Update README.md

README.md

@@ -2,42 +2,80 @@
 base_model:
 - mistralai/Mistral-Small-3.2-24B-Instruct-2506
 library_name: transformers
+thumbnail: >-
+  https://cdn-uploads.huggingface.co/production/uploads/634262af8d8089ebaefd410e/g6hHxcdrD8r-HSUAz9b89.png
 tags:
-- axolotl
-- unsloth
-- roleplay
-- conversational
-- mlx
+  - axolotl
+  - unsloth
+  - roleplay
+  - conversational
 datasets:
-- PygmalionAI/PIPPA
-- Alfitaria/nemotron-ultra-reasoning-synthkink
-- PocketDoc/Dans-Prosemaxx-Gutenberg
-- FreedomIntelligence/Medical-R1-Distill-Data
-- cognitivecomputations/SystemChat-2.0
-- allenai/tulu-3-sft-personas-instruction-following
-- kalomaze/Opus_Instruct_25k
-- simplescaling/s1K-claude-3-7-sonnet
-- ai2-adapt-dev/flan_v2_converted
-- grimulkan/theory-of-mind
-- grimulkan/physical-reasoning
-- nvidia/HelpSteer3
-- nbeerbower/gutenberg2-dpo
-- nbeerbower/gutenberg-moderne-dpo
-- nbeerbower/Purpura-DPO
-- antiven0m/physical-reasoning-dpo
-- allenai/tulu-3-IF-augmented-on-policy-70b
-- allenai/href
+  - PygmalionAI/PIPPA
+  - Alfitaria/nemotron-ultra-reasoning-synthkink
+  - PocketDoc/Dans-Prosemaxx-Gutenberg
+  - FreedomIntelligence/Medical-R1-Distill-Data
+  - cognitivecomputations/SystemChat-2.0
+  - allenai/tulu-3-sft-personas-instruction-following
+  - kalomaze/Opus_Instruct_25k
+  - simplescaling/s1K-claude-3-7-sonnet
+  - ai2-adapt-dev/flan_v2_converted
+  - grimulkan/theory-of-mind
+  - grimulkan/physical-reasoning
+  - nvidia/HelpSteer3
+  - nbeerbower/gutenberg2-dpo
+  - nbeerbower/gutenberg-moderne-dpo
+  - nbeerbower/Purpura-DPO
+  - antiven0m/physical-reasoning-dpo
+  - allenai/tulu-3-IF-augmented-on-policy-70b
+  - allenai/href
 ---
+# MLX format for Angel 24b
+Get em while they're hot.
 
-# soundTeam/MS3.2-24b-Angel_mlx-q4
-This model was converted to MLX format from [`allura-org/MS3.2-24b-Angel`]() using mlx-vlm version **0.3.1**.
-Refer to the [original model card](https://huggingface.co/allura-org/MS3.2-24b-Angel) for more details on the model.
-## Use with mlx
+This one is at Q4 quality. Vision stack appears to be horribly mangled.
 
-```bash
-pip install -U mlx-vlm
-```
 
-```bash
-python -m mlx_vlm.generate --model soundTeam/MS3.2-24b-Angel_mlx-q4 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
-```
+# Angel 24b
+
+![Very cursed generation of Angel Dust laying on a bed, staring at the camera smirking. Generated with Kiwimix-XL v3 + an Angel Dust lora, refined with GPT-image-1](https://cdn-uploads.huggingface.co/production/uploads/634262af8d8089ebaefd410e/g6hHxcdrD8r-HSUAz9b89.png)
+
+***Better to reign in Hell than serve in Heaven.***
+
+# Overview
+MS3.2-24b-Angel is a model finetuned from Mistral Small 3.2 for roleplaying, storywriting, and differently-flavored general instruct usecases.
+
+Testing revealed strong prose and character portrayal for its class, rivalling the preferred 72B models of some testers.
+
+# Quantizations
+EXL3:
+- [Official EXL3 quants](https://huggingface.co/allura-quants/allura-org_MS3.2-24b-Angel-EXL3) (thanks artus <3)
+
+GGUF:
+- [Official GGUF imatrix quants w/ mmproj](https://hf.co/allura-quants/allura-org_MS3.2-24b-Angel-GGUF) (thanks artus, again <3)
+
+MLX:
+- Right here baby
+
+# Usage
+- Use Mistral v7 Tekken.
+- It is **highly recommended** (if your framework supports it) to use the official Mistral tokenization code instead of Huggingface's. This is possible in vLLM with `--tokenizer-mode mistral`.
+- Recommended samplers (from CURSE and corroborated by me, Fizz) are 1.2 temperature, 0.1 min_p, and 1.05 repetition penalty.
+- We recommend *a* system prompt, but its contents only faintly matter (I accidentally had an assistant system prompt during the entire time I was testing)
+
+# Training Process
+1. [The original model had its vision adapter removed](https://huggingface.co/anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only) for better optimization and easier usage in training frameworks
+2. The model was then put through an SFT process (using Axolotl) on various sources of general instruct, storytelling, and RP data, which resulted in [allura-forge/ms32-sft-merged](https://hf.co/allura-forge/ms32-sft-merged).
+3. Afterwards, the model was put through a KTO process (using Unsloth) on more focused storywriting and anti-slop data, as well as general instruction following and human preference, which resulted in the final checkpoints at [allura-forge/ms32-final-TEXTONLY](https://hf.co/allura-forge/ms32-final-TEXTONLY).
+4. Finally, the vision tower was manually added back to the weights to continue to support multimodality.
+
+# Credits
+- Fizz - training and data wrangling
+- Artus (by proxy) & Bot - help with funding
+- CURSE - testing
+- Mango - testing, data, help with KTO configs
+- DoctorShotgun - making the original text-only model
+- Axolotl & Unsloth - creating the training frameworks used for parts of this finetune
+- Everyone in Allura - moral support, being cool
+- Vivziepop and co - Angel Dust
+
+<3 love you all