finetuningrag commited on
Commit
0f919f6
·
verified ·
1 Parent(s): 09af441

(Trained with Unsloth)

Browse files
Files changed (1) hide show
  1. Modelfile +22 -0
Modelfile ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ FROM /content/finetuningrag/Llama-3.2-1B_RAG_Resolucio_CA_gguf/unsloth.F16.gguf
2
+
3
+ TEMPLATE """You are an assistant for question-answering tasks. Use the following pieces of retrieved context
4
+ to answer the question. If you do not know the answer, just say that you do not know. Use three sentences
5
+ maximum and keep the answer concise. Return the result in Catalan.{{ if .Prompt }}
6
+
7
+ ### Instruction:
8
+ {{ .Prompt }}{{ end }}
9
+
10
+ ### Response:
11
+ {{ .Response }}<|end_of_text|>"""
12
+
13
+ PARAMETER stop "<|end_header_id|>"
14
+ PARAMETER stop "<|eom_id|>"
15
+ PARAMETER stop "<|finetune_right_pad_id|>"
16
+ PARAMETER stop "<|start_header_id|>"
17
+ PARAMETER stop "<|python_tag|>"
18
+ PARAMETER stop "<|eot_id|>"
19
+ PARAMETER stop "<|end_of_text|>"
20
+ PARAMETER stop "<|reserved_special_token_"
21
+ PARAMETER temperature 1.5
22
+ PARAMETER min_p 0.1