metadata

license: llama2
language:
  - en
pipeline_tag: text-generation
inference: false
tags:
  - dare
  - super mario merge
  - pytorch
  - llama
  - codellama

codellama 34b mega merge

The following were merged with DARE using https://github.com/martyn/safetensors-merge-supermario

Mergelist

codellama/CodeLlama-34b-hf
codellama/CodeLlama-34b-Instruct-hf
EleutherAI/llemma_34b
allenai/codetulu-2-34b
uukuguy/speechless-codellama-34b-v2.0
codellama/CodeLlama-34b-Python-hf
mzbac/CodeLlama-34b-guanaco
ehartford/WizardLM-1.0-Uncensored-CodeLlama-34b
ehartford/Samantha-1.11-CodeLlama-34b
uukuguy/speechless-codellama-dolphin-orca-platypus-34b
Phind/Phind-CodeLlama-34B-v1
Phind/Phind-CodeLlama-34B-Python-v1
Phind/Phind-CodeLlama-34B-v2

These models failed to merge:

pharaouk/unnatural_codellama_34B
codefuse-ai/CodeFuse-CodeLlama-34B
XAgentTeam/XAgentLLaMa-34B-preview

Merge command

python3 hf_merge.py codellama.txt codellama -p 0.12 -lambda 2.125