Downloads · 30 days
5
19% of all-time downloads
supportGPT-v7
rghosh8/supportGPT-v7
supportGPT-v7 is a text generation model from rghosh8. Use it when you need the model to write or continue text. It is set up for peft.
The following bitsandbytes quantization config was used during training: - quantmethod: bitsandbytes - loadin8bit: False - loadin4bit: True - llmint8threshold: 6.0 - llmint8skipmodules: None - llmint8enablefp32cpuoffl…
All-time downloads
26
Public
Repo size
227 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt302 MB · 66%
At a glance
- Task
- Text Generation
- Library
- peft
- Model type
- falcon
- Access
- Public
- Created
- Sep 23, 2023
- Updated
- Sep 23, 2023
- SHA
- c9c595fb
Try a prompt
Model card
From the Hugging Face model README
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: True
- bnb_4bit_compute_dtype: float16
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: True
- bnb_4bit_compute_dtype: float16
Framework versions
-
PEFT 0.6.0.dev0
-
PEFT 0.6.0.dev0
- Task
- Text Generation
- Library
- peft
- Type
- falcon
- Languages
- en
- Created
- Sep 23, 2023
- Updated
- Sep 23, 2023