Update README.md

README.md

@@ -22,22 +22,64 @@ pipeline_tag: image-text-to-text
 # Pixtral-Large-Instruct-2411 🧡
 
 Transformers implementation of [Pixtral-Large-Instruct-2411](https://huggingface.co/mistralai/Pixtral-Large-Instruct-2411).  
- 
- 
-## Tokenizer And Prompt Template
-Using conversion of v7m1 tokenizer with 32k vocab size.  
- 
-Chat template in chat_template.json uses the v7 instruct template:
- 
+
+***21 Dec 2024:** This model has been a LOT of fun to experiment and learn with. Model card updated below with changes made to this repo 
+over the last week.*
+
+## Architecture Differences to Pixtral 12B
+Pixtral 12B has bias keys for the multi_modal_projector layers, whereas Pixtral Large does not. Instead of including with low/zero values 
+this conversion does not include those bias keys, aligning with the keys present in the original Pixtral Large upload from Mistral. The 
+model's config.json file includes `"multimodal_projector_bias": false` to flag this. *n.b. If anyone in the community confirms initializing 
+these keys with zero values is the better way to go I'm happy to reupload without them excluded.*
+
+## Tokenizer
+This model uses a conversion of the Mistral v7m1 tokenizer. Pixtral 12B and Large use different tokenizers with different vocab sizes, 
+so make sure you use the right tokenizer. 
+
+## Prompting / Chat Template
+The included chat_template.json supports all of Mistral's defined features with some of my own additions.  
+
+I believe this implementation should give quite a lot of flexibility for using the model, and in my testing has worked quite well.  
+
+Example *(line breaks added for readability)*
 ```
-<s>[SYSTEM_PROMPT] <system prompt>[/SYSTEM_PROMPT][INST] <user message>[/INST] <assistant response></s>[INST] <user message>[/INST]
+<s>[SYSTEM_PROMPT] <system prompt>[/SYSTEM_PROMPT]  
+[INST] [IMG]<user message>  
+[AVAILABLE_TOOLS] [<tool definitions>][/AVAILABLE_TOOLS][/INST]  
+[IMG]<assistant response>  
+[TOOL_CALLS] [<tool calls>][/TOOL_CALLS]  
+[TOOL_RESULTS] <tool results including images>[/TOOL_RESULTS]  
+</s>[INST] <user message>[/INST]
 ```
 
-## Notes
-*- tool use hasn't been implemented in the template yet. I'll add this in later.*  
-*- I've added extra stop tokens between consecutive user messages. Helps contexts where there'll be multiple speakers etc but your milage may vary.*  
-*- If you have a better implementation of the tokenizer let me know and I'm happy to swap it out.*  
-*- As always pls respect the model license.* 
+**System Prompts**:  
+Messages with role "system" will be parsed as `[SYSTEM_PROMPT] <content>[/SYSTEM_PROMPT]` anywhere they appear in chat history. 
+
+This appears to work pretty well for passing extra instructions at various depths, and keeps instructions separate from conversation. 
+
+**Allowing Non-Alternating Roles**:  
+Multiple user messages in a row can be provided, and each will be separated with `[INST][/INST]`. This could work well in group conversation 
+settings, or environments where multiple user messages can be provided before the model is invoked. Having a `[/INST]` breaking each one up 
+appeared to help prevent the model thinking it needs to respond to every previous message and focus on the last message, while still retaining 
+knowledge of what messages sit before it.  
+
+**Image Inputs Everywhere**:  
+Images can now be sent in user, assistant, and tool result messages. And seems to actually work. I did tests like including an image on an 
+assistant reply 10-15 messages back in the conversation, asked the assistant to recall what image they previously sent, and it was able to 
+accurately describe it.  
+
+Having this flexibility could allow for interesting applications, for example if you were to define a tool definition for image generation:
+- tool is invoked and calls image generation api/model
+- image returned inside tool result message
+- model responds with a message with context of the image generated
+- you can have further conversation about the generated image, or make revisions with the model actually knowing what was created
+
+## Usage
+When loading in transformers you'll probably want to add some handling to ensure the lack of mmproj bias is respected for it to handle 
+vision input properly.
+
+Most of my testing has been using TabbyAPI and ExLlamaV2 (dev branch) with working vision input.
+<img src="https://huggingface.co/nintwentydo/Pixtral-Large-Instruct-2411/resolve/main/image-input-example.jpg">
  
 
 ## Quantizations