00harshh commited on
Commit
d8da8b4
·
verified ·
1 Parent(s): 6e33611

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -4
README.md CHANGED
@@ -4,7 +4,24 @@ A LoRA fine-tune of Microsoft's Phi-3-mini-4k-instruct (3.8B), trained on 467 cl
4
 
5
  The model is tuned to respond in the tone and phrasing style of the training set's support answers (policy language, portal references, timeframes) rather than generic conversational filler. Best suited for retail customer-support-style Q&A within the categories it was trained on; not intended for general-purpose or safety-critical use, and may hallucinate specifics (order numbers, exact policy details) on out-of-distribution questions — outputs should be reviewed before being shown to real customers.
6
 
7
- Base model: unsloth/Phi-3-mini-4k-instruct
8
- Training data: 467 examples, custom retail support dataset
9
- Method: QLoRA (4-bit), r=16, α=16
10
- Framework: Unsloth + TRL SFTTrainer
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
 
5
  The model is tuned to respond in the tone and phrasing style of the training set's support answers (policy language, portal references, timeframes) rather than generic conversational filler. Best suited for retail customer-support-style Q&A within the categories it was trained on; not intended for general-purpose or safety-critical use, and may hallucinate specifics (order numbers, exact policy details) on out-of-distribution questions — outputs should be reviewed before being shown to real customers.
6
 
7
+ ---
8
+ license: mit
9
+ base_model: unsloth/Phi-3-mini-4k-instruct
10
+ tags:
11
+ - unsloth
12
+ - lora
13
+ - phi-3
14
+ - customer-support
15
+ - fine-tuned
16
+ - qlora
17
+ language:
18
+ - en
19
+ pipeline_tag: text-generation
20
+ library_name: peft
21
+ model_type: phi3
22
+ datasets:
23
+ - custom
24
+ metrics:
25
+ - loss
26
+ inference: true
27
+ ---