Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
Casper_falcon_7b – AI Model by Casper0508 | AlphaNeural AI
You can deploy this model and start earning money today!
Casper0508
/
Casper_falcon_7b
like
0
peft
tensorboard
safetensors
generated_from_trainer
ybelkada/falcon-7b-sharded-bf16
adapter
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Casper_falcon_7b
This model is a fine-tuned version of
ybelkada/falcon-7b-sharded-bf16
on the None dataset.
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
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: bfloat16
load_in_4bit: True
load_in_8bit: False
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 0.0002
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
training_steps: 200
Training results
Framework versions
PEFT 0.4.0
Transformers 4.38.2
Pytorch 2.1.0+cu121
Datasets 2.13.1
Tokenizers 0.15.2
