apepkuss79 commited on
Commit
48e4277
·
verified ·
1 Parent(s): f5f425b

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +90 -1
README.md CHANGED
@@ -1,3 +1,92 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: other
3
+ license_name: glm-4
4
+ license_link: https://huggingface.co/THUDM/glm-4-9b-chat-1m/blob/main/LICENSE
5
+ inference: false
6
+ base_model: THUDM/glm-4-9b-chat-1m
7
+ model_creator: THUDM
8
+ model_name: glm-4-9b-chat-1m
9
+ quantized_by: Second State Inc.
10
+ language:
11
+ - zh
12
+ - en
13
+ tags:
14
+ - glm
15
+ - chatglm
16
+ - thudm
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
+ # glm-4-9b-chat-1m-GGUF
28
+
29
+ ## Original Model
30
+
31
+ [THUDM/glm-4-9b-chat-1m](https://huggingface.co/THUDM/glm-4-9b-chat-1m)
32
+
33
+ ## Run with LlamaEdge
34
+
35
+ - LlamaEdge version: coming soon
36
+
37
+ <!-- - LlamaEdge version: [v0.12.1](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.12.1) and above
38
+
39
+ - Prompt template
40
+
41
+ - Prompt type: `gemma-instruct`
42
+
43
+ - Prompt string
44
+
45
+ ```text
46
+ <bos><start_of_turn>user
47
+ {user_message}<end_of_turn>
48
+ <start_of_turn>model
49
+ {model_message}<end_of_turn>model
50
+ ``` -->
51
+
52
+ - Context size: `1000000`
53
+
54
+ <!-- - Run as LlamaEdge service
55
+
56
+ ```bash
57
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:glm-4-9b-chat-1m-Q5_K_M.gguf \
58
+ llama-api-server.wasm \
59
+ --prompt-template phi-3-chat \
60
+ --ctx-size 128000 \
61
+ --model-name glm-4-9b-chat-1m
62
+ ```
63
+
64
+ - Run as LlamaEdge command app
65
+
66
+ ```bash
67
+ wasmedge --dir .:. \
68
+ --nn-preload default:GGML:AUTO:glm-4-9b-chat-1m-Q5_K_M.gguf \
69
+ llama-chat.wasm \
70
+ --prompt-template phi-3-chat \
71
+ --ctx-size 128000
72
+ ``` -->
73
+
74
+ ## Quantized GGUF Models
75
+
76
+ | Name | Quant method | Bits | Size | Use case |
77
+ | ---- | ---- | ---- | ---- | ----- |
78
+ | [glm-4-9b-chat-1m-Q2_K.gguf](https://huggingface.co/second-state/glm-4-9b-chat-1m-GGUF/blob/main/glm-4-9b-chat-1m-Q2_K.gguf) | Q2_K | 2 | 3.99 GB| smallest, significant quality loss - not recommended for most purposes |
79
+ | [glm-4-9b-chat-1m-Q3_K_L.gguf](https://huggingface.co/second-state/glm-4-9b-chat-1m-GGUF/blob/main/glm-4-9b-chat-1m-Q3_K_L.gguf) | Q3_K_L | 3 | 5.28 GB| small, substantial quality loss |
80
+ | [glm-4-9b-chat-1m-Q3_K_M.gguf](https://huggingface.co/second-state/glm-4-9b-chat-1m-GGUF/blob/main/glm-4-9b-chat-1m-Q3_K_M.gguf) | Q3_K_M | 3 | 5.06 GB| very small, high quality loss |
81
+ | [glm-4-9b-chat-1m-Q3_K_S.gguf](https://huggingface.co/second-state/glm-4-9b-chat-1m-GGUF/blob/main/glm-4-9b-chat-1m-Q3_K_S.gguf) | Q3_K_S | 3 | 4.59 GB| very small, high quality loss |
82
+ | [glm-4-9b-chat-1m-Q4_0.gguf](https://huggingface.co/second-state/glm-4-9b-chat-1m-GGUF/blob/main/glm-4-9b-chat-1m-Q4_0.gguf) | Q4_0 | 4 | 5.46 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
83
+ | [glm-4-9b-chat-1m-Q4_K_M.gguf](https://huggingface.co/second-state/glm-4-9b-chat-1m-GGUF/blob/main/glm-4-9b-chat-1m-Q4_K_M.gguf) | Q4_K_M | 4 | 6.25 GB| medium, balanced quality - recommended |
84
+ | [glm-4-9b-chat-1m-Q4_K_S.gguf](https://huggingface.co/second-state/glm-4-9b-chat-1m-GGUF/blob/main/glm-4-9b-chat-1m-Q4_K_S.gguf) | Q4_K_S | 4 | 5.75 GB| small, greater quality loss |
85
+ | [glm-4-9b-chat-1m-Q5_0.gguf](https://huggingface.co/second-state/glm-4-9b-chat-1m-GGUF/blob/main/glm-4-9b-chat-1m-Q5_0.gguf) | Q5_0 | 5 | 6.55 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
86
+ | [glm-4-9b-chat-1m-Q5_K_M.gguf](https://huggingface.co/second-state/glm-4-9b-chat-1m-GGUF/blob/main/glm-4-9b-chat-1m-Q5_K_M.gguf) | Q5_K_M | 5 | 7.14 GB| large, very low quality loss - recommended |
87
+ | [glm-4-9b-chat-1m-Q5_K_S.gguf](https://huggingface.co/second-state/glm-4-9b-chat-1m-GGUF/blob/main/glm-4-9b-chat-1m-Q5_K_S.gguf) | Q5_K_S | 5 | 6.69 GB| large, low quality loss - recommended |
88
+ | [glm-4-9b-chat-1m-Q6_K.gguf](https://huggingface.co/second-state/glm-4-9b-chat-1m-GGUF/blob/main/glm-4-9b-chat-1m-Q6_K.gguf) | Q6_K | 6 | 8.26 GB| very large, extremely low quality loss |
89
+ | [glm-4-9b-chat-1m-Q8_0.gguf](https://huggingface.co/second-state/glm-4-9b-chat-1m-GGUF/blob/main/glm-4-9b-chat-1m-Q8_0.gguf) | Q8_0 | 8 | 9.99 GB| very large, extremely low quality loss - not recommended |
90
+ | [glm-4-9b-chat-1m-f16.gguf](https://huggingface.co/second-state/glm-4-9b-chat-1m-GGUF/blob/main/glm-4-9b-chat-1m-f16.gguf) | f16 | 16 | 18.8 GB| |
91
+
92
+ *Quantized with llama.cpp b3333*