apepkuss79 commited on
Commit
cf40ae7
1 Parent(s): 07604d4

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +92 -1
README.md CHANGED
@@ -1,3 +1,94 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: microsoft/Phi-3-mini-128k-instruct
3
+ license: mit
4
+ license_link: https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/LICENSE
5
+ language:
6
+ - en
7
+ pipeline_tag: text-generation
8
+ model_creator: Microsoft
9
+ model_name: Phi 3 mini 128k instruct
10
+ model_type: phi-msft
11
+ quantized_by: Second State Inc.
12
+ tags:
13
+ - nlp
14
+ - code
15
  ---
16
+
17
+ <!-- header start -->
18
+ <!-- 200823 -->
19
+ <div style="width: auto; margin-left: auto; margin-right: auto">
20
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
21
+ </div>
22
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
23
+ <!-- header end -->
24
+
25
+ # Phi-3-mini-128k-instruct-GGUF
26
+
27
+ ## Original Model
28
+
29
+ [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct)
30
+
31
+ ## Run with LlamaEdge
32
+
33
+ <!-- - LlamaEdge version: [v0.8.4](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.8.4) and above -->
34
+
35
+ - LlamaEdge version: coming soon
36
+
37
+ - Prompt template
38
+
39
+ - Prompt type: `phi-3-chat`
40
+
41
+ - Prompt string
42
+
43
+ ```text
44
+ <|system|>
45
+ {system_message}<|end|>
46
+ <|user|>
47
+ {user_message_1}<|end|>
48
+ <|assistant|>
49
+ {assistant_message_1}<|end|>
50
+ <|user|>
51
+ {user_message_2}<|end|>
52
+ <|assistant|>
53
+ ```
54
+
55
+ - Context size: `3072`
56
+
57
+ <!-- - Run as LlamaEdge service
58
+
59
+ ```bash
60
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-3-mini-128k-instruct-Q5_K_M.gguf \
61
+ llama-api-server.wasm \
62
+ --prompt-template phi-3-chat \
63
+ --ctx-size 3072 \
64
+ --model-name phi-3-mini
65
+ ```
66
+
67
+ - Run as LlamaEdge command app
68
+
69
+ ```bash
70
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-3-mini-128k-instruct-Q5_K_M.gguf \
71
+ llama-chat.wasm \
72
+ --prompt-template phi-3-chat \
73
+ --ctx-size 3072 \
74
+ ``` -->
75
+
76
+ ## Quantized GGUF Models
77
+
78
+ | Name | Quant method | Bits | Size | Use case |
79
+ | ---- | ---- | ---- | ---- | ----- |
80
+ | [Phi-3-mini-128k-instruct-Q2_K.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q2_K.gguf) | Q2_K | 2 | 1.42 GB| smallest, significant quality loss - not recommended for most purposes |
81
+ | [Phi-3-mini-128k-instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 2.09 GB| small, substantial quality loss |
82
+ | [Phi-3-mini-128k-instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 1.96 GB| very small, high quality loss |
83
+ | [Phi-3-mini-128k-instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 1.68 GB| very small, high quality loss |
84
+ | [Phi-3-mini-128k-instruct-Q4_0.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q4_0.gguf) | Q4_0 | 4 | 2.18 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
85
+ | [Phi-3-mini-128k-instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 2.39 GB| medium, balanced quality - recommended |
86
+ | [Phi-3-mini-128k-instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 2.19 GB| small, greater quality loss |
87
+ | [Phi-3-mini-128k-instruct-Q5_0.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q5_0.gguf) | Q5_0 | 5 | 2.64 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
88
+ | [Phi-3-mini-128k-instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 2.82 GB| large, very low quality loss - recommended |
89
+ | [Phi-3-mini-128k-instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 2.64 GB| large, low quality loss - recommended |
90
+ | [Phi-3-mini-128k-instruct-Q6_K.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q6_K.gguf) | Q6_K | 6 | 3.14 GB| very large, extremely low quality loss |
91
+ | [Phi-3-mini-128k-instruct-Q8_0.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-Q8_0.gguf) | Q8_0 | 8 | 4.06 GB| very large, extremely low quality loss - not recommended |
92
+ | [Phi-3-mini-128k-instruct-f16.gguf](https://huggingface.co/second-state/Phi-3-mini-128k-instruct-GGUF/blob/main/Phi-3-mini-128k-instruct-f16.gguf) | f16 | 16 | 7.64 GB| |
93
+
94
+ *Quantized with llama.cpp b2961.*