Hugging Face's logo

second-state
/
c4ai-command-r-08-2024-GGUF

Text Generation
Transformers
GGUF
cohere
Inference Endpoints
conversational
Model card Files Community
apepkuss79 commited on
Commit
cb4c68a
•
1 Parent(s): 541b8dd

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +94 -1
README.md CHANGED
@@ -1,3 +1,96 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: CohereForAI/c4ai-command-r-08-2024
3
+ license: cc-by-nc-4.0
4
+ model_creator: CohereForAI
5
+ model_name: c4ai-command-r-08-2024
6
+ quantized_by: Second State Inc.
7
+ library_name: transformers
8
+ language:
9
+ - en
10
+ - fr
11
+ - de
12
+ - es
13
+ - it
14
+ - pt
15
+ - ja
16
+ - ko
17
+ - zh
18
+ - ar
19
  ---
20
+
21
+ <!-- header start -->
22
+ <!-- 200823 -->
23
+ <div style="width: auto; margin-left: auto; margin-right: auto">
24
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
25
+ </div>
26
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
27
+ <!-- header end -->
28
+
29
+ # c4ai-command-r-08-2024-GGUF
30
+
31
+ ## Original Model
32
+
33
+ [CohereForAI/c4ai-command-r-08-2024](https://huggingface.co/CohereForAI/c4ai-command-r-08-2024)
34
+
35
+ ## Run with LlamaEdge
36
+
37
+ - LlamaEdge version: coming soon
38
+
39
+ <!-- - LlamaEdge version: [v0.13.2](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.13.2) and above
40
+
41
+ - Prompt template
42
+
43
+ - Prompt type: `chatml`
44
+
45
+ - Prompt string
46
+
47
+ ```text
48
+ <|im_start|>system
49
+ {system_message}<|im_end|>
50
+ <|im_start|>user
51
+ {prompt}<|im_end|>
52
+ <|im_start|>assistant
53
+ ```
54
+
55
+ - Context size: `128000`
56
+
57
+ - Run as LlamaEdge service
58
+
59
+ ```bash
60
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:c4ai-command-r-08-2024-Q5_K_M.gguf \
61
+ llama-api-server.wasm \
62
+ --model-name c4ai-command-r-08-2024 \
63
+ --prompt-template chatml \
64
+ --ctx-size 128000
65
+ ```
66
+
67
+ - Run as LlamaEdge command app
68
+
69
+ ```bash
70
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:c4ai-command-r-08-2024-Q5_K_M.gguf \
71
+ llama-chat.wasm \
72
+ --prompt-template chatml \
73
+ --ctx-size 128000
74
+ ``` -->
75
+
76
+ ## Quantized GGUF Models
77
+
78
+ | Name | Quant method | Bits | Size | Use case |
79
+ | ---- | ---- | ---- | ---- | ----- |
80
+ | [c4ai-command-r-08-2024-Q2_K.gguf](https://huggingface.co/second-state/c4ai-command-r-08-2024-GGUF/blob/main/c4ai-command-r-08-2024-Q2_K.gguf) | Q2_K | 2 | 12.8 GB| smallest, significant quality loss - not recommended for most purposes |
81
+ | [c4ai-command-r-08-2024-Q3_K_L.gguf](https://huggingface.co/second-state/c4ai-command-r-08-2024-GGUF/blob/main/c4ai-command-r-08-2024-Q3_K_L.gguf) | Q3_K_L | 3 | 17.6 GB| small, substantial quality loss |
82
+ | [c4ai-command-r-08-2024-Q3_K_M.gguf](https://huggingface.co/second-state/c4ai-command-r-08-2024-GGUF/blob/main/c4ai-command-r-08-2024-Q3_K_M.gguf) | Q3_K_M | 3 | 16.2 GB| very small, high quality loss |
83
+ | [c4ai-command-r-08-2024-Q3_K_S.gguf](https://huggingface.co/second-state/c4ai-command-r-08-2024-GGUF/blob/main/c4ai-command-r-08-2024-Q3_K_S.gguf) | Q3_K_S | 3 | 14.7 GB| very small, high quality loss |
84
+ | [c4ai-command-r-08-2024-Q4_0.gguf](https://huggingface.co/second-state/c4ai-command-r-08-2024-GGUF/blob/main/c4ai-command-r-08-2024-Q4_0.gguf) | Q4_0 | 4 | 18.7 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
85
+ | [c4ai-command-r-08-2024-Q4_K_M.gguf](https://huggingface.co/second-state/c4ai-command-r-08-2024-GGUF/blob/main/c4ai-command-r-08-2024-Q4_K_M.gguf) | Q4_K_M | 4 | 19.8 GB| medium, balanced quality - recommended |
86
+ | [c4ai-command-r-08-2024-Q4_K_S.gguf](https://huggingface.co/second-state/c4ai-command-r-08-2024-GGUF/blob/main/c4ai-command-r-08-2024-Q4_K_S.gguf) | Q4_K_S | 4 | 18.8 GB| small, greater quality loss |
87
+ | [c4ai-command-r-08-2024-Q5_0.gguf](https://huggingface.co/second-state/c4ai-command-r-08-2024-GGUF/blob/main/c4ai-command-r-08-2024-Q5_0.gguf) | Q5_0 | 5 | 22.5 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
88
+ | [c4ai-command-r-08-2024-Q5_K_M.gguf](https://huggingface.co/second-state/c4ai-command-r-08-2024-GGUF/blob/main/c4ai-command-r-08-2024-Q5_K_M.gguf) | Q5_K_M | 5 | 23.1 GB| large, very low quality loss - recommended |
89
+ | [c4ai-command-r-08-2024-Q5_K_S.gguf](https://huggingface.co/second-state/c4ai-command-r-08-2024-GGUF/blob/main/c4ai-command-r-08-2024-Q5_K_S.gguf) | Q5_K_S | 5 | 22.5 GB| large, low quality loss - recommended |
90
+ | [c4ai-command-r-08-2024-Q6_K.gguf](https://huggingface.co/second-state/c4ai-command-r-08-2024-GGUF/blob/main/c4ai-command-r-08-2024-Q6_K.gguf) | Q6_K | 6 | 26.5 GB| very large, extremely low quality loss |
91
+ | [c4ai-command-r-08-2024-Q8_0.gguf](https://huggingface.co/second-state/c4ai-command-r-08-2024-GGUF/blob/main/c4ai-command-r-08-2024-Q8_0.gguf) | Q8_0 | 8 | 34.3 GB| very large, extremely low quality loss - not recommended |
92
+ | [c4ai-command-r-08-2024-f16-00001-of-00003.gguf](https://huggingface.co/second-state/c4ai-command-r-08-2024-GGUF/blob/main/c4ai-command-r-08-2024-f16-00001-of-00003.gguf) | f16 | 16 | 29.9 GB| |
93
+ | [c4ai-command-r-08-2024-f16-00002-of-00003.gguf](https://huggingface.co/second-state/c4ai-command-r-08-2024-GGUF/blob/main/c4ai-command-r-08-2024-f16-00002-of-00003.gguf) | f16 | 16 | 29.8 GB| |
94
+ | [c4ai-command-r-08-2024-f16-00003-of-00003.gguf](https://huggingface.co/second-state/c4ai-command-r-08-2024-GGUF/blob/main/c4ai-command-r-08-2024-f16-00003-of-00003.gguf) | f16 | 16 | 4.93 GB| |
95
+
96
+ *Quantized with llama.cpp b3613*