Hugging Face's logo

kingabzpro
/
zephyr-7b-beta-Agent-Instruct

Text Generation
PEFT
Safetensors
English
pretrained
lora
qlora
4bit
Model card Files
xet
 Community
How to use from the
Use from the
PEFT library
from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("HuggingFaceH4/zephyr-7b-beta")
model = PeftModel.from_pretrained(base_model, "kingabzpro/zephyr-7b-beta-Agent-Instruct")

Training procedure

The following bitsandbytes quantization config was used during training:

  • quant_method: bitsandbytes
  • load_in_8bit: False
  • load_in_4bit: True
  • 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: nf4
  • bnb_4bit_use_double_quant: False
  • bnb_4bit_compute_dtype: bfloat16

Framework versions

  • PEFT 0.7.0
Downloads last month
2
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for kingabzpro/zephyr-7b-beta-Agent-Instruct

Base model

mistralai/Mistral-7B-v0.1
Finetuned
HuggingFaceH4/zephyr-7b-beta
Adapter
(414)
this model

Dataset used to train kingabzpro/zephyr-7b-beta-Agent-Instruct

Collection including kingabzpro/zephyr-7b-beta-Agent-Instruct