Hugging Face's logo

RichardErkhov
/
tourist800_-_Mistral-7B-Merge-14-v0.2-gguf

GGUF
Model card Files Community
RichardErkhov commited on
Commit
c37c1d2
•
1 Parent(s): b3f9874

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +81 -0
README.md ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ Mistral-7B-Merge-14-v0.2 - GGUF
11
+ - Model creator: https://huggingface.co/tourist800/
12
+ - Original model: https://huggingface.co/tourist800/Mistral-7B-Merge-14-v0.2/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [Mistral-7B-Merge-14-v0.2.Q2_K.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.Q2_K.gguf) | Q2_K | 2.53GB |
18
+ | [Mistral-7B-Merge-14-v0.2.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.IQ3_XS.gguf) | IQ3_XS | 2.81GB |
19
+ | [Mistral-7B-Merge-14-v0.2.IQ3_S.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.IQ3_S.gguf) | IQ3_S | 2.96GB |
20
+ | [Mistral-7B-Merge-14-v0.2.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.Q3_K_S.gguf) | Q3_K_S | 2.95GB |
21
+ | [Mistral-7B-Merge-14-v0.2.IQ3_M.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.IQ3_M.gguf) | IQ3_M | 3.06GB |
22
+ | [Mistral-7B-Merge-14-v0.2.Q3_K.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.Q3_K.gguf) | Q3_K | 3.28GB |
23
+ | [Mistral-7B-Merge-14-v0.2.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.Q3_K_M.gguf) | Q3_K_M | 3.28GB |
24
+ | [Mistral-7B-Merge-14-v0.2.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.Q3_K_L.gguf) | Q3_K_L | 3.56GB |
25
+ | [Mistral-7B-Merge-14-v0.2.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.IQ4_XS.gguf) | IQ4_XS | 3.67GB |
26
+ | [Mistral-7B-Merge-14-v0.2.Q4_0.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.Q4_0.gguf) | Q4_0 | 3.83GB |
27
+ | [Mistral-7B-Merge-14-v0.2.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.IQ4_NL.gguf) | IQ4_NL | 3.87GB |
28
+ | [Mistral-7B-Merge-14-v0.2.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.Q4_K_S.gguf) | Q4_K_S | 3.86GB |
29
+ | [Mistral-7B-Merge-14-v0.2.Q4_K.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.Q4_K.gguf) | Q4_K | 4.07GB |
30
+ | [Mistral-7B-Merge-14-v0.2.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.Q4_K_M.gguf) | Q4_K_M | 4.07GB |
31
+ | [Mistral-7B-Merge-14-v0.2.Q4_1.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.Q4_1.gguf) | Q4_1 | 4.24GB |
32
+ | [Mistral-7B-Merge-14-v0.2.Q5_0.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.Q5_0.gguf) | Q5_0 | 4.65GB |
33
+ | [Mistral-7B-Merge-14-v0.2.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.Q5_K_S.gguf) | Q5_K_S | 4.65GB |
34
+ | [Mistral-7B-Merge-14-v0.2.Q5_K.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.Q5_K.gguf) | Q5_K | 4.78GB |
35
+ | [Mistral-7B-Merge-14-v0.2.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.Q5_K_M.gguf) | Q5_K_M | 4.78GB |
36
+ | [Mistral-7B-Merge-14-v0.2.Q5_1.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.Q5_1.gguf) | Q5_1 | 5.07GB |
37
+ | [Mistral-7B-Merge-14-v0.2.Q6_K.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.Q6_K.gguf) | Q6_K | 5.53GB |
38
+ | [Mistral-7B-Merge-14-v0.2.Q8_0.gguf](https://huggingface.co/RichardErkhov/tourist800_-_Mistral-7B-Merge-14-v0.2-gguf/blob/main/Mistral-7B-Merge-14-v0.2.Q8_0.gguf) | Q8_0 | 7.17GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ license: apache-2.0
46
+ tags:
47
+ - merge
48
+ - mergekit
49
+ - lazymergekit
50
+ - EmbeddedLLM/Mistral-7B-Merge-14-v0.1
51
+ - amazon/MistralLite
52
+ ---
53
+
54
+ # Mistral-7B-Merge-14-v0.2
55
+
56
+ Mistral-7B-Merge-14-v0.2 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
57
+ * [EmbeddedLLM/Mistral-7B-Merge-14-v0.1](https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.1)
58
+ * [amazon/MistralLite](https://huggingface.co/amazon/MistralLite)
59
+
60
+ ## 🧩 Configuration
61
+
62
+ ```yaml
63
+ slices:
64
+ - sources:
65
+ - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.1
66
+ layer_range: [0, 32]
67
+ - model: amazon/MistralLite
68
+ layer_range: [0, 32]
69
+ merge_method: slerp
70
+ base_model: EmbeddedLLM/Mistral-7B-Merge-14-v0.1
71
+ parameters:
72
+ t:
73
+ - filter: self_attn
74
+ value: [0, 0.5, 0.3, 0.7, 1]
75
+ - filter: mlp
76
+ value: [1, 0.5, 0.7, 0.3, 0]
77
+ - value: 0.5
78
+ dtype: bfloat16
79
+
80
+ ```
81
+