Generated README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,58 @@
|
|
1 |
---
|
2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
tags:
|
6 |
+
- llm-rs
|
7 |
+
- ggml
|
8 |
+
pipeline_tag: text-generation
|
9 |
+
datasets:
|
10 |
+
- nomic-ai/gpt4all-j-prompt-generations
|
11 |
---
|
12 |
+
|
13 |
+
# GGML converted version of [Nomic AI](https://huggingface.co/nomic-ai) GPT4All-J-v1.0 models
|
14 |
+
|
15 |
+
## Description
|
16 |
+
|
17 |
+
An Apache-2 licensed chatbot trained over a massive curated corpus of assistant interactions including word problems, multi-turn dialogue, code, poems, songs, and stories.
|
18 |
+
|
19 |
+
|
20 |
+
## Converted Models
|
21 |
+
| Name | Based on | Type | Container | GGML Version |
|
22 |
+
|:---------------------------------------------------------------------------------------------------------------|:----------------------------------------------------------------|:-------|:------------|:---------------|
|
23 |
+
| [gpt4all-j-f16.bin](https://huggingface.co/rustformers/gpt4all-j-ggml/blob/main/gpt4all-j-f16.bin) | [nomic-ai/gpt4all-j](https://huggingface.co/nomic-ai/gpt4all-j) | F16 | GGML | V3 |
|
24 |
+
| [gpt4all-j-q4_0.bin](https://huggingface.co/rustformers/gpt4all-j-ggml/blob/main/gpt4all-j-q4_0.bin) | [nomic-ai/gpt4all-j](https://huggingface.co/nomic-ai/gpt4all-j) | Q4_0 | GGML | V3 |
|
25 |
+
| [gpt4all-j-q4_0-ggjt.bin](https://huggingface.co/rustformers/gpt4all-j-ggml/blob/main/gpt4all-j-q4_0-ggjt.bin) | [nomic-ai/gpt4all-j](https://huggingface.co/nomic-ai/gpt4all-j) | Q4_0 | GGJT | V3 |
|
26 |
+
| [gpt4all-j-q5_1-ggjt.bin](https://huggingface.co/rustformers/gpt4all-j-ggml/blob/main/gpt4all-j-q5_1-ggjt.bin) | [nomic-ai/gpt4all-j](https://huggingface.co/nomic-ai/gpt4all-j) | Q5_1 | GGJT | V3 |
|
27 |
+
|
28 |
+
## Usage
|
29 |
+
|
30 |
+
### Python via [llm-rs](https://github.com/LLukas22/llm-rs-python):
|
31 |
+
|
32 |
+
#### Installation
|
33 |
+
Via pip: `pip install llm-rs`
|
34 |
+
|
35 |
+
#### Run inference
|
36 |
+
```python
|
37 |
+
from llm_rs import AutoModel
|
38 |
+
|
39 |
+
#Load the model, define any model you like from the list above as the `model_file`
|
40 |
+
model = AutoModel.from_pretrained("rustformers/gpt4all-j-ggml",model_file="gpt4all-j-q4_0-ggjt.bin")
|
41 |
+
|
42 |
+
#Generate
|
43 |
+
print(model.generate("The meaning of life is"))
|
44 |
+
```
|
45 |
+
|
46 |
+
### Rust via [Rustformers/llm](https://github.com/rustformers/llm):
|
47 |
+
|
48 |
+
#### Installation
|
49 |
+
```
|
50 |
+
git clone --recurse-submodules https://github.com/rustformers/llm.git
|
51 |
+
cd llm
|
52 |
+
cargo build --release
|
53 |
+
```
|
54 |
+
|
55 |
+
#### Run inference
|
56 |
+
```
|
57 |
+
cargo run --release -- gptj infer -m path/to/model.bin -p "Tell me how cool the Rust programming language is:"
|
58 |
+
```
|