darwinkernelpanic commited on
Commit
65554c9
·
verified ·
1 Parent(s): 7e70d93

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -3
README.md CHANGED
@@ -7,6 +7,8 @@ tags:
7
  - base_model:adapter:deepseek-ai/deepseek-coder-6.7b-instruct
8
  - lora
9
  - transformers
 
 
10
  datasets:
11
  - darwinkernelpanic/luau_corpus_axolotl
12
  pipeline_tag: text-generation
@@ -100,18 +102,28 @@ It achieves the following results on the evaluation set:
100
 
101
  ## Model description
102
 
103
- More information needed
 
104
 
105
  ## Intended uses & limitations
106
 
107
- More information needed
 
 
 
 
 
 
 
108
 
109
  ## Training and evaluation data
110
 
111
- More information needed
112
 
113
  ## Training procedure
114
 
 
 
115
  ### Training hyperparameters
116
 
117
  The following hyperparameters were used during training:
 
7
  - base_model:adapter:deepseek-ai/deepseek-coder-6.7b-instruct
8
  - lora
9
  - transformers
10
+ - roblox
11
+ - luau
12
  datasets:
13
  - darwinkernelpanic/luau_corpus_axolotl
14
  pipeline_tag: text-generation
 
102
 
103
  ## Model description
104
 
105
+ The model was fine-tuned on the Roblox/luau_corpus dataset which was converted to have the "prompt" collum replaced by "text" for compatibility reasons.
106
+ It was fine-tuned for improved knowledge and performance on Luau code (Roblox's Lua dialect, see [luau.org](https://luau.org)), which should end up improving code quality for Luau and Roblox projects.
107
 
108
  ## Intended uses & limitations
109
 
110
+ This model is intended for use within applications that use the Luau programming language, including but not limited to
111
+ - Roblox projects
112
+ - Standalone Luau projects (Lune?)
113
+
114
+ It may have limitations for projects that
115
+ - Use alternative languages
116
+ - Use Lua
117
+ - Non programming related projects
118
 
119
  ## Training and evaluation data
120
 
121
+ N/A
122
 
123
  ## Training procedure
124
 
125
+ Trained on 1x RTX 6000Ada
126
+
127
  ### Training hyperparameters
128
 
129
  The following hyperparameters were used during training: