Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
Config file: 1.3B
|
3 |
+
Data: Vietnamese Dataset 30GB(CulturaX) + Project(1.3B)
|
4 |
+
Trained: Pretrain
|
5 |
+
base_model: eunyounglee/GPT-NeoX-1.3B-viet-final
|
6 |
+
inference: false
|
7 |
+
language:
|
8 |
+
- eng
|
9 |
+
model_creator: eunyounglee
|
10 |
+
model_name: GPT-NeoX-1.3B-viet-final
|
11 |
+
pipeline_tag: text-generation
|
12 |
+
quantized_by: afrideva
|
13 |
+
tags:
|
14 |
+
- gguf
|
15 |
+
- ggml
|
16 |
+
- quantized
|
17 |
+
- q2_k
|
18 |
+
- q3_k_m
|
19 |
+
- q4_k_m
|
20 |
+
- q5_k_m
|
21 |
+
- q6_k
|
22 |
+
- q8_0
|
23 |
+
---
|
24 |
+
# eunyounglee/GPT-NeoX-1.3B-viet-final-GGUF
|
25 |
+
|
26 |
+
Quantized GGUF model files for [GPT-NeoX-1.3B-viet-final](https://huggingface.co/eunyounglee/GPT-NeoX-1.3B-viet-final) from [eunyounglee](https://huggingface.co/eunyounglee)
|
27 |
+
|
28 |
+
|
29 |
+
| Name | Quant method | Size |
|
30 |
+
| ---- | ---- | ---- |
|
31 |
+
| [gpt-neox-1.3b-viet-final.q2_k.gguf](https://huggingface.co/afrideva/GPT-NeoX-1.3B-viet-final-GGUF/resolve/main/gpt-neox-1.3b-viet-final.q2_k.gguf) | q2_k | 635.16 MB |
|
32 |
+
| [gpt-neox-1.3b-viet-final.q3_k_m.gguf](https://huggingface.co/afrideva/GPT-NeoX-1.3B-viet-final-GGUF/resolve/main/gpt-neox-1.3b-viet-final.q3_k_m.gguf) | q3_k_m | 789.55 MB |
|
33 |
+
| [gpt-neox-1.3b-viet-final.q4_k_m.gguf](https://huggingface.co/afrideva/GPT-NeoX-1.3B-viet-final-GGUF/resolve/main/gpt-neox-1.3b-viet-final.q4_k_m.gguf) | q4_k_m | 944.92 MB |
|
34 |
+
| [gpt-neox-1.3b-viet-final.q5_k_m.gguf](https://huggingface.co/afrideva/GPT-NeoX-1.3B-viet-final-GGUF/resolve/main/gpt-neox-1.3b-viet-final.q5_k_m.gguf) | q5_k_m | 1.09 GB |
|
35 |
+
| [gpt-neox-1.3b-viet-final.q6_k.gguf](https://huggingface.co/afrideva/GPT-NeoX-1.3B-viet-final-GGUF/resolve/main/gpt-neox-1.3b-viet-final.q6_k.gguf) | q6_k | 1.20 GB |
|
36 |
+
| [gpt-neox-1.3b-viet-final.q8_0.gguf](https://huggingface.co/afrideva/GPT-NeoX-1.3B-viet-final-GGUF/resolve/main/gpt-neox-1.3b-viet-final.q8_0.gguf) | q8_0 | 1.55 GB |
|
37 |
+
|
38 |
+
|
39 |
+
|
40 |
+
## Original Model Card:
|
41 |
+
# Model Card for Model ID
|
42 |
+
|
43 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
44 |
+
|
45 |
+
Pretrained GPT-NeoX model with 31.3 Vietnamese dataset. Took about 4.5 hours to reach 40,000 iterations. Trained on A100 40GB GPU and 48 core CPU.
|
46 |
+
|
47 |
+
## Model Details
|
48 |
+
|
49 |
+
### Model Description
|
50 |
+
|
51 |
+
<!-- Provide a longer summary of what this model is. -->
|
52 |
+
|
53 |
+
|
54 |
+
|
55 |
+
- **Developed by:** Eunyoung Lee
|
56 |
+
- **Model type:** GPT-NeoX
|
57 |
+
- **Language(s) (NLP):** Vietnamese
|