Hugging Face's logo

second-state
/
Hermes-2-Pro-Llama-3-8B-GGUF

Text Generation
Transformers
GGUF
English
llama
text-generation-inference
conversational
Model card Files Community
apepkuss79 commited on
Commit
a59a628
•
1 Parent(s): 837fd92

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +84 -84
README.md CHANGED
@@ -1,84 +1,84 @@
1
- ---
2
- model_name: Hermes-2-Pro-Llama-3-8B
3
- base_model: NousResearch/Hermes-2-Pro-Llama-3-8B
4
- inference: false
5
- model_creator: NousResearch
6
- model_type: llama
7
- pipeline_tag: text-generation
8
- quantized_by: Second State Inc.
9
- language:
10
- - en
11
- ---
12
-
13
- <!-- header start -->
14
- <!-- 200823 -->
15
- <div style="width: auto; margin-left: auto; margin-right: auto">
16
- <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
17
- </div>
18
- <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
19
- <!-- header end -->
20
-
21
- # Hermes-2-Pro-Llama-3-8B-GGUF
22
-
23
- ## Original Model
24
-
25
- [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
26
-
27
- ## Run with LlamaEdge
28
-
29
- - LlamaEdge version: coming soon
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
- {user_message}<|im_end|>
42
- <|im_start|>assistant
43
- ```
44
-
45
- - Context size: `4096`
46
-
47
- - Run as LlamaEdge service
48
-
49
- ```bash
50
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf \
51
- llama-api-server.wasm \
52
- --prompt-template chatml \
53
- --ctx-size 4096 \
54
- --model-name hermes-2-pro-llama-3-8b
55
- ```
56
-
57
- - Run as LlamaEdge command app
58
-
59
- ```bash
60
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf \
61
- llama-chat.wasm \
62
- --prompt-template chatml \
63
- --ctx-size 4096 \
64
- ```
65
-
66
- ## Quantized GGUF Models
67
-
68
- | Name | Quant method | Bits | Size | Use case |
69
- | ---- | ---- | ---- | ---- | ----- |
70
- | [Hermes-2-Pro-Llama-3-8B-Q2_K.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q2_K.gguf) | Q2_K | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes |
71
- | [Hermes-2-Pro-Llama-3-8B-Q3_K_L.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q3_K_L.gguf) | Q3_K_L | 3 | 4.32 GB| small, substantial quality loss |
72
- | [Hermes-2-Pro-Llama-3-8B-Q3_K_M.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q3_K_M.gguf) | Q3_K_M | 3 | 4.02 GB| very small, high quality loss |
73
- | [Hermes-2-Pro-Llama-3-8B-Q3_K_S.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q3_K_S.gguf) | Q3_K_S | 3 | 3.66 GB| very small, high quality loss |
74
- | [Hermes-2-Pro-Llama-3-8B-Q4_0.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q4_0.gguf) | Q4_0 | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
75
- | [Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf) | Q4_K_M | 4 | 4.92 GB| medium, balanced quality - recommended |
76
- | [Hermes-2-Pro-Llama-3-8B-Q4_K_S.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q4_K_S.gguf) | Q4_K_S | 4 | 4.69 GB| small, greater quality loss |
77
- | [Hermes-2-Pro-Llama-3-8B-Q5_0.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q5_0.gguf) | Q5_0 | 5 | 5.6 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
78
- | [Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf) | Q5_K_M | 5 | 5.73 GB| large, very low quality loss - recommended |
79
- | [Hermes-2-Pro-Llama-3-8B-Q5_K_S.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q5_K_S.gguf) | Q5_K_S | 5 | 5.6 GB| large, low quality loss - recommended |
80
- | [Hermes-2-Pro-Llama-3-8B-Q6_K.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q6_K.gguf) | Q6_K | 6 | 6.6 GB| very large, extremely low quality loss |
81
- | [Hermes-2-Pro-Llama-3-8B-Q8_0.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q8_0.gguf) | Q8_0 | 8 | 8.54 GB| very large, extremely low quality loss - not recommended |
82
- | [Hermes-2-Pro-Llama-3-8B-f16.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-f16.gguf) | f16 | 16 | 16.1 GB| |
83
-
84
- *Quantized with llama.cpp b2734.*
 
1
+ ---
2
+ model_name: Hermes-2-Pro-Llama-3-8B
3
+ base_model: NousResearch/Hermes-2-Pro-Llama-3-8B
4
+ inference: false
5
+ model_creator: NousResearch
6
+ model_type: llama
7
+ pipeline_tag: text-generation
8
+ quantized_by: Second State Inc.
9
+ language:
10
+ - en
11
+ ---
12
+
13
+ <!-- header start -->
14
+ <!-- 200823 -->
15
+ <div style="width: auto; margin-left: auto; margin-right: auto">
16
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
17
+ </div>
18
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
19
+ <!-- header end -->
20
+
21
+ # Hermes-2-Pro-Llama-3-8B-GGUF
22
+
23
+ ## Original Model
24
+
25
+ [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
26
+
27
+ ## Run with LlamaEdge
28
+
29
+ - LlamaEdge version: [v0.9.1](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.9.1) 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
+ {user_message}<|im_end|>
42
+ <|im_start|>assistant
43
+ ```
44
+
45
+ - Context size: `4096`
46
+
47
+ - Run as LlamaEdge service
48
+
49
+ ```bash
50
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf \
51
+ llama-api-server.wasm \
52
+ --prompt-template chatml \
53
+ --ctx-size 4096 \
54
+ --model-name hermes-2-pro-llama-3-8b
55
+ ```
56
+
57
+ - Run as LlamaEdge command app
58
+
59
+ ```bash
60
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf \
61
+ llama-chat.wasm \
62
+ --prompt-template chatml \
63
+ --ctx-size 4096 \
64
+ ```
65
+
66
+ ## Quantized GGUF Models
67
+
68
+ | Name | Quant method | Bits | Size | Use case |
69
+ | ---- | ---- | ---- | ---- | ----- |
70
+ | [Hermes-2-Pro-Llama-3-8B-Q2_K.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q2_K.gguf) | Q2_K | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes |
71
+ | [Hermes-2-Pro-Llama-3-8B-Q3_K_L.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q3_K_L.gguf) | Q3_K_L | 3 | 4.32 GB| small, substantial quality loss |
72
+ | [Hermes-2-Pro-Llama-3-8B-Q3_K_M.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q3_K_M.gguf) | Q3_K_M | 3 | 4.02 GB| very small, high quality loss |
73
+ | [Hermes-2-Pro-Llama-3-8B-Q3_K_S.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q3_K_S.gguf) | Q3_K_S | 3 | 3.66 GB| very small, high quality loss |
74
+ | [Hermes-2-Pro-Llama-3-8B-Q4_0.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q4_0.gguf) | Q4_0 | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
75
+ | [Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf) | Q4_K_M | 4 | 4.92 GB| medium, balanced quality - recommended |
76
+ | [Hermes-2-Pro-Llama-3-8B-Q4_K_S.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q4_K_S.gguf) | Q4_K_S | 4 | 4.69 GB| small, greater quality loss |
77
+ | [Hermes-2-Pro-Llama-3-8B-Q5_0.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q5_0.gguf) | Q5_0 | 5 | 5.6 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
78
+ | [Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q5_K_M.gguf) | Q5_K_M | 5 | 5.73 GB| large, very low quality loss - recommended |
79
+ | [Hermes-2-Pro-Llama-3-8B-Q5_K_S.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q5_K_S.gguf) | Q5_K_S | 5 | 5.6 GB| large, low quality loss - recommended |
80
+ | [Hermes-2-Pro-Llama-3-8B-Q6_K.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q6_K.gguf) | Q6_K | 6 | 6.6 GB| very large, extremely low quality loss |
81
+ | [Hermes-2-Pro-Llama-3-8B-Q8_0.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-Q8_0.gguf) | Q8_0 | 8 | 8.54 GB| very large, extremely low quality loss - not recommended |
82
+ | [Hermes-2-Pro-Llama-3-8B-f16.gguf](https://huggingface.co/second-state/Hermes-2-Pro-Llama-3-8B-GGUF/blob/main/Hermes-2-Pro-Llama-3-8B-f16.gguf) | f16 | 16 | 16.1 GB| |
83
+
84
+ *Quantized with llama.cpp b2734.*