Add README
Browse files
README.md
CHANGED
@@ -1,3 +1,49 @@
|
|
1 |
---
|
2 |
license: llama2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: llama2
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
pipeline_tag: text-generation
|
6 |
+
inference: false
|
7 |
+
tags:
|
8 |
+
- dare
|
9 |
+
- super mario merge
|
10 |
+
- pytorch
|
11 |
+
- llama
|
12 |
+
- codellama
|
13 |
---
|
14 |
+
|
15 |
+
# codellama 34b mega merge
|
16 |
+
|
17 |
+
The following were merged with DARE using [https://github.com/martyn/safetensors-merge-supermario](https://github.com/martyn/safetensors-merge-supermario)
|
18 |
+
|
19 |
+
## Mergelist
|
20 |
+
|
21 |
+
|
22 |
+
```
|
23 |
+
codellama/CodeLlama-34b-hf
|
24 |
+
codellama/CodeLlama-34b-Instruct-hf
|
25 |
+
EleutherAI/llemma_34b
|
26 |
+
allenai/codetulu-2-34b
|
27 |
+
uukuguy/speechless-codellama-34b-v2.0
|
28 |
+
codellama/CodeLlama-34b-Python-hf
|
29 |
+
mzbac/CodeLlama-34b-guanaco
|
30 |
+
ehartford/WizardLM-1.0-Uncensored-CodeLlama-34b
|
31 |
+
ehartford/Samantha-1.11-CodeLlama-34b
|
32 |
+
uukuguy/speechless-codellama-dolphin-orca-platypus-34b
|
33 |
+
Phind/Phind-CodeLlama-34B-v1
|
34 |
+
Phind/Phind-CodeLlama-34B-Python-v1
|
35 |
+
Phind/Phind-CodeLlama-34B-v2
|
36 |
+
```
|
37 |
+
|
38 |
+
These models failed to merge:
|
39 |
+
```
|
40 |
+
pharaouk/unnatural_codellama_34B
|
41 |
+
codefuse-ai/CodeFuse-CodeLlama-34B
|
42 |
+
XAgentTeam/XAgentLLaMa-34B-preview
|
43 |
+
```
|
44 |
+
|
45 |
+
## Merge command
|
46 |
+
|
47 |
+
```
|
48 |
+
python3 hf_merge.py codellama.txt codellama -p 0.12 -lambda 2.125
|
49 |
+
```
|