bjoernp commited on
Commit
ff7a696
·
verified ·
1 Parent(s): a64b744

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +50 -0
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama3
3
+ language:
4
+ - de
5
+ library_name: transformers
6
+ ---
7
+
8
+ # Llama3_DiscoLeo_8B_DARE_Experimental_4bit_awq_glc
9
+
10
+ This model is a 4 bit quantization of [DiscoResearch/Llama3_DiscoLeo_8B_DARE_Experimental](https://huggingface.co/DiscoResearch/Llama3_DiscoLeo_8B_DARE_Experimental).
11
+ Copy of the original model card:
12
+
13
+
14
+ [DiscoResearch/Llama3_German_8B_v0.1](https://huggingface.co/collections/DiscoResearch/discoleo-8b-llama3-for-german-6650527496c0fafefd4c9729) is a large language model based on [Meta's Llama3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B). It is specialized for the German language through continuous pretraining on 65 billion high-quality tokens, similar to previous [LeoLM](https://huggingface.co/LeoLM) or [Occiglot](https://huggingface.co/collections/occiglot/occiglot-eu5-7b-v01-65dbed502a6348b052695e01) models.
15
+
16
+ This is a merge of our instruct model with the Instruct model by Meta. Created using [mergekit](https://github.com/cg123/mergekit).
17
+
18
+ ## Merge Details
19
+ ### Merge Method
20
+
21
+ This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) as a base.
22
+
23
+ ### Models Merged
24
+
25
+ The following models were included in the merge:
26
+ * [DiscoResearch/Llama3_DiscoLeo_Instruct_8B_v0.1](https://huggingface.co/DiscoResearch/Llama3_DiscoLeo_Instruct_8B_v0.1)
27
+ * [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
28
+
29
+ ### Configuration
30
+
31
+ The following YAML configuration was used to produce this model:
32
+
33
+ ```yaml
34
+ models:
35
+ - model: DiscoResearch/Llama3_DiscoLeo_Instruct_8B_v0.1
36
+ parameters:
37
+ density: 0.5
38
+ weight: 0.5
39
+ - model: meta-llama/Meta-Llama-3-8B-Instruct
40
+ parameters:
41
+ density: 0.5
42
+ weight: 0.5
43
+ merge_method: dare_ties
44
+ base_model: meta-llama/Meta-Llama-3-8B
45
+ parameters:
46
+ normalize: true
47
+ int8_mask: false
48
+ dtype: bfloat16
49
+
50
+ ```