Lewdiculous
/

Eris_Floramix_DPO_7B-GGUF-Imatrix

Model card Files Files and versions Community

Lewdiculous commited on Mar 8

Commit

9e88a38

•

1 Parent(s): ce98d83

Update README.md

Files changed (1) hide show

README.md +31 -9

README.md CHANGED Viewed

@@ -12,15 +12,18 @@ tags:
 - roleplay
 - imatrix
 - mistral
 inference: false
 ---
-This repository hosts GGUF-Imatrix quantizations for [ChaoticNeutrals/Eris_Floramix_DPO_7B](https://huggingface.co/ChaoticNeutrals/Eris_Floramix_DPO_7B).
 ```python
     quantization_options = [
-        "Q3_K_M", "Q4_K_M", "Q5_K_M", "Q6_K",
-        "Q8_0", "IQ4_XS", "IQ3_XXS"
     ]
 ```
@@ -30,14 +33,33 @@ For imatrix data generation, kalomaze's `groups_merged.txt` with added roleplay
 The goal is to measure the (hopefully positive) impact of this data for consistent formatting in roleplay chatting scenarios.
-**Image:**
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/1kuWjS4TnCIkCcdZdPfsG.png)
-**Original model information:**
-# Eris Floramix DPO
-This is a mix between Eris Remix DPO and Flora DPO, a finetune of the original Eris Remix on the Synthetic_Soul_1k dataset.
-Applied this DPO dataset: https://huggingface.co/datasets/athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW-v1-SHUFFLED

 - roleplay
 - imatrix
 - mistral
+- merge
 inference: false
 ---
+This repository hosts GGUF-Imatrix quantizations for [Test157t/Eris-Daturamix-7b](https://huggingface.co/Test157t/Eris-Daturamix-7b).
+To be uploaded:
 ```python
     quantization_options = [
+        "Q4_K_M", "IQ4_XS", "Q5_K_M", "Q6_K",
+        "Q8_0", "IQ3_M", "IQ3_S", "IQ3_XXS"
     ]
 ```
 The goal is to measure the (hopefully positive) impact of this data for consistent formatting in roleplay chatting scenarios.
+**Original model information:**
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/FtEEuyGni5M-cxkYYBBHw.jpeg)
+The following models were included in the merge:
+* [ResplendentAI/Datura_7B](https://huggingface.co/ResplendentAI/Datura_7B)
+* [Test157t/Eris-Floramix-7b](https://huggingface.co/Test157t/Eris-Floramix-7b)
+### Configuration
+The following YAML configuration was used to produce this model:
+```yaml
+slices:
+  - sources:
+      - model: Test157t/Eris-Floramix-7b
+        layer_range: [0, 32]
+      - model: ResplendentAI/Datura_7B
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: Test157t/Eris-Floramix-7b
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+```