metadata
base_model: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
datasets:
- ehartford/dolphin
- jondurbin/airoboros-2.2.1
- ehartford/dolphin-coder
- teknium/openhermes
- ise-uiuc/Magicoder-OSS-Instruct-75K
- ise-uiuc/Magicoder-Evol-Instruct-110K
- LDJnr/Capybara
inference: false
language:
- en
license: apache-2.0
model_creator: Cognitive Computations
model_name: Dolphin 2.6 Mistral 7B DPO Laser
model_type: mistral
prompt_template: |
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
quantized_by: lr1729
GGUF quants of https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser with importance matrix calculations run on 20k_random_data.txt for improved perplexity.