Upload README.md with huggingface_hub
Browse files
README.md
ADDED
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Felladrin/TinyMistral-248M-SFT-v4
|
3 |
+
datasets:
|
4 |
+
- OpenAssistant/oasst_top1_2023-08-25
|
5 |
+
inference: false
|
6 |
+
license: apache-2.0
|
7 |
+
model_creator: Felladrin
|
8 |
+
model_name: TinyMistral-248M-SFT-v4
|
9 |
+
pipeline_tag: text-generation
|
10 |
+
quantized_by: afrideva
|
11 |
+
tags:
|
12 |
+
- text-generation
|
13 |
+
- gguf
|
14 |
+
- ggml
|
15 |
+
- quantized
|
16 |
+
- q2_k
|
17 |
+
- q3_k_m
|
18 |
+
- q4_k_m
|
19 |
+
- q5_k_m
|
20 |
+
- q6_k
|
21 |
+
- q8_0
|
22 |
+
widget:
|
23 |
+
- text: '<|im_start|>user
|
24 |
+
|
25 |
+
Invited some friends to come home today. Give me some ideas for games to play
|
26 |
+
with them!<|im_end|>
|
27 |
+
|
28 |
+
<|im_start|>assistant'
|
29 |
+
- text: '<|im_start|>user
|
30 |
+
|
31 |
+
How do meteorologists predict how much air pollution will be produced in the next
|
32 |
+
year?<|im_end|>
|
33 |
+
|
34 |
+
<|im_start|>assistant'
|
35 |
+
- text: '<|im_start|>user
|
36 |
+
|
37 |
+
Who is Mona Lisa?<|im_end|>
|
38 |
+
|
39 |
+
<|im_start|>assistant'
|
40 |
+
- text: '<|im_start|>user
|
41 |
+
|
42 |
+
Heya!<|im_end|>
|
43 |
+
|
44 |
+
<|im_start|>assistant
|
45 |
+
|
46 |
+
Hi! How may I help you today?<|im_end|>
|
47 |
+
|
48 |
+
<|im_start|>user
|
49 |
+
|
50 |
+
I need to build a simple website. Where should I start learning about web development?<|im_end|>
|
51 |
+
|
52 |
+
<|im_start|>assistant'
|
53 |
+
- text: '<|im_start|>user
|
54 |
+
|
55 |
+
What are some potential applications for quantum computing?<|im_end|>
|
56 |
+
|
57 |
+
<|im_start|>assistant'
|
58 |
+
- text: '<|im_start|>user
|
59 |
+
|
60 |
+
Write the specs of a game about dragons and warriors in a fantasy world.<|im_end|>
|
61 |
+
|
62 |
+
<|im_start|>assistant'
|
63 |
+
- text: "<|im_start|>user\nGot a question for you!<|im_end|>\n<|im_start|>assistant\nSure!
|
64 |
+
What's it?<|im_end|>\n<|im_start|>user\nWhy do you love cats so much!? \U0001F408<|im_end|>\n<|im_start|>assistant"
|
65 |
+
- text: '<|im_start|>user
|
66 |
+
|
67 |
+
Tell me about the pros and cons of social media.<|im_end|>
|
68 |
+
|
69 |
+
<|im_start|>assistant'
|
70 |
+
---
|
71 |
+
# Felladrin/TinyMistral-248M-SFT-v4-GGUF
|
72 |
+
|
73 |
+
Quantized GGUF model files for [TinyMistral-248M-SFT-v4](https://huggingface.co/Felladrin/TinyMistral-248M-SFT-v4) from [Felladrin](https://huggingface.co/Felladrin)
|
74 |
+
|
75 |
+
|
76 |
+
| Name | Quant method | Size |
|
77 |
+
| ---- | ---- | ---- |
|
78 |
+
| [tinymistral-248m-sft-v4.fp16.gguf](https://huggingface.co/afrideva/TinyMistral-248M-SFT-v4-GGUF/resolve/main/tinymistral-248m-sft-v4.fp16.gguf) | fp16 | 497.75 MB |
|
79 |
+
| [tinymistral-248m-sft-v4.q2_k.gguf](https://huggingface.co/afrideva/TinyMistral-248M-SFT-v4-GGUF/resolve/main/tinymistral-248m-sft-v4.q2_k.gguf) | q2_k | 116.20 MB |
|
80 |
+
| [tinymistral-248m-sft-v4.q3_k_m.gguf](https://huggingface.co/afrideva/TinyMistral-248M-SFT-v4-GGUF/resolve/main/tinymistral-248m-sft-v4.q3_k_m.gguf) | q3_k_m | 131.01 MB |
|
81 |
+
| [tinymistral-248m-sft-v4.q4_k_m.gguf](https://huggingface.co/afrideva/TinyMistral-248M-SFT-v4-GGUF/resolve/main/tinymistral-248m-sft-v4.q4_k_m.gguf) | q4_k_m | 156.60 MB |
|
82 |
+
| [tinymistral-248m-sft-v4.q5_k_m.gguf](https://huggingface.co/afrideva/TinyMistral-248M-SFT-v4-GGUF/resolve/main/tinymistral-248m-sft-v4.q5_k_m.gguf) | q5_k_m | 180.16 MB |
|
83 |
+
| [tinymistral-248m-sft-v4.q6_k.gguf](https://huggingface.co/afrideva/TinyMistral-248M-SFT-v4-GGUF/resolve/main/tinymistral-248m-sft-v4.q6_k.gguf) | q6_k | 205.20 MB |
|
84 |
+
| [tinymistral-248m-sft-v4.q8_0.gguf](https://huggingface.co/afrideva/TinyMistral-248M-SFT-v4-GGUF/resolve/main/tinymistral-248m-sft-v4.q8_0.gguf) | q8_0 | 265.26 MB |
|
85 |
+
|
86 |
+
|
87 |
+
|
88 |
+
## Original Model Card:
|
89 |
+
# Locutusque's TinyMistral-248M trained on OpenAssistant TOP-1 Conversation Threads
|
90 |
+
|
91 |
+
- Base model: [Locutusque/TinyMistral-248M](https://huggingface.co/Locutusque/TinyMistral-248M)
|
92 |
+
- Dataset: [OpenAssistant/oasst_top1_2023-08-25](https://huggingface.co/datasets/OpenAssistant/oasst_top1_2023-08-25)
|
93 |
+
- Availability in other ML formats:
|
94 |
+
- GGUF: [Felladrin/gguf-TinyMistral-248M-SFT-v4](https://huggingface.co/Felladrin/gguf-TinyMistral-248M-SFT-v4)
|
95 |
+
- ONNX: [Felladrin/onnx-TinyMistral-248M-SFT-v4](https://huggingface.co/Felladrin/onnx-TinyMistral-248M-SFT-v4)
|
96 |
+
|
97 |
+
## Recommended Prompt Format
|
98 |
+
|
99 |
+
```
|
100 |
+
<|im_start|>user
|
101 |
+
{message}<|im_end|>
|
102 |
+
<|im_start|>assistant
|
103 |
+
```
|