Xin Liu
commited on
Commit
•
004ad1b
1
Parent(s):
bdc47e8
Update
Browse filesSigned-off-by: Xin Liu <[email protected]>
README.md
CHANGED
@@ -1,3 +1,56 @@
|
|
1 |
---
|
2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
base_model: stabilityai/stablelm-2-zephyr-1_6b
|
3 |
+
license: other
|
4 |
+
model_creator: stabilityai
|
5 |
+
model_name: StableLM 2 Zephyr 1.6B
|
6 |
+
pipeline_tag: text-generation
|
7 |
+
quantized_by: Second State Inc.
|
8 |
+
datasets:
|
9 |
+
- HuggingFaceH4/ultrachat_200k
|
10 |
+
- allenai/ultrafeedback_binarized_cleaned
|
11 |
+
- meta-math/MetaMathQA
|
12 |
+
- WizardLM/WizardLM_evol_instruct_V2_196k
|
13 |
+
- openchat/openchat_sharegpt4_dataset
|
14 |
+
- LDJnr/Capybara
|
15 |
+
- Intel/orca_dpo_pairs
|
16 |
+
- hkust-nlp/deita-10k-v0
|
17 |
+
language:
|
18 |
+
- en
|
19 |
+
tags:
|
20 |
+
- causal-lm
|
21 |
---
|
22 |
+
|
23 |
+
<!-- header start -->
|
24 |
+
<!-- 200823 -->
|
25 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
26 |
+
<img src="https://github.com/second-state/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
27 |
+
</div>
|
28 |
+
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
|
29 |
+
<!-- header end -->
|
30 |
+
|
31 |
+
# StableLM-2-Zephyr-1.6B-GGUF
|
32 |
+
|
33 |
+
## Original Model
|
34 |
+
|
35 |
+
[stabilityai/stablelm-2-zephyr-1_6b](https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b)
|
36 |
+
|
37 |
+
## Run with LlamaEdge
|
38 |
+
|
39 |
+
- LlamaEdge version: coming soon
|
40 |
+
|
41 |
+
## Quantized GGUF Models
|
42 |
+
|
43 |
+
| Name | Quant method | Bits | Size | Use case |
|
44 |
+
| ---- | ---- | ---- | ---- | ----- |
|
45 |
+
| [stablelm-2-zephyr-1_6b-Q2_K.gguf](https://huggingface.co/second-state/stablelm-2-zephyr-1.6b-GGUF/blob/main/stablelm-2-zephyr-1_6b-Q2_K.gguf) | Q2_K | 2 | 694 MB| smallest, significant quality loss - not recommended for most purposes |
|
46 |
+
| [stablelm-2-zephyr-1_6b-Q3_K_L.gguf](https://huggingface.co/second-state/stablelm-2-zephyr-1.6b-GGUF/blob/main/stablelm-2-zephyr-1_6b-Q3_K_L.gguf) | Q3_K_L | 3 | 915 MB| small, substantial quality loss |
|
47 |
+
| [stablelm-2-zephyr-1_6b-Q3_K_M.gguf](https://huggingface.co/second-state/stablelm-2-zephyr-1.6b-GGUF/blob/main/stablelm-2-zephyr-1_6b-Q3_K_M.gguf) | Q3_K_M | 3 | 858 MB| very small, high quality loss |
|
48 |
+
| [stablelm-2-zephyr-1_6b-Q3_K_S.gguf](https://huggingface.co/second-state/stablelm-2-zephyr-1.6b-GGUF/blob/main/stablelm-2-zephyr-1_6b-Q3_K_S.gguf) | Q3_K_S | 3 | 792 MB| very small, high quality loss |
|
49 |
+
| [stablelm-2-zephyr-1_6b-Q4_0.gguf](https://huggingface.co/second-state/stablelm-2-zephyr-1.6b-GGUF/blob/main/stablelm-2-zephyr-1_6b-Q4_0.gguf) | Q4_0 | 4 | 983 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
|
50 |
+
| [stablelm-2-zephyr-1_6b-Q4_K_M.gguf](https://huggingface.co/second-state/stablelm-2-zephyr-1.6b-GGUF/blob/main/stablelm-2-zephyr-1_6b-Q4_K_M.gguf) | Q4_K_M | 4 | 1.03 GB| medium, balanced quality - recommended |
|
51 |
+
| [stablelm-2-zephyr-1_6b-Q4_K_S.gguf](https://huggingface.co/second-state/stablelm-2-zephyr-1.6b-GGUF/blob/main/stablelm-2-zephyr-1_6b-Q4_K_S.gguf) | Q4_K_S | 4 | 989 MB| small, greater quality loss |
|
52 |
+
| [stablelm-2-zephyr-1_6b-Q5_0.gguf](https://huggingface.co/second-state/stablelm-2-zephyr-1.6b-GGUF/blob/main/stablelm-2-zephyr-1_6b-Q5_0.gguf) | Q5_0 | 5 | 1.16 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
|
53 |
+
| [stablelm-2-zephyr-1_6b-Q5_K_M.gguf](https://huggingface.co/second-state/stablelm-2-zephyr-1.6b-GGUF/blob/main/stablelm-2-zephyr-1_6b-Q5_K_M.gguf) | Q5_K_M | 5 | 1.19 GB| large, very low quality loss - recommended |
|
54 |
+
| [stablelm-2-zephyr-1_6b-Q5_K_S.gguf](https://huggingface.co/second-state/stablelm-2-zephyr-1.6b-GGUF/blob/main/stablelm-2-zephyr-1_6b-Q5_K_S.gguf) | Q5_K_S | 5 | 1.16 GB| large, low quality loss - recommended |
|
55 |
+
| [stablelm-2-zephyr-1_6b-Q6_K.gguf](https://huggingface.co/second-state/stablelm-2-zephyr-1.6b-GGUF/blob/main/stablelm-2-zephyr-1_6b-Q6_K.gguf) | Q6_K | 6 | 1.35 GB| very large, extremely low quality loss |
|
56 |
+
| [stablelm-2-zephyr-1_6b-Q8_0.gguf](https://huggingface.co/second-state/stablelm-2-zephyr-1.6b-GGUF/blob/main/stablelm-2-zephyr-1_6b-Q8_0.gguf) | Q8_0 | 8 | 1.75 GB| very large, extremely low quality loss - not recommended |
|