Hugging Face's logo

second-state
/
xLAM-1b-fc-r-GGUF

Text Generation
GGUF
English
llama
function-calling
LLM Agent
tool-use
deepseek
conversational
Model card Files Community
apepkuss79 commited on
Commit
ac16a64
•
1 Parent(s): 7c07aea

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +85 -85
README.md CHANGED
@@ -1,86 +1,86 @@
1
- ---
2
- license: cc-by-nc-4.0
3
- model_name: xLAM-1b-fc-r
4
- base_model: Salesforce/xLAM-1b-fc-r
5
- inference: false
6
- model_creator: BAAI
7
- quantized_by: Second State Inc.
8
- pipeline_tag: text-generation
9
- tags:
10
- - function-calling
11
- - LLM Agent
12
- - tool-use
13
- - deepseek
14
- language:
15
- - en
16
- ---
17
-
18
- <!-- header start -->
19
- <!-- 200823 -->
20
- <div style="width: auto; margin-left: auto; margin-right: auto">
21
- <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
22
- </div>
23
- <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
24
- <!-- header end -->
25
-
26
- # xLAM-1b-fc-r-GGUF
27
-
28
- ## Original Model
29
-
30
- [Salesforce/xLAM-1b-fc-r](https://huggingface.co/Salesforce/xLAM-1b-fc-r)
31
-
32
- ## Run with LlamaEdge
33
-
34
- - LlamaEdge version: coming soon
35
-
36
- <!-- - LlamaEdge version: [v0.14.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.0) and above
37
-
38
- - Prompt template
39
-
40
- - Prompt type: `chatml`
41
-
42
- - Prompt string
43
-
44
- ```text
45
- <|im_start|>system
46
- {system_message}<|im_end|>
47
- <|im_start|>user
48
- {prompt}<|im_end|>
49
- <|im_start|>assistant
50
- ```
51
-
52
- - Reverse prompt: `<|im_end|>`
53
-
54
- - Run as LlamaEdge service
55
-
56
- ```bash
57
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:xLAM-1b-fc-r-Q5_K_M.gguf llama-api-server.wasm -p chatml -r '<|im_end|>'
58
- ``` -->
59
-
60
- - Context size: `16000`
61
-
62
- <!-- - Run as LlamaEdge command app
63
-
64
- ```bash
65
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:xLAM-1b-fc-r-Q5_K_M.gguf llama-chat.wasm -p chatml -r '<|im_end|>'
66
- ``` -->
67
-
68
- ## Quantized GGUF Models
69
-
70
- | Name | Quant method | Bits | Size | Use case |
71
- | ---- | ---- | ---- | ---- | ----- |
72
- | [xLAM-1b-fc-r-Q2_K.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q2_K.gguf) | Q2_K | 2 | 560 MB| smallest, significant quality loss - not recommended for most purposes |
73
- | [xLAM-1b-fc-r-Q3_K_L.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q3_K_L.gguf) | Q3_K_L | 3 | 744 MB| small, substantial quality loss |
74
- | [xLAM-1b-fc-r-Q3_K_M.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q3_K_M.gguf) | Q3_K_M | 3 | 704 MB| very small, high quality loss |
75
- | [xLAM-1b-fc-r-Q3_K_S.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q3_K_S.gguf) | Q3_K_S | 3 | 642 MB| very small, high quality loss |
76
- | [xLAM-1b-fc-r-Q4_0.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q4_0.gguf) | Q4_0 | 4 | 776 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
77
- | [xLAM-1b-fc-r-Q4_K_M.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q4_K_M.gguf) | Q4_K_M | 4 | 873 MB| medium, balanced quality - recommended |
78
- | [xLAM-1b-fc-r-Q4_K_S.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q4_K_S.gguf) | Q4_K_S | 4 | 814 MB| small, greater quality loss |
79
- | [xLAM-1b-fc-r-Q5_0.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q5_0.gguf) | Q5_0 | 5 | 936 MB| legacy; medium, balanced quality - prefer using Q4_K_M |
80
- | [xLAM-1b-fc-r-Q5_K_M.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q5_K_M.gguf) | Q5_K_M | 5 | 1.00 GB| large, very low quality loss - recommended |
81
- | [xLAM-1b-fc-r-Q5_K_S.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q5_K_S.gguf) | Q5_K_S | 5 | 953 MB| large, low quality loss - recommended |
82
- | [xLAM-1b-fc-r-Q6_K.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q6_K.gguf) | Q6_K | 6 | 1.17 GB| very large, extremely low quality loss |
83
- | [xLAM-1b-fc-r-Q8_0.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q8_0.gguf) | Q8_0 | 8 | 1.43 GB| very large, extremely low quality loss - not recommended |
84
- | [xLAM-1b-fc-r-f16.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-f16.gguf) | f16 | 16 | 2.69 GB| |
85
-
86
  *Quantized with llama.cpp b3613.*
 
1
+ ---
2
+ license: cc-by-nc-4.0
3
+ model_name: xLAM-1b-fc-r
4
+ base_model: Salesforce/xLAM-1b-fc-r
5
+ inference: false
6
+ model_creator: Salesforce
7
+ quantized_by: Second State Inc.
8
+ pipeline_tag: text-generation
9
+ tags:
10
+ - function-calling
11
+ - LLM Agent
12
+ - tool-use
13
+ - deepseek
14
+ language:
15
+ - en
16
+ ---
17
+
18
+ <!-- header start -->
19
+ <!-- 200823 -->
20
+ <div style="width: auto; margin-left: auto; margin-right: auto">
21
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
22
+ </div>
23
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
24
+ <!-- header end -->
25
+
26
+ # xLAM-1b-fc-r-GGUF
27
+
28
+ ## Original Model
29
+
30
+ [Salesforce/xLAM-1b-fc-r](https://huggingface.co/Salesforce/xLAM-1b-fc-r)
31
+
32
+ ## Run with LlamaEdge
33
+
34
+ - LlamaEdge version: coming soon
35
+
36
+ <!-- - LlamaEdge version: [v0.14.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.0) and above
37
+
38
+ - Prompt template
39
+
40
+ - Prompt type: `chatml`
41
+
42
+ - Prompt string
43
+
44
+ ```text
45
+ <|im_start|>system
46
+ {system_message}<|im_end|>
47
+ <|im_start|>user
48
+ {prompt}<|im_end|>
49
+ <|im_start|>assistant
50
+ ```
51
+
52
+ - Reverse prompt: `<|im_end|>`
53
+
54
+ - Run as LlamaEdge service
55
+
56
+ ```bash
57
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:xLAM-1b-fc-r-Q5_K_M.gguf llama-api-server.wasm -p chatml -r '<|im_end|>'
58
+ ``` -->
59
+
60
+ - Context size: `16000`
61
+
62
+ <!-- - Run as LlamaEdge command app
63
+
64
+ ```bash
65
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:xLAM-1b-fc-r-Q5_K_M.gguf llama-chat.wasm -p chatml -r '<|im_end|>'
66
+ ``` -->
67
+
68
+ ## Quantized GGUF Models
69
+
70
+ | Name | Quant method | Bits | Size | Use case |
71
+ | ---- | ---- | ---- | ---- | ----- |
72
+ | [xLAM-1b-fc-r-Q2_K.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q2_K.gguf) | Q2_K | 2 | 560 MB| smallest, significant quality loss - not recommended for most purposes |
73
+ | [xLAM-1b-fc-r-Q3_K_L.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q3_K_L.gguf) | Q3_K_L | 3 | 744 MB| small, substantial quality loss |
74
+ | [xLAM-1b-fc-r-Q3_K_M.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q3_K_M.gguf) | Q3_K_M | 3 | 704 MB| very small, high quality loss |
75
+ | [xLAM-1b-fc-r-Q3_K_S.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q3_K_S.gguf) | Q3_K_S | 3 | 642 MB| very small, high quality loss |
76
+ | [xLAM-1b-fc-r-Q4_0.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q4_0.gguf) | Q4_0 | 4 | 776 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
77
+ | [xLAM-1b-fc-r-Q4_K_M.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q4_K_M.gguf) | Q4_K_M | 4 | 873 MB| medium, balanced quality - recommended |
78
+ | [xLAM-1b-fc-r-Q4_K_S.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q4_K_S.gguf) | Q4_K_S | 4 | 814 MB| small, greater quality loss |
79
+ | [xLAM-1b-fc-r-Q5_0.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q5_0.gguf) | Q5_0 | 5 | 936 MB| legacy; medium, balanced quality - prefer using Q4_K_M |
80
+ | [xLAM-1b-fc-r-Q5_K_M.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q5_K_M.gguf) | Q5_K_M | 5 | 1.00 GB| large, very low quality loss - recommended |
81
+ | [xLAM-1b-fc-r-Q5_K_S.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q5_K_S.gguf) | Q5_K_S | 5 | 953 MB| large, low quality loss - recommended |
82
+ | [xLAM-1b-fc-r-Q6_K.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q6_K.gguf) | Q6_K | 6 | 1.17 GB| very large, extremely low quality loss |
83
+ | [xLAM-1b-fc-r-Q8_0.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-Q8_0.gguf) | Q8_0 | 8 | 1.43 GB| very large, extremely low quality loss - not recommended |
84
+ | [xLAM-1b-fc-r-f16.gguf](https://huggingface.co/second-state/xLAM-1b-fc-r-GGUF/blob/main/xLAM-1b-fc-r-f16.gguf) | f16 | 16 | 2.69 GB| |
85
+
86
  *Quantized with llama.cpp b3613.*