apepkuss79 commited on
Commit
a87ef15
·
verified ·
1 Parent(s): 5b8fc18

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
+ license: other
3
+ pipeline_tag: text-generation
4
+ base_model: internlm/internlm2_5-7b-chat-1m
5
+ model_creator: InternLM
6
+ model_name: internlm2_5-7b-chat-1m
7
+ quantized_by: Second State Inc.
8
  ---
9
+
10
+ <!-- header start -->
11
+ <!-- 200823 -->
12
+ <div style="width: auto; margin-left: auto; margin-right: auto">
13
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
14
+ </div>
15
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
16
+ <!-- header end -->
17
+
18
+ # internlm2_5-7b-chat-1m-GGUF
19
+
20
+ ## Original Model
21
+
22
+ [internlm/internlm2_5-7b-chat-1m](https://huggingface.co/internlm/internlm2_5-7b-chat-1m)
23
+
24
+ ## Run with LlamaEdge
25
+
26
+ - LlamaEdge version: [v0.12.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.12.3) and above
27
+
28
+ - Prompt template
29
+
30
+ - Prompt type
31
+ - chat: `chatml`
32
+ - tool use: `internlm-2-tool`
33
+
34
+ - Prompt string
35
+
36
+ ```text
37
+ <|im_start|>system
38
+ {system_message}<|im_end|>
39
+ <|im_start|>user
40
+ {prompt}<|im_end|>
41
+ <|im_start|>assistant
42
+ ```
43
+
44
+ - Context size: `1000000`
45
+
46
+ - Run as LlamaEdge service
47
+
48
+ - Chat
49
+
50
+ ```bash
51
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:internlm2_5-7b-chat-1m-Q5_K_M.gguf \
52
+ llama-api-server.wasm \
53
+ --prompt-template chatml \
54
+ --ctx-size 1000000 \
55
+ --model-name internlm2_5-7b-chat-1m
56
+ ```
57
+
58
+ - Tool use
59
+
60
+ ```bash
61
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:internlm2_5-7b-chat-1m-Q5_K_M.gguf \
62
+ llama-api-server.wasm \
63
+ --prompt-template internlm-2-tool \
64
+ --ctx-size 1000000 \
65
+ --model-name internlm2_5-7b-chat-1m
66
+ ```
67
+
68
+ - Run as LlamaEdge command app
69
+
70
+ ```bash
71
+ wasmedge --dir .:. \
72
+ --nn-preload default:GGML:AUTO:internlm2_5-7b-chat-1m-Q5_K_M.gguf \
73
+ llama-chat.wasm \
74
+ --prompt-template chatml \
75
+ --ctx-size 1000000
76
+ ```
77
+
78
+ <!-- ## Quantized GGUF Models
79
+
80
+ | Name | Quant method | Bits | Size | Use case |
81
+ | ---- | ---- | ---- | ---- | ----- |
82
+ | [internlm2_5-7b-chat-1m-1m-Q2_K.gguf](https://huggingface.co/second-state/internlm2_5-7b-chat-1m-1m-GGUF/blob/main/internlm2_5-7b-chat-1m-1m-Q2_K.gguf) | Q2_K | 2 | 3.01 GB| smallest, significant quality loss - not recommended for most purposes |
83
+ | [internlm2_5-7b-chat-1m-1m-Q3_K_L.gguf](https://huggingface.co/second-state/internlm2_5-7b-chat-1m-1m-GGUF/blob/main/internlm2_5-7b-chat-1m-1m-Q3_K_L.gguf) | Q3_K_L | 3 | 4.13 GB| small, substantial quality loss |
84
+ | [internlm2_5-7b-chat-1m-Q3_K_M.gguf](https://huggingface.co/second-state/internlm2_5-7b-chat-1m-GGUF/blob/main/internlm2_5-7b-chat-1m-Q3_K_M.gguf) | Q3_K_M | 3 | 3.83 GB| very small, high quality loss |
85
+ | [internlm2_5-7b-chat-1m-Q3_K_S.gguf](https://huggingface.co/second-state/internlm2_5-7b-chat-1m-GGUF/blob/main/internlm2_5-7b-chat-1m-Q3_K_S.gguf) | Q3_K_S | 3 | 3.48 GB| very small, high quality loss |
86
+ | [internlm2_5-7b-chat-1m-Q4_0.gguf](https://huggingface.co/second-state/internlm2_5-7b-chat-1m-GGUF/blob/main/internlm2_5-7b-chat-1m-Q4_0.gguf) | Q4_0 | 4 | 4.45 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
87
+ | [internlm2_5-7b-chat-1m-Q4_K_M.gguf](https://huggingface.co/second-state/internlm2_5-7b-chat-1m-GGUF/blob/main/internlm2_5-7b-chat-1m-Q4_K_M.gguf) | Q4_K_M | 4 | 4.71 GB| medium, balanced quality - recommended |
88
+ | [internlm2_5-7b-chat-1m-Q4_K_S.gguf](https://huggingface.co/second-state/internlm2_5-7b-chat-1m-GGUF/blob/main/internlm2_5-7b-chat-1m-Q4_K_S.gguf) | Q4_K_S | 4 | 4.48 GB| small, greater quality loss |
89
+ | [internlm2_5-7b-chat-1m-Q5_0.gguf](https://huggingface.co/second-state/internlm2_5-7b-chat-1m-GGUF/blob/main/internlm2_5-7b-chat-1m-Q5_0.gguf) | Q5_0 | 5 | 5.37 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
90
+ | [internlm2_5-7b-chat-1m-Q5_K_M.gguf](https://huggingface.co/second-state/internlm2_5-7b-chat-1m-GGUF/blob/main/internlm2_5-7b-chat-1m-Q5_K_M.gguf) | Q5_K_M | 5 | 5.51 GB| large, very low quality loss - recommended |
91
+ | [internlm2_5-7b-chat-1m-Q5_K_S.gguf](https://huggingface.co/second-state/internlm2_5-7b-chat-1m-GGUF/blob/main/internlm2_5-7b-chat-1m-Q5_K_S.gguf) | Q5_K_S | 5 | 5.37 GB| large, low quality loss - recommended |
92
+ | [internlm2_5-7b-chat-1m-Q6_K.gguf](https://huggingface.co/second-state/internlm2_5-7b-chat-1m-GGUF/blob/main/internlm2_5-7b-chat-1m-Q6_K.gguf) | Q6_K | 6 | 6.35 GB| very large, extremely low quality loss |
93
+ | [internlm2_5-7b-chat-1m-Q8_0.gguf](https://huggingface.co/second-state/internlm2_5-7b-chat-1m-GGUF/blob/main/internlm2_5-7b-chat-1m-Q8_0.gguf) | Q8_0 | 8 | 8.22 GB| very large, extremely low quality loss - not recommended |
94
+ | [internlm2_5-7b-chat-1m-f16.gguf](https://huggingface.co/second-state/internlm2_5-7b-chat-1m-GGUF/blob/main/internlm2_5-7b-chat-1m-f16.gguf) | f16 | 16 | 15.5 GB| | -->
95
+
96
+ *Quantized with llama.cpp b3933*