Lambent / CosmoAlpacaLisa-1b

huggingface.co
Total runs: 14
24-hour runs: -1
7-day runs: 5
30-day runs: 8
Model's Last Updated: April 05 2024
text-generation

Introduction of CosmoAlpacaLisa-1b

Model Details of CosmoAlpacaLisa-1b

Trying out some LISA training. A few too many numbers changed to be quite directly comparable, but here's the nous-eval comparisons with the CosmoAlpacaLight using LORA:

Model AGIEval GPT4All TruthfulQA Bigbench Average
CosmoAlpacaLisa-1b 23.89 51.93 39.93 28.68 36.11
Model AGIEval GPT4All TruthfulQA Bigbench Average
CosmoAlpacaLight-1b 24.28 51.31 40.33 29.47 36.35
Model AGIEval GPT4All TruthfulQA Bigbench Average
cosmo-1b 22.97 52.01 38.02 28.73 35.43

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

base_model: HuggingFaceTB/cosmo-1b
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: vicgalle/alpaca-gpt4
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./lisa-out

sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true

adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:

lisa_n_layers: 8
lisa_step_interval: 10
lisa_layers_attribute: model.layers

wandb_project: CosmoAlpacaLisa-1b-v0.1
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 5e-5

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

lisa-out

This model is a fine-tuned version of HuggingFaceTB/cosmo-1b on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0634
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: 5e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 10
  • num_epochs: 1
Training results
Training Loss Epoch Step Validation Loss
1.2281 0.0 1 1.2636
1.0796 0.25 166 1.0695
1.0272 0.5 332 1.0644
1.0471 0.75 498 1.0634
Framework versions
  • Transformers 4.40.0.dev0
  • Pytorch 2.1.2+cu118
  • Datasets 2.18.0
  • Tokenizers 0.15.0

Runs of Lambent CosmoAlpacaLisa-1b on huggingface.co

14
Total runs
-1
24-hour runs
1
3-day runs
5
7-day runs
8
30-day runs

More Information About CosmoAlpacaLisa-1b huggingface.co Model

More CosmoAlpacaLisa-1b license Visit here:

https://choosealicense.com/licenses/cc

CosmoAlpacaLisa-1b huggingface.co

CosmoAlpacaLisa-1b huggingface.co is an AI model on huggingface.co that provides CosmoAlpacaLisa-1b's model effect (), which can be used instantly with this Lambent CosmoAlpacaLisa-1b model. huggingface.co supports a free trial of the CosmoAlpacaLisa-1b model, and also provides paid use of the CosmoAlpacaLisa-1b. Support call CosmoAlpacaLisa-1b model through api, including Node.js, Python, http.

CosmoAlpacaLisa-1b huggingface.co Url

https://huggingface.co/Lambent/CosmoAlpacaLisa-1b

Lambent CosmoAlpacaLisa-1b online free

CosmoAlpacaLisa-1b huggingface.co is an online trial and call api platform, which integrates CosmoAlpacaLisa-1b's modeling effects, including api services, and provides a free online trial of CosmoAlpacaLisa-1b, you can try CosmoAlpacaLisa-1b online for free by clicking the link below.

Lambent CosmoAlpacaLisa-1b online free url in huggingface.co:

https://huggingface.co/Lambent/CosmoAlpacaLisa-1b

CosmoAlpacaLisa-1b install

CosmoAlpacaLisa-1b is an open source model from GitHub that offers a free installation service, and any user can find CosmoAlpacaLisa-1b on GitHub to install. At the same time, huggingface.co provides the effect of CosmoAlpacaLisa-1b install, users can directly use CosmoAlpacaLisa-1b installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

CosmoAlpacaLisa-1b install url in huggingface.co:

https://huggingface.co/Lambent/CosmoAlpacaLisa-1b

Url of CosmoAlpacaLisa-1b

CosmoAlpacaLisa-1b huggingface.co Url

Provider of CosmoAlpacaLisa-1b huggingface.co

Lambent
ORGANIZATIONS

Other API from Lambent

huggingface.co

Total runs: 104
Run Growth: 12
Growth Rate: 11.54%
Updated:March 16 2024
huggingface.co

Total runs: 40
Run Growth: 18
Growth Rate: 45.00%
Updated:March 17 2026
huggingface.co

Total runs: 26
Run Growth: 12
Growth Rate: 46.15%
Updated:March 26 2026
huggingface.co

Total runs: 12
Run Growth: -16
Growth Rate: -133.33%
Updated:March 09 2026