Hugging Face's logo

second-state
/
Mistral-Small-3.1-24B-Instruct-2503-GGUF

Image-Text-to-Text
Transformers
GGUF
mistral3
conversational
Model card Files Community
apepkuss79 commited on
Commit
a57061e
·
verified ·
1 Parent(s): 1ef89c4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +134 -134
README.md CHANGED
@@ -1,135 +1,135 @@
1
- ---
2
- license: apache-2.0
3
- model_name: Mistral-Small-3.1-24B-Instruct-2503
4
- base_model: mistralai/Mistral-Small-3.1-24B-Instruct-2503
5
- model_creator: mistralai
6
- quantized_by: Second State Inc.
7
- inference: false
8
- language:
9
- - en
10
- - fr
11
- - de
12
- - es
13
- - pt
14
- - it
15
- - ja
16
- - ko
17
- - ru
18
- - zh
19
- - ar
20
- - fa
21
- - id
22
- - ms
23
- - ne
24
- - pl
25
- - ro
26
- - sr
27
- - sv
28
- - tr
29
- - uk
30
- - vi
31
- - hi
32
- - bn
33
- tags:
34
- - transformers
35
- pipeline_tag: image-text-to-text
36
- ---
37
-
38
- <!-- header start -->
39
- <!-- 200823 -->
40
- <div style="width: auto; margin-left: auto; margin-right: auto">
41
- <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
42
- </div>
43
- <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
44
- <!-- header end -->
45
-
46
- # Mistral-Small-3.1-24B-Instruct-2503-GGUF
47
-
48
- ## Original Model
49
-
50
- [mistralai/Mistral-Small-3.1-24B-Instruct-2503](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503)
51
-
52
- ## Run with LlamaEdge
53
-
54
- - LlamaEdge version: [v0.16.5](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.5)
55
-
56
- - Prompt template
57
-
58
- - Chat
59
-
60
- - Prompt type: `mistral-small-chat`
61
-
62
- - Prompt string
63
-
64
- ```text
65
- <s>[SYSTEM_PROMPT]<system prompt>[/SYSTEM_PROMPT][INST]<user message>[/INST]<assistant response></s>[INST]<user message>[/INST]
66
- ```
67
-
68
- <!-- - Chat + Tool Use
69
-
70
- - Prompt type: `mistral-small-tool`
71
-
72
- - Prompt string
73
-
74
- ```text
75
- <s>[INST] {user_message_1}[/INST][TOOL_CALLS] [{tool_call_1},{tool_call_2}]</s>[TOOL_RESULTS] {tool_result_1}[/TOOL_RESULTS] {assistant_message_1}</s>[AVAILABLE_TOOLS] [{tool_1},{tool_2}][/AVAILABLE_TOOLS][INST] {system_message}<0x0A><0x0A>{user_message_2}[/INST]
76
- ``` -->
77
-
78
- - Context size: `32000`
79
-
80
- - Run as LlamaEdge service
81
-
82
- - Chat
83
-
84
- ```bash
85
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-Small-3.1-24B-Instruct-2503-Q5_K_M.gguf \
86
- llama-api-server.wasm \
87
- --prompt-template mistral-small-chat \
88
- --ctx-size 32000 \
89
- --model-name Mistral-Small
90
- ```
91
-
92
- <!-- - Chat + Tool Use
93
-
94
- ```bash
95
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-Small-3.1-24B-Instruct-2503-Q5_K_M.gguf \
96
- llama-api-server.wasm \
97
- --prompt-template mistral-small-tool \
98
- --ctx-size 32000 \
99
- --model-name Mistral-Small
100
- ```
101
-
102
- Example:
103
-
104
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64e47b341deccdb4dccaa431/MlKzPbiZ8yz8j18vqa6Ax.png) -->
105
-
106
- - Run as LlamaEdge command app
107
-
108
- - Chat
109
-
110
- ```bash
111
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-Small-3.1-24B-Instruct-2503-Q5_K_M.gguf \
112
- llama-chat.wasm \
113
- --prompt-template mistral-small-chat \
114
- --ctx-size 32000
115
- ```
116
-
117
- ## Quantized GGUF Models
118
-
119
- | Name | Quant method | Bits | Size | Use case |
120
- | ---- | ---- | ---- | ---- | ----- |
121
- | [Mistral-Small-3.1-24B-Instruct-2503-Q2_K.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q2_K.gguf) | Q2_K | 2 | 8.89 GB| smallest, significant quality loss - not recommended for most purposes |
122
- | [Mistral-Small-3.1-24B-Instruct-2503-Q3_K_L.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q3_K_L.gguf) | Q3_K_L | 3 | 12.4 GB| small, substantial quality loss |
123
- | [Mistral-Small-3.1-24B-Instruct-2503-Q3_K_M.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q3_K_M.gguf) | Q3_K_M | 3 | 11.5 GB| very small, high quality loss |
124
- | [Mistral-Small-3.1-24B-Instruct-2503-Q3_K_S.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q3_K_S.gguf) | Q3_K_S | 3 | 10.4 GB| very small, high quality loss |
125
- | [Mistral-Small-3.1-24B-Instruct-2503-Q4_0.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q4_0.gguf) | Q4_0 | 4 | 13.4 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
126
- | [Mistral-Small-3.1-24B-Instruct-2503-Q4_K_M.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q4_K_M.gguf) | Q4_K_M | 4 | 14.3 GB| medium, balanced quality - recommended |
127
- | [Mistral-Small-3.1-24B-Instruct-2503-Q4_K_S.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q4_K_S.gguf) | Q4_K_S | 4 | 13.5 GB| small, greater quality loss |
128
- | [Mistral-Small-3.1-24B-Instruct-2503-Q5_0.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q5_0.gguf) | Q5_0 | 5 | 16.3 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
129
- | [Mistral-Small-3.1-24B-Instruct-2503-Q5_K_M.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q5_K_M.gguf) | Q5_K_M | 5 | 16.8 GB| large, very low quality loss - recommended |
130
- | [Mistral-Small-3.1-24B-Instruct-2503-Q5_K_S.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q5_K_S.gguf) | Q5_K_S | 5 | 16.3 GB| large, low quality loss - recommended |
131
- | [Mistral-Small-3.1-24B-Instruct-2503-Q6_K.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q6_K.gguf) | Q6_K | 6 | 19.3 GB| very large, extremely low quality loss |
132
- | [Mistral-Small-3.1-24B-Instruct-2503-Q8_0.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q8_0.gguf) | Q8_0 | 8 | 25.1 GB| very large, extremely low quality loss - not recommended |
133
- | [Mistral-Small-3.1-24B-Instruct-2503-f16.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-f16.gguf) | f16 | 16 | 47.2 GB| |
134
-
135
  *Quantized with llama.cpp b4944.*
 
1
+ ---
2
+ license: apache-2.0
3
+ model_name: Mistral-Small-3.1-24B-Instruct-2503
4
+ base_model: mistralai/Mistral-Small-3.1-24B-Instruct-2503
5
+ model_creator: mistralai
6
+ quantized_by: Second State Inc.
7
+ inference: false
8
+ language:
9
+ - en
10
+ - fr
11
+ - de
12
+ - es
13
+ - pt
14
+ - it
15
+ - ja
16
+ - ko
17
+ - ru
18
+ - zh
19
+ - ar
20
+ - fa
21
+ - id
22
+ - ms
23
+ - ne
24
+ - pl
25
+ - ro
26
+ - sr
27
+ - sv
28
+ - tr
29
+ - uk
30
+ - vi
31
+ - hi
32
+ - bn
33
+ tags:
34
+ - transformers
35
+ pipeline_tag: image-text-to-text
36
+ ---
37
+
38
+ <!-- header start -->
39
+ <!-- 200823 -->
40
+ <div style="width: auto; margin-left: auto; margin-right: auto">
41
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
42
+ </div>
43
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
44
+ <!-- header end -->
45
+
46
+ # Mistral-Small-3.1-24B-Instruct-2503-GGUF
47
+
48
+ ## Original Model
49
+
50
+ [mistralai/Mistral-Small-3.1-24B-Instruct-2503](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503)
51
+
52
+ ## Run with LlamaEdge
53
+
54
+ - LlamaEdge version: [v0.16.5](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.5) and above
55
+
56
+ - Prompt template
57
+
58
+ - Chat
59
+
60
+ - Prompt type: `mistral-small-chat`
61
+
62
+ - Prompt string
63
+
64
+ ```text
65
+ <s>[SYSTEM_PROMPT]<system prompt>[/SYSTEM_PROMPT][INST]<user message>[/INST]<assistant response></s>[INST]<user message>[/INST]
66
+ ```
67
+
68
+ <!-- - Chat + Tool Use
69
+
70
+ - Prompt type: `mistral-small-tool`
71
+
72
+ - Prompt string
73
+
74
+ ```text
75
+ <s>[INST] {user_message_1}[/INST][TOOL_CALLS] [{tool_call_1},{tool_call_2}]</s>[TOOL_RESULTS] {tool_result_1}[/TOOL_RESULTS] {assistant_message_1}</s>[AVAILABLE_TOOLS] [{tool_1},{tool_2}][/AVAILABLE_TOOLS][INST] {system_message}<0x0A><0x0A>{user_message_2}[/INST]
76
+ ``` -->
77
+
78
+ - Context size: `32000`
79
+
80
+ - Run as LlamaEdge service
81
+
82
+ - Chat
83
+
84
+ ```bash
85
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-Small-3.1-24B-Instruct-2503-Q5_K_M.gguf \
86
+ llama-api-server.wasm \
87
+ --prompt-template mistral-small-chat \
88
+ --ctx-size 32000 \
89
+ --model-name Mistral-Small
90
+ ```
91
+
92
+ <!-- - Chat + Tool Use
93
+
94
+ ```bash
95
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-Small-3.1-24B-Instruct-2503-Q5_K_M.gguf \
96
+ llama-api-server.wasm \
97
+ --prompt-template mistral-small-tool \
98
+ --ctx-size 32000 \
99
+ --model-name Mistral-Small
100
+ ```
101
+
102
+ Example:
103
+
104
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64e47b341deccdb4dccaa431/MlKzPbiZ8yz8j18vqa6Ax.png) -->
105
+
106
+ - Run as LlamaEdge command app
107
+
108
+ - Chat
109
+
110
+ ```bash
111
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Mistral-Small-3.1-24B-Instruct-2503-Q5_K_M.gguf \
112
+ llama-chat.wasm \
113
+ --prompt-template mistral-small-chat \
114
+ --ctx-size 32000
115
+ ```
116
+
117
+ ## Quantized GGUF Models
118
+
119
+ | Name | Quant method | Bits | Size | Use case |
120
+ | ---- | ---- | ---- | ---- | ----- |
121
+ | [Mistral-Small-3.1-24B-Instruct-2503-Q2_K.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q2_K.gguf) | Q2_K | 2 | 8.89 GB| smallest, significant quality loss - not recommended for most purposes |
122
+ | [Mistral-Small-3.1-24B-Instruct-2503-Q3_K_L.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q3_K_L.gguf) | Q3_K_L | 3 | 12.4 GB| small, substantial quality loss |
123
+ | [Mistral-Small-3.1-24B-Instruct-2503-Q3_K_M.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q3_K_M.gguf) | Q3_K_M | 3 | 11.5 GB| very small, high quality loss |
124
+ | [Mistral-Small-3.1-24B-Instruct-2503-Q3_K_S.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q3_K_S.gguf) | Q3_K_S | 3 | 10.4 GB| very small, high quality loss |
125
+ | [Mistral-Small-3.1-24B-Instruct-2503-Q4_0.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q4_0.gguf) | Q4_0 | 4 | 13.4 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
126
+ | [Mistral-Small-3.1-24B-Instruct-2503-Q4_K_M.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q4_K_M.gguf) | Q4_K_M | 4 | 14.3 GB| medium, balanced quality - recommended |
127
+ | [Mistral-Small-3.1-24B-Instruct-2503-Q4_K_S.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q4_K_S.gguf) | Q4_K_S | 4 | 13.5 GB| small, greater quality loss |
128
+ | [Mistral-Small-3.1-24B-Instruct-2503-Q5_0.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q5_0.gguf) | Q5_0 | 5 | 16.3 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
129
+ | [Mistral-Small-3.1-24B-Instruct-2503-Q5_K_M.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q5_K_M.gguf) | Q5_K_M | 5 | 16.8 GB| large, very low quality loss - recommended |
130
+ | [Mistral-Small-3.1-24B-Instruct-2503-Q5_K_S.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q5_K_S.gguf) | Q5_K_S | 5 | 16.3 GB| large, low quality loss - recommended |
131
+ | [Mistral-Small-3.1-24B-Instruct-2503-Q6_K.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q6_K.gguf) | Q6_K | 6 | 19.3 GB| very large, extremely low quality loss |
132
+ | [Mistral-Small-3.1-24B-Instruct-2503-Q8_0.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-Q8_0.gguf) | Q8_0 | 8 | 25.1 GB| very large, extremely low quality loss - not recommended |
133
+ | [Mistral-Small-3.1-24B-Instruct-2503-f16.gguf](https://huggingface.co/second-state/Mistral-Small-3.1-24B-Instruct-2503-GGUF/blob/main/Mistral-Small-3.1-24B-Instruct-2503-f16.gguf) | f16 | 16 | 47.2 GB| |
134
+
135
  *Quantized with llama.cpp b4944.*