Hugging Face's logo

gaianet
/
Phi-3-medium-4k-instruct-GGUF

Text Generation
Transformers
GGUF
multilingual
phi3
nlp
code
custom_code
text-generation-inference
Inference Endpoints
conversational
Model card Files Community
apepkuss79 commited on
Commit
bdadae1
•
1 Parent(s): 8544707

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +59 -59
README.md CHANGED
@@ -1,59 +1,59 @@
1
- ---
2
- base_model: microsoft/Phi-3-medium-4k-instruct
3
- license: mit
4
- license_link: https://huggingface.co/microsoft/Phi-3-medium-4k-instruct/resolve/main/LICENSE
5
- language:
6
- - multilingual
7
- pipeline_tag: text-generation
8
- model_creator: Microsoft
9
- model_name: Phi 3 mini 4k instruct
10
- model_type: phi-msft
11
- quantized_by: Second State Inc.
12
- tags:
13
- - nlp
14
- - code
15
- ---
16
-
17
- ![](https://github.com/GaiaNet-AI/.github/assets/45785633/d6976adc-f97d-4f86-a648-0f2f5c8e7eee)
18
-
19
- # Phi-3-medium-4k-instruct-GGUF
20
-
21
- ## Original Model
22
-
23
- [microsoft/Phi-3-medium-4k-instruct](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct)
24
-
25
- ## Run with Gaianet
26
-
27
- **Prompt template**
28
-
29
- prompt template: `phi-3-chat`
30
-
31
- **Context size**
32
-
33
- chat_ctx_size: `5120`
34
-
35
- **Run with GaiaNet**
36
-
37
- - Quick start: https://docs.gaianet.ai/node-guide/quick-start
38
-
39
- - Customize your node: https://docs.gaianet.ai/node-guide/customize
40
-
41
- ## Quantized GGUF Models
42
-
43
- | Name | Quant method | Bits | Size | Use case |
44
- | ---- | ---- | ---- | ---- | ----- |
45
- | [Phi-3-medium-4k-instruct-Q2_K.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q2_K.gguf) | Q2_K | 2 | 5.14 GB| smallest, significant quality loss - not recommended for most purposes |
46
- | [Phi-3-medium-4k-instruct-Q3_K_L.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 7.49 GB| small, substantial quality loss |
47
- | [Phi-3-medium-4k-instruct-Q3_K_M.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 6.92 GB| very small, high quality loss |
48
- | [Phi-3-medium-4k-instruct-Q3_K_S.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 6.06 GB| very small, high quality loss |
49
- | [Phi-3-medium-4k-instruct-Q4_0.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q4_0.gguf) | Q4_0 | 4 | 7.9 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
50
- | [Phi-3-medium-4k-instruct-Q4_K_M.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 8.57 GB| medium, balanced quality - recommended |
51
- | [Phi-3-medium-4k-instruct-Q4_K_S.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 7.95 GB| small, greater quality loss |
52
- | [Phi-3-medium-4k-instruct-Q5_0.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q5_0.gguf) | Q5_0 | 5 | 9.62 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
53
- | [Phi-3-medium-4k-instruct-Q5_K_M.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 10.1 GB| large, very low quality loss - recommended |
54
- | [Phi-3-medium-4k-instruct-Q5_K_S.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 9.62 GB| large, low quality loss - recommended |
55
- | [Phi-3-medium-4k-instruct-Q6_K.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q6_K.gguf) | Q6_K | 6 | 11.5 GB| very large, extremely low quality loss |
56
- | [Phi-3-medium-4k-instruct-Q8_0.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q8_0.gguf) | Q8_0 | 8 | 14.8 GB| very large, extremely low quality loss - not recommended |
57
- | [Phi-3-medium-4k-instruct-f16.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-f16.gguf) | f16 | 16 | 27.9 GB| |
58
-
59
- *Quantized with llama.cpp b2961.*
 
1
+ ---
2
+ base_model: microsoft/Phi-3-medium-4k-instruct
3
+ license: mit
4
+ license_link: https://huggingface.co/microsoft/Phi-3-medium-4k-instruct/resolve/main/LICENSE
5
+ language:
6
+ - multilingual
7
+ pipeline_tag: text-generation
8
+ model_creator: Microsoft
9
+ model_name: Phi 3 medium 4k instruct
10
+ model_type: phi-msft
11
+ quantized_by: Second State Inc.
12
+ tags:
13
+ - nlp
14
+ - code
15
+ ---
16
+
17
+ ![](https://github.com/GaiaNet-AI/.github/assets/45785633/d6976adc-f97d-4f86-a648-0f2f5c8e7eee)
18
+
19
+ # Phi-3-medium-4k-instruct-GGUF
20
+
21
+ ## Original Model
22
+
23
+ [microsoft/Phi-3-medium-4k-instruct](https://huggingface.co/microsoft/Phi-3-medium-4k-instruct)
24
+
25
+ ## Run with Gaianet
26
+
27
+ **Prompt template**
28
+
29
+ prompt template: `phi-3-chat`
30
+
31
+ **Context size**
32
+
33
+ chat_ctx_size: `5120`
34
+
35
+ **Run with GaiaNet**
36
+
37
+ - Quick start: https://docs.gaianet.ai/node-guide/quick-start
38
+
39
+ - Customize your node: https://docs.gaianet.ai/node-guide/customize
40
+
41
+ ## Quantized GGUF Models
42
+
43
+ | Name | Quant method | Bits | Size | Use case |
44
+ | ---- | ---- | ---- | ---- | ----- |
45
+ | [Phi-3-medium-4k-instruct-Q2_K.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q2_K.gguf) | Q2_K | 2 | 5.14 GB| smallest, significant quality loss - not recommended for most purposes |
46
+ | [Phi-3-medium-4k-instruct-Q3_K_L.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 7.49 GB| small, substantial quality loss |
47
+ | [Phi-3-medium-4k-instruct-Q3_K_M.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 6.92 GB| very small, high quality loss |
48
+ | [Phi-3-medium-4k-instruct-Q3_K_S.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 6.06 GB| very small, high quality loss |
49
+ | [Phi-3-medium-4k-instruct-Q4_0.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q4_0.gguf) | Q4_0 | 4 | 7.9 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
50
+ | [Phi-3-medium-4k-instruct-Q4_K_M.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 8.57 GB| medium, balanced quality - recommended |
51
+ | [Phi-3-medium-4k-instruct-Q4_K_S.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 7.95 GB| small, greater quality loss |
52
+ | [Phi-3-medium-4k-instruct-Q5_0.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q5_0.gguf) | Q5_0 | 5 | 9.62 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
53
+ | [Phi-3-medium-4k-instruct-Q5_K_M.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 10.1 GB| large, very low quality loss - recommended |
54
+ | [Phi-3-medium-4k-instruct-Q5_K_S.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 9.62 GB| large, low quality loss - recommended |
55
+ | [Phi-3-medium-4k-instruct-Q6_K.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q6_K.gguf) | Q6_K | 6 | 11.5 GB| very large, extremely low quality loss |
56
+ | [Phi-3-medium-4k-instruct-Q8_0.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-Q8_0.gguf) | Q8_0 | 8 | 14.8 GB| very large, extremely low quality loss - not recommended |
57
+ | [Phi-3-medium-4k-instruct-f16.gguf](https://huggingface.co/gaianet/Phi-3-medium-4k-instruct-GGUF/blob/main/Phi-3-medium-4k-instruct-f16.gguf) | f16 | 16 | 27.9 GB| |
58
+
59
+ *Quantized with llama.cpp b2961.*