Lewdiculous commited on
Commit
8ea5e9e
·
verified ·
1 Parent(s): 649323d

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +80 -0
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ language:
5
+ - en
6
+ tags:
7
+ - gguf
8
+ - quantized
9
+ - roleplay
10
+ - imatrix
11
+ - mistral
12
+ - merge
13
+ inference: false
14
+ # base_model:
15
+ # - Epiculous/Fett-uccine-Long-Noodle-7B-120k-Context
16
+ # - Epiculous/Mika-7B
17
+ ---
18
+
19
+ This repository hosts GGUF-IQ-Imatrix quantizations for **[ChaoticNeutrals/InfinityNexus_9B](https://huggingface.co/ChaoticNeutrals/InfinityNexus_9B)**.
20
+
21
+ **What does "Imatrix" mean?**
22
+
23
+ It stands for **Importance Matrix**, a technique used to improve the quality of quantized models.
24
+ The **Imatrix** is calculated based on calibration data, and it helps determine the importance of different model activations during the quantization process.
25
+ The idea is to preserve the most important information during quantization, which can help reduce the loss of model performance, especially when the calibration data is diverse.
26
+ [[1]](https://github.com/ggerganov/llama.cpp/discussions/5006) [[2]](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
27
+
28
+ For imatrix data generation, kalomaze's `groups_merged.txt` with added roleplay chats was used, you can find it [here](https://huggingface.co/Lewdiculous/Datura_7B-GGUF-Imatrix/blob/main/imatrix-with-rp-format-data.txt).
29
+
30
+ **Steps:**
31
+
32
+ ```
33
+ Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)
34
+ ```
35
+ *Using the latest llama.cpp at the time.*
36
+
37
+ **Quants:**
38
+ ```python
39
+ quantization_options = [
40
+ "Q4_K_M", "Q4_K_S" "IQ4_XS", "Q5_K_M", "Q5_K_S", "Q6_K",
41
+ "Q8_0", "IQ3_M", "IQ3_S", "IQ3_XXS"
42
+ ]
43
+ ```
44
+
45
+ If you want anything that's not here or another model, feel free to request.
46
+
47
+ **Original model information:**
48
+
49
+ # InfinityNexus
50
+
51
+ ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/626dfb8786671a29c715f8a9/QNJ-bM2K8brYL-Z--tcI0.jpeg)
52
+
53
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
54
+
55
+ ## Merge Details
56
+ ### Merge Method
57
+
58
+ This model was merged using the passthrough merge method.
59
+
60
+ ### Models Merged
61
+
62
+ The following models were included in the merge:
63
+ * [Endevor/InfinityRP-v1-7B](https://huggingface.co/Endevor/InfinityRP-v1-7B)
64
+ * [jeiku/NarrativeNexus_7B](https://huggingface.co/jeiku/NarrativeNexus_7B)
65
+
66
+ ### Configuration
67
+
68
+ The following YAML configuration was used to produce this model:
69
+
70
+ ```yaml
71
+ slices:
72
+ - sources:
73
+ - model: Endevor/InfinityRP-v1-7B
74
+ layer_range: [0, 20]
75
+ - sources:
76
+ - model: jeiku/NarrativeNexus_7B
77
+ layer_range: [12, 32]
78
+ merge_method: passthrough
79
+ dtype: float16
80
+ ```