Exllamav2
Transformers
Load model
A
í Terminal
Model Loader
Chat Loader
>
Inference
Code Completion
Function Calling
RAG
+
add wallpaper
+
add modules
+
new tab
>
Embeddings
Chat ID:
Select Model:
-- Select a model --
HTML:
Streaming:
Prompt Template:
Alpaca
C4AI
ChatML
CodeFuse
Deepseek-LLM
Google
Llama
Mistral
OpenChat
Phi
Orca-Vicuna
Phind
Xwin
D1 (### Instruction: / ### Response:)
D2 (USER: / ASSISTANT:)
System Message:
Below is an instruction that describes a task. Write a response that appropriately completes the request. If instructions are requested, provide clear step-by-step explanations.
Memory Mode:
Dynamic Sort
Static All
Top Rows:
Bot Rows:
Max Tokens:
Temp:
Top P:
Top K: