mav23 commited on
Commit
0fa6b7e
·
verified ·
1 Parent(s): 6e27e40

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. .gitattributes +1 -0
  2. README.md +48 -0
  3. llama-3-sqlcoder-8b.Q4_0.gguf +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ llama-3-sqlcoder-8b.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-sa-4.0
3
+ metrics:
4
+ - accuracy
5
+ pipeline_tag: text-generation
6
+ tags:
7
+ - code
8
+ ---
9
+
10
+ A capable language model for text to SQL generation for Postgres, Redshift and Snowflake that is on-par with the most capable generalist frontier models.
11
+
12
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/603bbad3fd770a9997b57cb6/h52Z_OKYBaDDQMFZyU5pF.png)
13
+
14
+ ## Model Description
15
+
16
+ Developed by: Defog, Inc
17
+ Model type: [Text to SQL]
18
+ License: [CC-by-SA-4.0]
19
+ Finetuned from model: [Meta-Llama-3-8B-Instruct]
20
+
21
+ ## Demo Page
22
+ [https://defog.ai/sqlcoder-demo/](https://defog.ai/sqlcoder-demo/)
23
+
24
+ ## Ideal prompt and inference parameters
25
+ Set temperature to 0, and do not do sampling.
26
+
27
+ ### Prompt
28
+ ```
29
+ <|begin_of_text|><|start_header_id|>user<|end_header_id|>
30
+
31
+ Generate a SQL query to answer this question: `{user_question}`
32
+ {instructions}
33
+
34
+ DDL statements:
35
+ {create_table_statements}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
36
+
37
+ The following SQL query best answers the question `{user_question}`:
38
+ ```sql
39
+
40
+ ```
41
+
42
+ ## Evaluation
43
+ This model was evaluated on SQL-Eval, a PostgreSQL based evaluation framework developed by Defog for testing and alignment of model capabilities.
44
+
45
+ You can read more about the methodology behind SQLEval [here](https://defog.ai/blog/open-sourcing-sqleval/).
46
+
47
+ ## Contact
48
+ Contact us on X at [@defogdata](https://twitter.com/defogdata), or on email at founders@defog.ai
llama-3-sqlcoder-8b.Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cbce7fe3b3af9bad8cafdb77df6e6718108c627e4213bf203fb336b9cd2c872
3
+ size 4661211744