kaitchup/Llama-2-7B-oasstguanaco-adapter

Model

0

stars

5

commits

1

repos using this model

1

linked in READMEs

Nov 27, 2023

updated

peft

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 0.5.0
PEFT 0.5.0

Contributors

4 commits

1 commits

Similar repos

sallywww/invonly

0

sallywww/tier3b_bug

0

sallywww/tot_llama_update

0

HeshamHaroon/llama-2-7b-chat-ar

4

TJKlein/ContrastivePerplexity

1

UnderstandLing/llama-2-7b-chat-bn

0

UnderstandLing/llama-2-7b-chat-pt

2

UnderstandLing/llama-2-7b-chat-es

5

Used in code

stllfe/llm-lora-hotswap

Showcasing how PEFT adapters may be interchanged at Runtime to change behaviour of the same…

1

Linked in READMEs

stllfe/llm-lora-hotswap

Showcasing how PEFT adapters may be interchanged at Runtime to change behaviour of the same…

1

kaitchup/Llama-2-7B-oasstguanaco-adapter

Model

0

stars

5

commits

1

repos using this model

1

linked in READMEs

Nov 27, 2023

updated

peft

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 0.5.0
PEFT 0.5.0

Similar repos

sallywww/invonly

0

sallywww/tier3b_bug

0

sallywww/tot_llama_update

0

HeshamHaroon/llama-2-7b-chat-ar

4

TJKlein/ContrastivePerplexity

1

UnderstandLing/llama-2-7b-chat-bn

0

UnderstandLing/llama-2-7b-chat-pt

2

UnderstandLing/llama-2-7b-chat-es

5

Used in code

stllfe/llm-lora-hotswap

Showcasing how PEFT adapters may be interchanged at Runtime to change behaviour of the same…

1

Linked in READMEs

stllfe/llm-lora-hotswap

Showcasing how PEFT adapters may be interchanged at Runtime to change behaviour of the same…

1

Contributors

4 commits

1 commits