初始化项目，由ModelHub XC社区提供模型

Model: Quant-Cartel/Luca-MN-iMat-GGUF Source: Original Platform
2026-06-22 14:20:18 +08:00
commit 92e5d6667e
16 changed files with 145 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,53 @@
+---
+license: apache-2.0
+base_model_relation: quantized
+quantized_by: Quant-Cartel
+base_model: rAIfle/Luca-MN-bf16
+pipeline_tag: text-generation
+tags:
+- iMat
+- GGUF
+- unsloth
+- trl
+- sft
+---
+```
+  e88 88e                               d8     
+ d888 888b  8888 8888  ,"Y88b 888 8e   d88     
+C8888 8888D 8888 8888 "8" 888 888 88b d88888   
+ Y888 888P  Y888 888P ,ee 888 888 888  888     
+  "88 88"    "88 88"  "88 888 888 888  888     
+      b                                        
+      8b,                                      
+ 
+  e88'Y88                  d8           888    
+ d888  'Y  ,"Y88b 888,8,  d88    ,e e,  888    
+C8888     "8" 888 888 "  d88888 d88 88b 888    
+ Y888  ,d ,ee 888 888     888   888   , 888    
+  "88,d88 "88 888 888     888    "YeeP" 888    
+                                               
+PROUDLY PRESENTS         
+```
+# Luca-MN-iMat-GGUF
+
+Quantized with love from fp32.
+
+* Importance Matrix calculated using [groups_merged.txt](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
+*  92 chunks
+*  n_ctx=512
+*  Importance Matrix uses fp32 precision model weights, fp32.imatrix file to be added in repo
+
+Original model README [here](https://huggingface.co/rAIFle/Luca-MN-bf16) and below:
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6569a4ed2419be6072890cf8/T_ITjuaHakgamjwuElcAs.png)
+
+## Luca-MN-iMat-GGUF
+
+
+This thing was just intended as an experiment but it turned out quite good. I had it both name and prompt imagegen for itself.
+
+Created by running a high-r LoRA-pass over Nemo-Base with 2 epochs of some RP data, then a low-r pass with 0.5 epochs of the c2-data, then 3 epochs of DPO using [jondurbin/gutenberg-dpo-v0.1](https://huggingface.co/datasets/jondurbin/gutenberg-dpo-v0.1).
+
+## Prompting
+
+Use the `Mistral V3-Tekken` context- and instruct-templates. Temperature at about `1.25` seems to be the sweet spot, with either MinP at `0.05` or TopP at `0.9`. DRY/Smoothing etc depending on your preference.