kv shift improvement

guinmoon · Oct 26, 2024 · db2ad97 · db2ad97
1 parent aa9c11c
commit db2ad97
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 3 deletions.
diff --git a/LLMFarm/Chats/ChatView.swift b/LLMFarm/Chats/ChatView.swift
@@ -132,7 +132,7 @@ struct ChatView: View {
                         HStack{
                             Text(String(describing: aiChatModel.state))
                                 .foregroundColor(.white)
-                                .frame(width: 100 /*,height: 25*/)
+                                .frame(width: 200 /*,height: 25*/)
                     //            .padding([.top, .leading], 5)
                                 .opacity(0.4)
                                 .offset(x: 0,y: 8)

diff --git a/README.md b/README.md
@@ -73,7 +73,7 @@ See full list [here](https://github.com/ggerganov/llama.cpp).
 - [x] [Yi-VL](https://huggingface.co/models?search=Yi-VL)
 - [x] [Moondream](https://huggingface.co/vikhyatk/moondream2)
 
-Note: For *Falcon, Alpaca, GPT4All, Chinese LLaMA / Alpaca and Chinese LLaMA-2 / Alpaca-2, Vigogne (French), Vicuna, Koala, OpenBuddy (Multilingual), Pygmalion/Metharme, WizardLM, Baichuan 1 & 2 + derivations, Aquila 1 & 2, Mistral AI v0.1, Refact, Persimmon 8B, MPT, Bloom* select `llama inferece` in model settings.
+Note: For *Falcon, Alpaca, GPT4All, Chinese LLaMA / Alpaca and Chinese LLaMA-2 / Alpaca-2, Vigogne (French), Vicuna, Koala, OpenBuddy (Multilingual), Pygmalion/Metharme, WizardLM, Baichuan 1 & 2 + derivations, Aquila 1 & 2, Mistral AI v0.1, Refact, Persimmon 8B, MPT, Bloom* select `llama inference` in model settings.
 
 # Sampling methods
 - [x] Temperature (temp, tok-k, top-p)

diff --git a/llmfarm_core.swift b/llmfarm_core.swift
+2 −2		Sources/llmfarm_core/LLMBase.swift
+9 −7		Sources/llmfarm_core/LLaMa.swift