File size: 2,519 Bytes
4ad8cfb
 
 
 
 
 
 
 
 
 
d8b5471
 
4ad8cfb
 
320c3b4
d8b5471
 
4ad8cfb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
---
base_model: []
library_name: transformers
tags:
- mergekit
- merge

---
# Llama-3.1-8B-InitializedEmbeddings_with_Hermes-3

This is [Meta's LLaMA-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) (base model) pre-initialized to [NousResearch/Hermes-3-Llama-3.1-8B's](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B) embedding's special tokens (prompt/chat template).

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

Credit for the idea of this merge goes to Charles Goddard (Creator of mergekit); his merge [chargoddard/Meta-Llama-3-8B-InitializedEmbeds](https://huggingface.co/chargoddard/Meta-Llama-3-8B-InitializedEmbeds) outlined the details for this merge and explained how it all works, and why it is necessary to pre-initialize the base model with the instruct model's embedding's special tokens.


## Merge Details
### Merge Method

This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.

### Models Merged

The following models were included in the merge:
* /Users/jsarnecki/opt/Workspace/meta-llama/Llama-3.1-8B
* /Users/jsarnecki/opt/Workspace/NousResearch/Hermes-3-Llama-3.1-8B

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: linear
dtype: float32
out_dtype: bfloat16
models:
  - model: /Users/jsarnecki/opt/Workspace/meta-llama/Llama-3.1-8B
    parameters:
      weight: 1.0
  - model: /Users/jsarnecki/opt/Workspace/NousResearch/Hermes-3-Llama-3.1-8B 
    parameters:
      weight: 0.0
tokenizer:
  source: /Users/jsarnecki/opt/Workspace/NousResearch/Hermes-3-Llama-3.1-8B
  tokens:
    <|start_header_id|>:
      source: /Users/jsarnecki/opt/Workspace/NousResearch/Hermes-3-Llama-3.1-8B
      force: true
    <|end_header_id|>:
      source: /Users/jsarnecki/opt/Workspace/NousResearch/Hermes-3-Llama-3.1-8B
      force: true
    <|eot_id|>:
      source: /Users/jsarnecki/opt/Workspace/NousResearch/Hermes-3-Llama-3.1-8B
      force: true
    <|begin_of_text|>:
      source: /Users/jsarnecki/opt/Workspace/NousResearch/Hermes-3-Llama-3.1-8B
      force: true
    <|end_of_text|>:
      source: /Users/jsarnecki/opt/Workspace/NousResearch/Hermes-3-Llama-3.1-8B
      force: true
    <|im_start|>:
      source: /Users/jsarnecki/opt/Workspace/NousResearch/Hermes-3-Llama-3.1-8B
      force: true
    <|im_end|>:
      source: /Users/jsarnecki/opt/Workspace/NousResearch/Hermes-3-Llama-3.1-8B
      force: true
        
    

```