Generated README.md
Browse files
README.md
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-sa-4.0
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
tags:
|
6 |
+
- llm-rs
|
7 |
+
- ggml
|
8 |
+
pipeline_tag: text-generation
|
9 |
+
---
|
10 |
+
|
11 |
+
# GGML converted version of [StabilityAI](https://huggingface.co/stabilityai)'s StableLM models
|
12 |
+
|
13 |
+
## Description
|
14 |
+
|
15 |
+
`StableLM-Base-Alpha` is a suite of 3B and 7B parameter decoder-only language models pre-trained on a diverse collection of English and Code datasets with a sequence length of 4096 to push beyond the context window limitations of existing open-source language models.
|
16 |
+
|
17 |
+
|
18 |
+
## Converted Models
|
19 |
+
| Name | Based on | Type | Container | GGML Version |
|
20 |
+
|:------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------|:-------|:------------|:---------------|
|
21 |
+
| [stablelm-base-alpha-3b-f16.bin](https://huggingface.co/rustformers/stablelm-ggml/blob/main/stablelm-base-alpha-3b-f16.bin) | [stabilityai/stablelm-base-alpha-3b](https://huggingface.co/stabilityai/stablelm-base-alpha-3b) | F16 | GGML | V3 |
|
22 |
+
| [stablelm-base-alpha-3b-q4_0.bin](https://huggingface.co/rustformers/stablelm-ggml/blob/main/stablelm-base-alpha-3b-q4_0.bin) | [stabilityai/stablelm-base-alpha-3b](https://huggingface.co/stabilityai/stablelm-base-alpha-3b) | Q4_0 | GGML | V3 |
|
23 |
+
| [stablelm-base-alpha-3b-q4_0-ggjt.bin](https://huggingface.co/rustformers/stablelm-ggml/blob/main/stablelm-base-alpha-3b-q4_0-ggjt.bin) | [stabilityai/stablelm-base-alpha-3b](https://huggingface.co/stabilityai/stablelm-base-alpha-3b) | Q4_0 | GGJT | V3 |
|
24 |
+
| [stablelm-base-alpha-3b-q5_1-ggjt.bin](https://huggingface.co/rustformers/stablelm-ggml/blob/main/stablelm-base-alpha-3b-q5_1-ggjt.bin) | [stabilityai/stablelm-base-alpha-3b](https://huggingface.co/stabilityai/stablelm-base-alpha-3b) | Q5_1 | GGJT | V3 |
|
25 |
+
| [stablelm-base-alpha-7b-f16.bin](https://huggingface.co/rustformers/stablelm-ggml/blob/main/stablelm-base-alpha-7b-f16.bin) | [stabilityai/stablelm-base-alpha-7b](https://huggingface.co/stabilityai/stablelm-base-alpha-7b) | F16 | GGML | V3 |
|
26 |
+
| [stablelm-base-alpha-7b-q4_0.bin](https://huggingface.co/rustformers/stablelm-ggml/blob/main/stablelm-base-alpha-7b-q4_0.bin) | [stabilityai/stablelm-base-alpha-7b](https://huggingface.co/stabilityai/stablelm-base-alpha-7b) | Q4_0 | GGML | V3 |
|
27 |
+
| [stablelm-base-alpha-7b-q4_0-ggjt.bin](https://huggingface.co/rustformers/stablelm-ggml/blob/main/stablelm-base-alpha-7b-q4_0-ggjt.bin) | [stabilityai/stablelm-base-alpha-7b](https://huggingface.co/stabilityai/stablelm-base-alpha-7b) | Q4_0 | GGJT | V3 |
|
28 |
+
| [stablelm-base-alpha-7b-q5_1-ggjt.bin](https://huggingface.co/rustformers/stablelm-ggml/blob/main/stablelm-base-alpha-7b-q5_1-ggjt.bin) | [stabilityai/stablelm-base-alpha-7b](https://huggingface.co/stabilityai/stablelm-base-alpha-7b) | Q5_1 | GGJT | V3 |
|
29 |
+
| [stablelm-tuned-alpha-3b-f16.bin](https://huggingface.co/rustformers/stablelm-ggml/blob/main/stablelm-tuned-alpha-3b-f16.bin) | [stabilityai/stablelm-tuned-alpha-3b](https://huggingface.co/stabilityai/stablelm-tuned-alpha-3b) | F16 | GGML | V3 |
|
30 |
+
| [stablelm-tuned-alpha-3b-q4_0.bin](https://huggingface.co/rustformers/stablelm-ggml/blob/main/stablelm-tuned-alpha-3b-q4_0.bin) | [stabilityai/stablelm-tuned-alpha-3b](https://huggingface.co/stabilityai/stablelm-tuned-alpha-3b) | Q4_0 | GGML | V3 |
|
31 |
+
| [stablelm-tuned-alpha-3b-q4_0-ggjt.bin](https://huggingface.co/rustformers/stablelm-ggml/blob/main/stablelm-tuned-alpha-3b-q4_0-ggjt.bin) | [stabilityai/stablelm-tuned-alpha-3b](https://huggingface.co/stabilityai/stablelm-tuned-alpha-3b) | Q4_0 | GGJT | V3 |
|
32 |
+
| [stablelm-tuned-alpha-3b-q5_1-ggjt.bin](https://huggingface.co/rustformers/stablelm-ggml/blob/main/stablelm-tuned-alpha-3b-q5_1-ggjt.bin) | [stabilityai/stablelm-tuned-alpha-3b](https://huggingface.co/stabilityai/stablelm-tuned-alpha-3b) | Q5_1 | GGJT | V3 |
|
33 |
+
| [stablelm-tuned-alpha-7b-f16.bin](https://huggingface.co/rustformers/stablelm-ggml/blob/main/stablelm-tuned-alpha-7b-f16.bin) | [stabilityai/stablelm-tuned-alpha-7b](https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b) | F16 | GGML | V3 |
|
34 |
+
| [stablelm-tuned-alpha-7b-q4_0.bin](https://huggingface.co/rustformers/stablelm-ggml/blob/main/stablelm-tuned-alpha-7b-q4_0.bin) | [stabilityai/stablelm-tuned-alpha-7b](https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b) | Q4_0 | GGML | V3 |
|
35 |
+
| [stablelm-tuned-alpha-7b-q4_0-ggjt.bin](https://huggingface.co/rustformers/stablelm-ggml/blob/main/stablelm-tuned-alpha-7b-q4_0-ggjt.bin) | [stabilityai/stablelm-tuned-alpha-7b](https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b) | Q4_0 | GGJT | V3 |
|
36 |
+
| [stablelm-tuned-alpha-7b-q5_1-ggjt.bin](https://huggingface.co/rustformers/stablelm-ggml/blob/main/stablelm-tuned-alpha-7b-q5_1-ggjt.bin) | [stabilityai/stablelm-tuned-alpha-7b](https://huggingface.co/stabilityai/stablelm-tuned-alpha-7b) | Q5_1 | GGJT | V3 |
|
37 |
+
|
38 |
+
## Usage
|
39 |
+
|
40 |
+
### Python via [llm-rs](https://github.com/LLukas22/llm-rs-python):
|
41 |
+
|
42 |
+
#### Installation
|
43 |
+
Via pip: `pip install llm-rs`
|
44 |
+
|
45 |
+
#### Run inference
|
46 |
+
```python
|
47 |
+
from llm_rs import AutoModel
|
48 |
+
|
49 |
+
#Load the model, define any model you like from the list above as the `model_file`
|
50 |
+
model = AutoModel.from_pretrained("rustformers/stablelm-ggml",model_file="stablelm-base-alpha-3b-q4_0-ggjt.bin")
|
51 |
+
|
52 |
+
#Generate
|
53 |
+
print(model.generate("The meaning of life is"))
|
54 |
+
```
|
55 |
+
|
56 |
+
### Rust via [Rustformers/llm](https://github.com/rustformers/llm):
|
57 |
+
|
58 |
+
#### Installation
|
59 |
+
```
|
60 |
+
git clone --recurse-submodules https://github.com/rustformers/llm.git
|
61 |
+
cd llm
|
62 |
+
cargo build --release
|
63 |
+
```
|
64 |
+
|
65 |
+
#### Run inference
|
66 |
+
```
|
67 |
+
cargo run --release -- gptneox infer -m path/to/model.bin -p "Tell me how cool the Rust programming language is:"
|
68 |
+
```
|