Hugging Face's logo

second-state
/
Tessa-T1-3B-GGUF

GGUF
English
qwen2
conversational
Model card Files Community
apepkuss79 commited on
Commit
73a5d6a
·
verified ·
1 Parent(s): b081126

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +105 -83
README.md CHANGED
@@ -1,84 +1,106 @@
1
- ---
2
- base_model: Tesslate/Tessa-T1-3B
3
- license: apache-2.0
4
- model_creator: Tesslate
5
- model_name: Tessa-T1-3B
6
- quantized_by: Second State Inc.
7
- language:
8
- - en
9
- ---
10
-
11
- <!-- header start -->
12
- <!-- 200823 -->
13
- <div style="width: auto; margin-left: auto; margin-right: auto">
14
- <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
15
- </div>
16
- <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
17
- <!-- header end -->
18
-
19
- # Tessa-T1-3B-GGUF
20
-
21
- ## Original Model
22
-
23
- [Tesslate/Tessa-T1-3B](https://huggingface.co/Tesslate/Tessa-T1-3B)
24
-
25
- ## Run with LlamaEdge
26
-
27
- - LlamaEdge version: coming soon
28
-
29
- <!-- - LlamaEdge version: [v0.14.14](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.14) and above
30
-
31
- - Prompt template
32
-
33
- - Prompt type: `chatml`
34
-
35
- - Prompt string
36
-
37
- ```text
38
- <|im_start|>system
39
- {system_message}<|im_end|>
40
- <|im_start|>user
41
- {prompt}<|im_end|>
42
- <|im_start|>assistant
43
- ```
44
-
45
- - Context size: `32000`
46
-
47
- - Run as LlamaEdge service
48
-
49
- ```bash
50
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:Tessa-T1-3B-Q5_K_M.gguf \
51
- llama-api-server.wasm \
52
- --model-name Tessa-T1-3B \
53
- --prompt-template chatml \
54
- --ctx-size 32000
55
- ```
56
-
57
- - Run as LlamaEdge command app
58
-
59
- ```bash
60
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:Tessa-T1-3B-Q5_K_M.gguf \
61
- llama-chat.wasm \
62
- --prompt-template chatml \
63
- --ctx-size 32000
64
- ``` -->
65
-
66
- ## Quantized GGUF Models
67
-
68
- | Name | Quant method | Bits | Size | Use case |
69
- | ---- | ---- | ---- | ---- | ----- |
70
- | [Tessa-T1-3B-Q2_K.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q2_K.gguf) | Q2_K | 2 | 1.27 GB| smallest, significant quality loss - not recommended for most purposes |
71
- | [Tessa-T1-3B-Q3_K_L.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q3_K_L.gguf) | Q3_K_L | 3 | 1.71 GB| small, substantial quality loss |
72
- | [Tessa-T1-3B-Q3_K_M.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q3_K_M.gguf) | Q3_K_M | 3 | 1.59 GB| very small, high quality loss |
73
- | [Tessa-T1-3B-Q3_K_S.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q3_K_S.gguf) | Q3_K_S | 3 | 1.45 GB| very small, high quality loss |
74
- | [Tessa-T1-3B-Q4_0.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q4_0.gguf) | Q4_0 | 4 | 1.82 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
75
- | [Tessa-T1-3B-Q4_K_M.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q4_K_M.gguf) | Q4_K_M | 4 | 1.93 GB| medium, balanced quality - recommended |
76
- | [Tessa-T1-3B-Q4_K_S.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q4_K_S.gguf) | Q4_K_S | 4 | 1.83 GB| small, greater quality loss |
77
- | [Tessa-T1-3B-Q5_0.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q5_0.gguf) | Q5_0 | 5 | 2.17 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
78
- | [Tessa-T1-3B-Q5_K_M.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q5_K_M.gguf) | Q5_K_M | 5 | 2.22 GB| large, very low quality loss - recommended |
79
- | [Tessa-T1-3B-Q5_K_S.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q5_K_S.gguf) | Q5_K_S | 5 | 2.17 GB| large, low quality loss - recommended |
80
- | [Tessa-T1-3B-Q6_K.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q6_K.gguf) | Q6_K | 6 | 2.54 GB| very large, extremely low quality loss |
81
- | [Tessa-T1-3B-Q8_0.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q8_0.gguf) | Q8_0 | 8 | 3.29 GB| very large, extremely low quality loss - not recommended |
82
- | [Tessa-T1-3B-f16.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-f16.gguf) | f16 | 16 | 6.18 GB| |
83
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
84
  *Quantized with llama.cpp b4944*
 
1
+ ---
2
+ base_model: Tesslate/Tessa-T1-3B
3
+ license: apache-2.0
4
+ model_creator: Tesslate
5
+ model_name: Tessa-T1-3B
6
+ quantized_by: Second State Inc.
7
+ language:
8
+ - en
9
+ ---
10
+
11
+ <!-- header start -->
12
+ <!-- 200823 -->
13
+ <div style="width: auto; margin-left: auto; margin-right: auto">
14
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
15
+ </div>
16
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
17
+ <!-- header end -->
18
+
19
+ # Tessa-T1-3B-GGUF
20
+
21
+ ## Original Model
22
+
23
+ [Tesslate/Tessa-T1-3B](https://huggingface.co/Tesslate/Tessa-T1-3B)
24
+
25
+ ## Run with LlamaEdge
26
+
27
+ - LlamaEdge version: coming soon
28
+
29
+ <!-- - LlamaEdge version: [v0.14.14](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.14) and above -->
30
+
31
+ - Prompt template
32
+
33
+ - Prompt type: `chatml`
34
+
35
+ ```text
36
+ <|im_start|>system
37
+ {system_message}<|im_end|>
38
+ <|im_start|>user
39
+ {prompt}<|im_end|>
40
+ <|im_start|>assistant
41
+ ```
42
+
43
+ - Prompt type: `chatml-think`
44
+
45
+ ```text
46
+ <|im_start|>system
47
+ {system_message}<|im_end|>
48
+ <|im_start|>user
49
+ {prompt}<|im_end|>
50
+ <|im_start|>assistant
51
+ <|im_start|>think
52
+ ```
53
+
54
+ - Context size: `32000`
55
+
56
+ - Run as LlamaEdge service
57
+
58
+ ```bash
59
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Tessa-T1-3B-Q5_K_M.gguf \
60
+ llama-api-server.wasm \
61
+ --model-name Tessa-T1-3B \
62
+ --prompt-template chatml \
63
+ --ctx-size 32000
64
+
65
+ # Think mode
66
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Tessa-T1-3B-Q5_K_M.gguf \
67
+ llama-api-server.wasm \
68
+ --model-name Tessa-T1-3B \
69
+ --prompt-template chatml-think \
70
+ --ctx-size 32000
71
+ ```
72
+
73
+ - Run as LlamaEdge command app
74
+
75
+ ```bash
76
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Tessa-T1-3B-Q5_K_M.gguf \
77
+ llama-chat.wasm \
78
+ --prompt-template chatml \
79
+ --ctx-size 32000
80
+
81
+ # Think mode
82
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Tessa-T1-3B-Q5_K_M.gguf \
83
+ llama-chat.wasm \
84
+ --prompt-template chatml-think \
85
+ --ctx-size 32000
86
+ ```
87
+
88
+ ## Quantized GGUF Models
89
+
90
+ | Name | Quant method | Bits | Size | Use case |
91
+ | ---- | ---- | ---- | ---- | ----- |
92
+ | [Tessa-T1-3B-Q2_K.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q2_K.gguf) | Q2_K | 2 | 1.27 GB| smallest, significant quality loss - not recommended for most purposes |
93
+ | [Tessa-T1-3B-Q3_K_L.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q3_K_L.gguf) | Q3_K_L | 3 | 1.71 GB| small, substantial quality loss |
94
+ | [Tessa-T1-3B-Q3_K_M.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q3_K_M.gguf) | Q3_K_M | 3 | 1.59 GB| very small, high quality loss |
95
+ | [Tessa-T1-3B-Q3_K_S.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q3_K_S.gguf) | Q3_K_S | 3 | 1.45 GB| very small, high quality loss |
96
+ | [Tessa-T1-3B-Q4_0.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q4_0.gguf) | Q4_0 | 4 | 1.82 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
97
+ | [Tessa-T1-3B-Q4_K_M.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q4_K_M.gguf) | Q4_K_M | 4 | 1.93 GB| medium, balanced quality - recommended |
98
+ | [Tessa-T1-3B-Q4_K_S.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q4_K_S.gguf) | Q4_K_S | 4 | 1.83 GB| small, greater quality loss |
99
+ | [Tessa-T1-3B-Q5_0.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q5_0.gguf) | Q5_0 | 5 | 2.17 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
100
+ | [Tessa-T1-3B-Q5_K_M.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q5_K_M.gguf) | Q5_K_M | 5 | 2.22 GB| large, very low quality loss - recommended |
101
+ | [Tessa-T1-3B-Q5_K_S.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q5_K_S.gguf) | Q5_K_S | 5 | 2.17 GB| large, low quality loss - recommended |
102
+ | [Tessa-T1-3B-Q6_K.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q6_K.gguf) | Q6_K | 6 | 2.54 GB| very large, extremely low quality loss |
103
+ | [Tessa-T1-3B-Q8_0.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-Q8_0.gguf) | Q8_0 | 8 | 3.29 GB| very large, extremely low quality loss - not recommended |
104
+ | [Tessa-T1-3B-f16.gguf](https://huggingface.co/second-state/Tessa-T1-3B-GGUF/blob/main/Tessa-T1-3B-f16.gguf) | f16 | 16 | 6.18 GB| |
105
+
106
  *Quantized with llama.cpp b4944*