Hugging Face's logo

QuantFactory
/
TableLLM-13b-GGUF

Table Question Answering
Transformers
GGUF
Model card Files
xet
 Community
1
aashish1904 nielsr HF Staff commited on
Commit
462bbbe
·
verified ·
1 Parent(s): 6444303

Update model card metadata: pipeline tag, license, and add Github link (#1)

Browse files

- Update model card metadata: pipeline tag, license, and add Github link (4d9ccaded7954c2ffa58f71318d8d85370a8dfd1)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +8 -12
README.md CHANGED
@@ -1,10 +1,8 @@
1
-
2
  ---
3
-
4
- pipeline_tag: text-generation
5
  base_model: TableLLM-13b
6
  library_name: transformers
7
-
 
8
  ---
9
 
10
  [![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)
@@ -17,7 +15,6 @@ This is quantized version of [RUCKBReasoning/TableLLM-13b](https://huggingface.c
17
 
18
  ---
19
 
20
- license: llama2
21
  datasets:
22
  - RUCKBReasoning/TableLLM-SFT
23
  language:
@@ -29,7 +26,7 @@ tags:
29
 
30
  ---
31
 
32
- [![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)
33
 
34
 
35
  # QuantFactory/TableLLM-13b-GGUF
@@ -52,9 +49,9 @@ We evaluate the code solution generation ability of TableLLM on three benchmarks
52
  | Model | WikiTQ | TAT-QA | FeTaQA | OTTQA | WikiSQL | Spider | Self-created | Average |
53
  | :------------------- | :----: | :----: | :----: | :-----: | :-----: | :----: | :----------: | :-----: |
54
  | TaPEX | 38.5 | – | – | – | 83.9 | 15.0 | / | 45.8 |
55
- | TaPas | 31.5 | – | – | – | 74.2 | 23.1 | / | 42.92 |
56
  | TableLlama | 24.0 | 22.2 | 20.5 | 6.4 | 43.7 | 9.0 | / | 20.7 |
57
- | GPT3.5 | 58.5 |<ins>72.1</ins>| 71.2 | 60.8 | 81.7 | 67.4 | 77.1 | 69.8 |
58
  | GPT4 |**74.1**|**77.1**|**78.4**|**69.5** | 84.0 | 69.5 | 77.8 | **75.8**|
59
  | Llama2-Chat (13B) | 48.8 | 49.6 | 67.7 | 61.5 | – | – | – | 56.9 |
60
  | CodeLlama (13B) | 43.4 | 47.2 | 57.2 | 49.7 | 38.3 | 21.9 | 47.6 | 43.6 |
@@ -62,8 +59,8 @@ We evaluate the code solution generation ability of TableLLM on three benchmarks
62
  | StructGPT (GPT3.5) | 52.5 | 27.5 | 11.8 | 14.0 | 67.8 |**84.8**| / | 48.9 |
63
  | Binder (GPT3.5) | 61.6 | 12.8 | 6.8 | 5.1 | 78.6 | 52.6 | / | 42.5 |
64
  | DATER (GPT3.5) | 53.4 | 28.4 | 18.3 | 13.0 | 58.2 | 26.5 | / | 37.0 |
65
- | TableLLM-7B (Ours) | 58.8 | 66.9 | 72.6 |<ins>63.1</ins>|<ins>86.6</ins>| 82.6 |<ins>78.8</ins>| 72.8 |
66
- | TableLLM-13B (Ours) |<ins>62.4</ins>| 68.2 |<ins>74.5</ins>| 62.5 | **90.7**|<ins>83.4</ins>| **80.8** |<ins>74.7</ins>|
67
 
68
  ## Prompt Template
69
  The prompts we used for generating code solutions and text answers are introduced below.
@@ -120,5 +117,4 @@ The prompt template for direct text answer generation on short tables.
120
  ### [Solution][INST/]
121
  ````
122
 
123
- For more details about how to use TableLLM, please refer to our GitHub page: <https://github.com/TableLLM/TableLLM>
124
-
 
 
1
  ---
 
 
2
  base_model: TableLLM-13b
3
  library_name: transformers
4
+ pipeline_tag: table-question-answering
5
+ license: llama2
6
  ---
7
 
8
  [![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)
 
15
 
16
  ---
17
 
 
18
  datasets:
19
  - RUCKBReasoning/TableLLM-SFT
20
  language:
 
26
 
27
  ---
28
 
29
+ [![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44UcQKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)
30
 
31
 
32
  # QuantFactory/TableLLM-13b-GGUF
 
49
  | Model | WikiTQ | TAT-QA | FeTaQA | OTTQA | WikiSQL | Spider | Self-created | Average |
50
  | :------------------- | :----: | :----: | :----: | :-----: | :-----: | :----: | :----------: | :-----: |
51
  | TaPEX | 38.5 | – | – | – | 83.9 | 15.0 | / | 45.8 |
52
+ | TaPas | 31.5 | – | – | 74.2 | 23.1 | / | 42.92 |
53
  | TableLlama | 24.0 | 22.2 | 20.5 | 6.4 | 43.7 | 9.0 | / | 20.7 |
54
+ | GPT3.5 | 58.5 | 72.1 | 71.2 | 60.8 | 81.7 | 67.4 | 77.1 | 69.8 |
55
  | GPT4 |**74.1**|**77.1**|**78.4**|**69.5** | 84.0 | 69.5 | 77.8 | **75.8**|
56
  | Llama2-Chat (13B) | 48.8 | 49.6 | 67.7 | 61.5 | – | – | – | 56.9 |
57
  | CodeLlama (13B) | 43.4 | 47.2 | 57.2 | 49.7 | 38.3 | 21.9 | 47.6 | 43.6 |
 
59
  | StructGPT (GPT3.5) | 52.5 | 27.5 | 11.8 | 14.0 | 67.8 |**84.8**| / | 48.9 |
60
  | Binder (GPT3.5) | 61.6 | 12.8 | 6.8 | 5.1 | 78.6 | 52.6 | / | 42.5 |
61
  | DATER (GPT3.5) | 53.4 | 28.4 | 18.3 | 13.0 | 58.2 | 26.5 | / | 37.0 |
62
+ | TableLLM-7B (Ours) | 58.8 | 66.9 | 72.6 | 63.1 | 86.6| 82.6 | 78.8| 72.8 |
63
+ | TableLLM-13B (Ours) | 62.4| 68.2 | 74.5| 62.5 | **90.7**| 83.4| **80.8** | 74.7|
64
 
65
  ## Prompt Template
66
  The prompts we used for generating code solutions and text answers are introduced below.
 
117
  ### [Solution][INST/]
118
  ````
119
 
120
+ For more details about how to use TableLLM, please refer to our GitHub page: <https://github.com/TableLLM/TableLLM>