Hugging Face's logo

second-state
/
Falcon3-3B-Instruct-GGUF

Text Generation
Transformers
GGUF
llama
falcon3
Inference Endpoints
conversational
Model card Files Community
apepkuss79 commited on
Commit
b5ff099
·
verified ·
1 Parent(s): b4b3efe

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +92 -92
README.md CHANGED
@@ -1,92 +1,92 @@
1
- ---
2
- base_model: tiiuae/Falcon3-3B-Instruct
3
- license: other
4
- license_name: falcon-llm-license
5
- license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
6
- model_creator: tiiuae
7
- model_name: Falcon3-3B-Instruct
8
- quantized_by: Second State Inc.
9
- language:
10
- - en
11
- - fr
12
- - es
13
- - pt
14
- library_name: transformers
15
- tags:
16
- - falcon3
17
- ---
18
-
19
- <!-- header start -->
20
- <!-- 200823 -->
21
- <div style="width: auto; margin-left: auto; margin-right: auto">
22
- <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
23
- </div>
24
- <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
25
- <!-- header end -->
26
-
27
- # Falcon3-3B-Instruct-GGUF
28
-
29
- ## Original Model
30
-
31
- [tiiuae/Falcon3-3B-Instruct](https://huggingface.co/tiiuae/Falcon3-3B-Instruct)
32
-
33
- ## Run with LlamaEdge
34
-
35
- - LlamaEdge version: coming soon
36
-
37
- <!-- - LlamaEdge version: [v0.14.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.3) and above -->
38
-
39
- - Prompt template
40
-
41
- - Prompt type: `falcon3`
42
-
43
- - Prompt string
44
-
45
- ```text
46
- <|system|>
47
- You are a helpful friendly assistant Falcon3 from TII, try to follow instructions as much as possible.
48
- <|user|>
49
- {user_message}
50
- <|assistant|>
51
- ```
52
-
53
- - Context size: `32000`
54
-
55
- - Run as LlamaEdge service
56
-
57
- ```bash
58
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:Falcon3-3B-Instruct-Q5_K_M.gguf \
59
- llama-api-server.wasm \
60
- --model-name Falcon3-3B-Instruct \
61
- --prompt-template falcon3 \
62
- --ctx-size 32000
63
- ```
64
-
65
- - Run as LlamaEdge command app
66
-
67
- ```bash
68
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:Falcon3-3B-Instruct-Q5_K_M.gguf \
69
- llama-chat.wasm \
70
- --prompt-template falcon3 \
71
- --ctx-size 32000
72
- ```
73
-
74
- ## Quantized GGUF Models
75
-
76
- | Name | Quant method | Bits | Size | Use case |
77
- | ---- | ---- | ---- | ---- | ----- |
78
- | [Falcon3-3B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q2_K.gguf) | Q2_K | 2 | 1.35 GB| smallest, significant quality loss - not recommended for most purposes |
79
- | [Falcon3-3B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 1.78 GB| small, substantial quality loss |
80
- | [Falcon3-3B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 1.67 GB| very small, high quality loss |
81
- | [Falcon3-3B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 1.55 GB| very small, high quality loss |
82
- | [Falcon3-3B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 1.92 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
83
- | [Falcon3-3B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 2.01 GB| medium, balanced quality - recommended |
84
- | [Falcon3-3B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 1.93 GB| small, greater quality loss |
85
- | [Falcon3-3B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 2.28 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
86
- | [Falcon3-3B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 2.32 GB| large, very low quality loss - recommended |
87
- | [Falcon3-3B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 2.28 GB| large, low quality loss - recommended |
88
- | [Falcon3-3B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q6_K.gguf) | Q6_K | 6 | 2.65 GB| very large, extremely low quality loss |
89
- | [Falcon3-3B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 3.43 GB| very large, extremely low quality loss - not recommended |
90
- | [Falcon3-3B-Instruct-f16.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-f16.gguf) | f16 | 16 | 6.46 GB| |
91
-
92
- *Quantized with llama.cpp (commit: b92a14a8)*
 
1
+ ---
2
+ base_model: tiiuae/Falcon3-3B-Instruct
3
+ license: other
4
+ license_name: falcon-llm-license
5
+ license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html
6
+ model_creator: tiiuae
7
+ model_name: Falcon3-3B-Instruct
8
+ quantized_by: Second State Inc.
9
+ language:
10
+ - en
11
+ - fr
12
+ - es
13
+ - pt
14
+ library_name: transformers
15
+ tags:
16
+ - falcon3
17
+ ---
18
+
19
+ <!-- header start -->
20
+ <!-- 200823 -->
21
+ <div style="width: auto; margin-left: auto; margin-right: auto">
22
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
23
+ </div>
24
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
25
+ <!-- header end -->
26
+
27
+ # Falcon3-3B-Instruct-GGUF
28
+
29
+ ## Original Model
30
+
31
+ [tiiuae/Falcon3-3B-Instruct](https://huggingface.co/tiiuae/Falcon3-3B-Instruct)
32
+
33
+ ## Run with LlamaEdge
34
+
35
+ - LlamaEdge version: coming soon
36
+
37
+ <!-- - LlamaEdge version: [v0.14.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.3) and above -->
38
+
39
+ - Prompt template
40
+
41
+ - Prompt type: `falcon3`
42
+
43
+ - Prompt string
44
+
45
+ ```text
46
+ <|system|>
47
+ You are a helpful friendly assistant Falcon3 from TII, try to follow instructions as much as possible.
48
+ <|user|>
49
+ {user_message}
50
+ <|assistant|>
51
+ ```
52
+
53
+ - Context size: `32000`
54
+
55
+ - Run as LlamaEdge service
56
+
57
+ ```bash
58
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Falcon3-3B-Instruct-Q5_K_M.gguf \
59
+ llama-api-server.wasm \
60
+ --model-name Falcon3-3B-Instruct \
61
+ --prompt-template falcon3 \
62
+ --ctx-size 32000
63
+ ```
64
+
65
+ - Run as LlamaEdge command app
66
+
67
+ ```bash
68
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Falcon3-3B-Instruct-Q5_K_M.gguf \
69
+ llama-chat.wasm \
70
+ --prompt-template falcon3 \
71
+ --ctx-size 32000
72
+ ```
73
+
74
+ ## Quantized GGUF Models
75
+
76
+ | Name | Quant method | Bits | Size | Use case |
77
+ | ---- | ---- | ---- | ---- | ----- |
78
+ | [Falcon3-3B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q2_K.gguf) | Q2_K | 2 | 1.35 GB| smallest, significant quality loss - not recommended for most purposes |
79
+ | [Falcon3-3B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 1.78 GB| small, substantial quality loss |
80
+ | [Falcon3-3B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 1.67 GB| very small, high quality loss |
81
+ | [Falcon3-3B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 1.55 GB| very small, high quality loss |
82
+ | [Falcon3-3B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 1.92 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
83
+ | [Falcon3-3B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 2.01 GB| medium, balanced quality - recommended |
84
+ | [Falcon3-3B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 1.93 GB| small, greater quality loss |
85
+ | [Falcon3-3B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 2.28 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
86
+ | [Falcon3-3B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 2.32 GB| large, very low quality loss - recommended |
87
+ | [Falcon3-3B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 2.28 GB| large, low quality loss - recommended |
88
+ | [Falcon3-3B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q6_K.gguf) | Q6_K | 6 | 2.65 GB| very large, extremely low quality loss |
89
+ | [Falcon3-3B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 3.43 GB| very large, extremely low quality loss - not recommended |
90
+ | [Falcon3-3B-Instruct-f16.gguf](https://huggingface.co/second-state/Falcon3-3B-Instruct-GGUF/blob/main/Falcon3-3B-Instruct-f16.gguf) | f16 | 16 | 6.46 GB| |
91
+
92
+ *Quantized with llama.cpp b4381*