Update README.md

README.md

@@ -12,14 +12,14 @@ pipeline_tag: text-generation
 
 [ExLlamaV2 is an inference library for running local LLMs on modern consumer GPUs.](https://github.com/turboderp-org/exllamav2)
 
-| Filename | Quant type | File Size |
+| Filename | Quant type | File Size | Vram at 16k context|
 | -------- | ---------- | --------- |
-| [phi-4_hb8_3bpw](https://huggingface.co/cmh/phi-4_exl2/tree/hb8_3bpw) | 3.00 bits per weight | 6.66 GB |
-| [phi-4_hb8_4bpw](https://huggingface.co/cmh/phi-4_exl2/tree/hb8_4bpw) | 4.00 bits per weight | 8.36 GB |
-| [phi-4_hb8_5bpw](https://huggingface.co/cmh/phi-4_exl2/tree/hb8_5bpw) | 5.00 bits per weight | 10.1 GB |
-| [phi-4_hb8_6bpw](https://huggingface.co/cmh/phi-4_exl2/tree/hb8_6bpw) | 6.00 bits per weight | 11.8 GB |
-| [phi-4_hb8_7bpw](https://huggingface.co/cmh/phi-4_exl2/tree/hb8_7bpw) | 7.00 bits per weight | 13.5 GB |
-| [phi-4_hb8_8bpw](https://huggingface.co/cmh/phi-4_exl2/tree/hb8_8bpw) | 8.00 bits per weight | 15.2 GB |
+| [phi-4_hb8_3bpw](https://huggingface.co/cmh/phi-4_exl2/tree/hb8_3bpw) | 3.00 bits per weight | 6.66 GB | 10,3 GB |
+| [phi-4_hb8_4bpw](https://huggingface.co/cmh/phi-4_exl2/tree/hb8_4bpw) | 4.00 bits per weight | 8.36 GB | 11,9 GB |
+| [phi-4_hb8_5bpw](https://huggingface.co/cmh/phi-4_exl2/tree/hb8_5bpw) | 5.00 bits per weight | 10.1 GB | 13,5 GB |
+| [phi-4_hb8_6bpw](https://huggingface.co/cmh/phi-4_exl2/tree/hb8_6bpw) | 6.00 bits per weight | 11.8 GB | 15,1 GB |
+| [phi-4_hb8_7bpw](https://huggingface.co/cmh/phi-4_exl2/tree/hb8_7bpw) | 7.00 bits per weight | 13.5 GB | 16,7 GB |
+| [phi-4_hb8_8bpw](https://huggingface.co/cmh/phi-4_exl2/tree/hb8_8bpw) | 8.00 bits per weight | 15.2 GB | 18,2 GB |
 
 # Phi-4 Model Card 
 
@@ -32,8 +32,7 @@ pipeline_tag: text-generation
 | **Developers**          | Microsoft Research                                                            |
 | **Description**         | `phi-4` is a state-of-the-art open model built upon a blend of synthetic datasets, data from filtered public domain websites, and acquired academic books and Q&A datasets. The goal of this approach was to ensure that small capable models were trained with data focused on high quality and advanced reasoning.<br><br>`phi-4` underwent a rigorous enhancement and alignment process, incorporating both supervised fine-tuning and direct preference optimization to ensure precise instruction adherence and robust safety measures                |
 | **Architecture**        | 14B parameters, dense decoder-only Transformer model                          |
-| **Inputs**              | Text, best suited for prompts in the chat format                              |
-| **Context length**      | 16K tokens                                                                    |
+| **Context length**      | 16384 tokens                                                                    |
 
 ## Usage
 
@@ -47,4 +46,65 @@ You are a medieval knight and must provide explanations to modern people.<|im_en
 <|im_start|>user<|im_sep|>
 How should I explain the Internet?<|im_end|>
 <|im_start|>assistant<|im_sep|>
+```
+
+### With ExUI:
+edit exui/backend/prompts.py
+
+```
+class PromptFormat_phi4(PromptFormat):
+
+    description = "Phi-4 format"
+
+    def __init__(self):
+        super().__init__()
+        pass
+
+    def is_instruct(self):
+        return True
+
+    def stop_conditions(self, tokenizer, settings):
+        return \
+            [tokenizer.eos_token_id,
+             """<|im_end|>"""]
+
+    def format(self, prompt, response, system_prompt, settings):
+        text = ""
+        if system_prompt and system_prompt.strip() != "":
+            text += "<|im_start|>system\n"
+            text += system_prompt
+            text += "\n<|im_end|>\n"
+        text += "<|im_start|>user\n"
+        text += prompt
+        text += "<|im_end|>\n"
+        text += "<|im_start|>assistant\n"
+        if response:
+            text += response
+            text += "<|im_end|>\n"
+        return text
+
+    def context_bos(self):
+        return True
+
+prompt_formats = \
+{
+    "Chat-RP": PromptFormat_raw,
+    "Llama-chat": PromptFormat_llama,
+    "Llama3-instruct": PromptFormat_llama3,
+    "ChatML": PromptFormat_chatml,
+    "TinyLlama-chat": PromptFormat_tinyllama,
+    "MistralLite": PromptFormat_mistrallite,
+    "Phind-CodeLlama": PromptFormat_phind_codellama,
+    "Deepseek-chat": PromptFormat_deepseek_chat,
+    "Deepseek-instruct": PromptFormat_deepseek_instruct,
+    "OpenChat": PromptFormat_openchat,
+    "Gemma": PromptFormat_gemma,
+    "Cohere": PromptFormat_cohere,
+    "Phi3-instruct": PromptFormat_phi3,
+    "Phi4": PromptFormat_phi4,
+    "Granite": PromptFormat_granite,
+    "Mistral V1": PromptFormat_mistralv1,
+    "Mistral V2/V3": PromptFormat_mistralv2v3,
+    "Mistral V3 (Tekken)": PromptFormat_mistralTekken,
+}
 ```