Add pipeline tag, link to code

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +15 -2
README.md CHANGED
@@ -1,6 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
1
 
2
  ---
3
  license: llama2
 
 
4
  base_model:
5
  - unsloth/llama-2-13b
6
  - layoric/llama-2-13b-code-alpaca
@@ -9,7 +22,7 @@ tags:
9
  - merge
10
  ---
11
  # AIM Paper Checkpoints Uploaded For Replication
12
- This repository includes one of the checkpoints used in the paper "Activation-Informed Merging of Large Language Models". Specifics of this model are as follows:
13
 
14
  - **Merging Method:** WIDEN
15
  - **Models Used In Merging**
@@ -18,4 +31,4 @@ This repository includes one of the checkpoints used in the paper "Activation-In
18
  - ***Math:*** vanillaOVO/WizardMath-13B-V1.0
19
  - **AIM:** True
20
 
21
- Benchmark results and paper details can be found at the official [GitHub](https://github.com/ahnobari/ActivationInformedMerging.git).
 
1
+ ---
2
+ license: llama2
3
+ library_name: transformers
4
+ pipeline_tag: text-generation
5
+ base_model:
6
+ - unsloth/llama-2-13b
7
+ - layoric/llama-2-13b-code-alpaca
8
+ - vanillaOVO/WizardMath-13B-V1.0
9
+ tags:
10
+ - merge
11
+ ---
12
 
13
  ---
14
  license: llama2
15
+ library_name: transformers
16
+ pipeline_tag: text-generation
17
  base_model:
18
  - unsloth/llama-2-13b
19
  - layoric/llama-2-13b-code-alpaca
 
22
  - merge
23
  ---
24
  # AIM Paper Checkpoints Uploaded For Replication
25
+ This repository includes one of the checkpoints used in the paper "Activation-Informed Merging of Large Language Models" at https://huggingface.co/papers/2502.02421. Specifics of this model are as follows:
26
 
27
  - **Merging Method:** WIDEN
28
  - **Models Used In Merging**
 
31
  - ***Math:*** vanillaOVO/WizardMath-13B-V1.0
32
  - **AIM:** True
33
 
34
+ Benchmark results and paper details can be found at the official [GitHub](https://github.com/ahnobari/ActivationInformedMerging.git).