dolphin-2.1-mistral-7b-agent-lora

dolphin-2.1-mistral-7b-agent-lora

This is a rank 64 LoRA finetune of ehartford/dolphin-2.1-mistral-7b on THUDM/AgentInstruct for 1.1 epochs.

<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

<!-- Provide a longer summary of what this model is. -->

Prompt Format

Dolphin-Agent uses ChatML as the prompt format:

<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
If Danny owns a bike, then Edward owns a bike. If Edward owns a bike, then Freddy owns a bike. If Danny owns a bike, which of the following statements must be true? Let's think step by step.

I. Edward owns a bike.
II. Freddy owns a bike.
III. Freddy does not own a bike.

Choose one answer:
I only
II only
III only
I and II only
I and III only
<|im_end|>
<|im_start|>assistant

Training procedure

The following bitsandbytes quantization config was used during training:

• quant_method: bitsandbytes
• load_in_8bit: True
• load_in_4bit: False
• llm_int8_threshold: 6.0
• llm_int8_skip_modules: None
• llm_int8_enable_fp32_cpu_offload: False
• llm_int8_has_fp16_weight: False
• bnb_4bit_quant_type: fp4
• bnb_4bit_use_double_quant: False
• bnb_4bit_compute_dtype: float32

Framework versions

• PEFT 0.6.0.dev0

Training procedure

Framework versions

• PEFT 0.6.0.dev0