# use google/gemma-7b if you have access#base_model: mhenrichsen/gemma-7bbase_model:google/gemma-7bmodel_type:AutoModelForCausalLMtokenizer_type:AutoTokenizerhub_model_id:MaziyarPanahi/gemma-7b-alpaca-52k-v0.1hf_use_auth_token:trueload_in_8bit:falseload_in_4bit:truestrict:false# huggingface repodatasets:-path:tatsu-lab/alpacatype:alpacaval_set_size:0.1output_dir:./qlora-gemma-7b-alpacaadapter:qloralora_r:32lora_alpha:16lora_dropout:0.05lora_target_linear:truesequence_len:4096sample_packing:falsepad_to_sequence_len:falsewandb_project:wandb_entity:wandb_watch:wandb_name:wandb_log_model:gradient_accumulation_steps:3micro_batch_size:2num_epochs:1optimizer:adamw_bnb_8bitlr_scheduler:cosinelearning_rate:0.0002train_on_inputs:falsegroup_by_length:falsebf16:autofp16:tf32:falsegradient_checkpointing:trueearly_stopping_patience:resume_from_checkpoint:local_rank:logging_steps:1xformers_attention:flash_attention:truewarmup_ratio:0.1evals_per_epoch:4eval_table_size:eval_max_new_tokens:128saves_per_epoch:1debug:deepspeed:weight_decay:0.0fsdp:fsdp_config:special_tokens:
gemma-7b-alpaca-52k-v0.1
This model is a fine-tuned version of
google/gemma-7b
on the None dataset.
It achieves the following results on the evaluation set:
Loss: 1.1468
How to use
PEFT
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM
model_id = "MaziyarPanahi/gemma-7b-alpaca-52k-v0.1"
config = PeftConfig.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained("google/gemma-7b")
model = PeftModel.from_pretrained(model, model_id)
Transformers
# Use a pipeline as a high-level helperfrom transformers import pipeline
model_id = "MaziyarPanahi/gemma-7b-alpaca-52k-v0.1"
pipe = pipeline("text-generation", model=model_id)
# Load model directlyfrom transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 0.0002
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 3
total_train_batch_size: 24
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 48
num_epochs: 1
Training results
Training Loss
Epoch
Step
Validation Loss
1.5395
0.0
1
1.4186
1.099
0.25
488
1.1994
1.2188
0.5
976
1.1751
1.0511
0.75
1464
1.1468
Framework versions
PEFT 0.8.2
Transformers 4.39.0.dev0
Pytorch 2.2.0+cu121
Datasets 2.17.0
Tokenizers 0.15.0
Runs of MaziyarPanahi gemma-7b-alpaca-52k-v0.1 on huggingface.co
616
Total runs
7
24-hour runs
14
3-day runs
21
7-day runs
582
30-day runs
More Information About gemma-7b-alpaca-52k-v0.1 huggingface.co Model
gemma-7b-alpaca-52k-v0.1 huggingface.co is an AI model on huggingface.co that provides gemma-7b-alpaca-52k-v0.1's model effect (), which can be used instantly with this MaziyarPanahi gemma-7b-alpaca-52k-v0.1 model. huggingface.co supports a free trial of the gemma-7b-alpaca-52k-v0.1 model, and also provides paid use of the gemma-7b-alpaca-52k-v0.1. Support call gemma-7b-alpaca-52k-v0.1 model through api, including Node.js, Python, http.
gemma-7b-alpaca-52k-v0.1 huggingface.co is an online trial and call api platform, which integrates gemma-7b-alpaca-52k-v0.1's modeling effects, including api services, and provides a free online trial of gemma-7b-alpaca-52k-v0.1, you can try gemma-7b-alpaca-52k-v0.1 online for free by clicking the link below.
MaziyarPanahi gemma-7b-alpaca-52k-v0.1 online free url in huggingface.co:
gemma-7b-alpaca-52k-v0.1 is an open source model from GitHub that offers a free installation service, and any user can find gemma-7b-alpaca-52k-v0.1 on GitHub to install. At the same time, huggingface.co provides the effect of gemma-7b-alpaca-52k-v0.1 install, users can directly use gemma-7b-alpaca-52k-v0.1 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
gemma-7b-alpaca-52k-v0.1 install url in huggingface.co: