Hugging Face's logo

RichardErkhov
/
s1ghhh_-_dissim_round6-gguf

GGUF
Inference Endpoints
conversational
Model card Files Community
RichardErkhov commited on
Commit
3512718
·
verified ·
1 Parent(s): a246b47

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +85 -0
README.md ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ dissim_round6 - GGUF
11
+ - Model creator: https://huggingface.co/s1ghhh/
12
+ - Original model: https://huggingface.co/s1ghhh/dissim_round6/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [dissim_round6.Q2_K.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.Q2_K.gguf) | Q2_K | 2.53GB |
18
+ | [dissim_round6.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.IQ3_XS.gguf) | IQ3_XS | 2.81GB |
19
+ | [dissim_round6.IQ3_S.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.IQ3_S.gguf) | IQ3_S | 2.96GB |
20
+ | [dissim_round6.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.Q3_K_S.gguf) | Q3_K_S | 2.95GB |
21
+ | [dissim_round6.IQ3_M.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.IQ3_M.gguf) | IQ3_M | 3.06GB |
22
+ | [dissim_round6.Q3_K.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.Q3_K.gguf) | Q3_K | 3.28GB |
23
+ | [dissim_round6.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.Q3_K_M.gguf) | Q3_K_M | 3.28GB |
24
+ | [dissim_round6.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.Q3_K_L.gguf) | Q3_K_L | 3.56GB |
25
+ | [dissim_round6.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.IQ4_XS.gguf) | IQ4_XS | 3.67GB |
26
+ | [dissim_round6.Q4_0.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.Q4_0.gguf) | Q4_0 | 3.83GB |
27
+ | [dissim_round6.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.IQ4_NL.gguf) | IQ4_NL | 3.87GB |
28
+ | [dissim_round6.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.Q4_K_S.gguf) | Q4_K_S | 3.86GB |
29
+ | [dissim_round6.Q4_K.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.Q4_K.gguf) | Q4_K | 4.07GB |
30
+ | [dissim_round6.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.Q4_K_M.gguf) | Q4_K_M | 4.07GB |
31
+ | [dissim_round6.Q4_1.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.Q4_1.gguf) | Q4_1 | 4.24GB |
32
+ | [dissim_round6.Q5_0.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.Q5_0.gguf) | Q5_0 | 4.65GB |
33
+ | [dissim_round6.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.Q5_K_S.gguf) | Q5_K_S | 4.65GB |
34
+ | [dissim_round6.Q5_K.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.Q5_K.gguf) | Q5_K | 4.78GB |
35
+ | [dissim_round6.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.Q5_K_M.gguf) | Q5_K_M | 4.78GB |
36
+ | [dissim_round6.Q5_1.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.Q5_1.gguf) | Q5_1 | 5.07GB |
37
+ | [dissim_round6.Q6_K.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.Q6_K.gguf) | Q6_K | 5.53GB |
38
+ | [dissim_round6.Q8_0.gguf](https://huggingface.co/RichardErkhov/s1ghhh_-_dissim_round6-gguf/blob/main/dissim_round6.Q8_0.gguf) | Q8_0 | 7.17GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ base_model:
46
+ - HuggingFaceH4/zephyr-7b-beta
47
+ library_name: transformers
48
+ tags:
49
+ - mergekit
50
+ - merge
51
+
52
+ ---
53
+ # round_5
54
+
55
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
56
+
57
+ ## Merge Details
58
+ ### Merge Method
59
+
60
+ This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
61
+
62
+ ### Models Merged
63
+
64
+ The following models were included in the merge:
65
+ * [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta)
66
+ * /workspace/0814_nips_db_rebuttal/heur/old_codebase/dissim/round_2
67
+
68
+ ### Configuration
69
+
70
+ The following YAML configuration was used to produce this model:
71
+
72
+ ```yaml
73
+ dtype: bfloat16
74
+ merge_method: linear
75
+ models:
76
+ - model: /workspace/0814_nips_db_rebuttal/heur/old_codebase/dissim/round_2
77
+ parameters:
78
+ weight: 0.7
79
+ - model: HuggingFaceH4/zephyr-7b-beta
80
+ parameters:
81
+ weight: 0.30000000000000004
82
+
83
+ ```
84
+
85
+