/mpt-7b-storywriter) | Q4_0 | GGJT | V3 |
|
42 |
+
| [mpt-7b-storywriter-q5_1-ggjt.bin](https://huggingface.co/rustformers/mpt-7b-ggml/blob/main/mpt-7b-storywriter-q5_1-ggjt.bin) | [mosaicml/mpt-7b-storywriter](https://huggingface.co/mosaicml/mpt-7b-storywriter) | Q5_1 | GGJT | V3 |
|
43 |
|
44 |
⚠️Caution⚠️: mpt-7b-storywriter is still under development!
|
45 |
|
|
|
64 |
|
65 |
#### Installation
|
66 |
```
|
67 |
+
git clone --recurse-submodules https://github.com/rustformers/llm.git
|
68 |
+
cd llm
|
69 |
cargo build --release
|
70 |
```
|
71 |
|