Hugging Face's logo

Tarek07
/
Primogenitor-V2.1-LLaMa-70B

Text Generation
Transformers
Safetensors
llama
mergekit
Merge
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Tarek07 commited on
Commit
04e29f2
·
verified ·
1 Parent(s): baec9c8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -16
README.md CHANGED
@@ -1,5 +1,11 @@
1
  ---
2
- base_model: []
 
 
 
 
 
 
3
  library_name: transformers
4
  tags:
5
  - mergekit
@@ -13,17 +19,17 @@ This is a merge of pre-trained language models created using [mergekit](https://
13
  ## Merge Details
14
  ### Merge Method
15
 
16
- This model was merged using the [Linear DELLA](https://arxiv.org/abs/2406.11617) merge method using downloads/Llama-3.1-Nemotron-lorablated-70B as a base.
17
 
18
  ### Models Merged
19
 
20
  The following models were included in the merge:
21
- * downloads/Anubis-70B-v1
22
- * downloads/L3.1-70B-Hanami-x1
23
- * downloads/EVA-LLaMA-3.33-70B-v0.1
24
- * downloads/70B-L3.3-Cirrus-x1
25
- * downloads/Wayfarer-Large-70B-Llama-3.3
26
- * downloads/Negative_LLAMA_70B
27
 
28
  ### Configuration
29
 
@@ -31,37 +37,37 @@ The following YAML configuration was used to produce this model:
31
 
32
  ```yaml
33
  models:
34
- - model: downloads/L3.1-70B-Hanami-x1
35
  parameters:
36
  weight: 0.16
37
  density: 0.7
38
- - model: downloads/70B-L3.3-Cirrus-x1
39
  parameters:
40
  weight: 0.16
41
  density: 0.7
42
- - model: downloads/Wayfarer-Large-70B-Llama-3.3
43
  parameters:
44
  weight: 0.16
45
  density: 0.7
46
- - model: downloads/Negative_LLAMA_70B
47
  parameters:
48
  weight: 0.20
49
  density: 0.7
50
- - model: downloads/Anubis-70B-v1
51
  parameters:
52
  weight: 0.16
53
  density: 0.7
54
- - model: downloads/EVA-LLaMA-3.33-70B-v0.1
55
  parameters:
56
  weight: 0.16
57
  density: 0.7
58
  merge_method: della_linear
59
- base_model: downloads/Llama-3.1-Nemotron-lorablated-70B
60
  parameters:
61
  epsilon: 0.2
62
  lambda: 1.1
63
  normalize: true
64
  out_dtype: bfloat16
65
  tokenizer:
66
- source: downloads/Negative_LLAMA_70B
67
  ```
 
1
  ---
2
+ base_model:
3
+ - Sao10K/L3.1-70B-Hanami-x1
4
+ - Sao10K/70B-L3.3-Cirrus-x1
5
+ - LatitudeGames/Wayfarer-Large-70B-Llama-3.3
6
+ - SicariusSicariiStuff/Negative_LLAMA_70B
7
+ - TheDrummer/Anubis-70B-v1
8
+ - EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
9
  library_name: transformers
10
  tags:
11
  - mergekit
 
19
  ## Merge Details
20
  ### Merge Method
21
 
22
+ This model was merged using the [Linear DELLA](https://arxiv.org/abs/2406.11617) merge method using [nbeerbower/Llama-3.1-Nemotron-lorablated-70B](https://huggingface.co/nbeerbower/Llama-3.1-Nemotron-lorablated-70B) as a base.
23
 
24
  ### Models Merged
25
 
26
  The following models were included in the merge:
27
+ * Sao10K/L3.1-70B-Hanami-x1
28
+ * Sao10K/70B-L3.3-Cirrus-x1
29
+ * LatitudeGames/Wayfarer-Large-70B-Llama-3.3
30
+ * SicariusSicariiStuff/Negative_LLAMA_70B
31
+ * TheDrummer/Anubis-70B-v1
32
+ * EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
33
 
34
  ### Configuration
35
 
 
37
 
38
  ```yaml
39
  models:
40
+ - model: Sao10K/L3.1-70B-Hanami-x1
41
  parameters:
42
  weight: 0.16
43
  density: 0.7
44
+ - model: Sao10K/70B-L3.3-Cirrus-x1
45
  parameters:
46
  weight: 0.16
47
  density: 0.7
48
+ - model: LatitudeGames/Wayfarer-Large-70B-Llama-3.3
49
  parameters:
50
  weight: 0.16
51
  density: 0.7
52
+ - model: SicariusSicariiStuff/Negative_LLAMA_70B
53
  parameters:
54
  weight: 0.20
55
  density: 0.7
56
+ - model: TheDrummer/Anubis-70B-v1
57
  parameters:
58
  weight: 0.16
59
  density: 0.7
60
+ - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
61
  parameters:
62
  weight: 0.16
63
  density: 0.7
64
  merge_method: della_linear
65
+ base_model: nbeerbower/Llama-3.1-Nemotron-lorablated-70B
66
  parameters:
67
  epsilon: 0.2
68
  lambda: 1.1
69
  normalize: true
70
  out_dtype: bfloat16
71
  tokenizer:
72
+ source: SicariusSicariiStuff/Negative_LLAMA_70B
73
  ```