eac123 / olmo3-7b-exp1b-lora128-e5

huggingface.co
Total runs: 5
24-hour runs: 0
7-day runs: 0
30-day runs: 5
Model's Last Updated: March 11 2026
text-generation

Introduction of olmo3-7b-exp1b-lora128-e5

Model Details of olmo3-7b-exp1b-lora128-e5

Built with Axolotl

See axolotl config

axolotl version: 0.15.0

# ── Continued Pretraining: 7B on 8×A40 (48GB) ──

base_model: allenai/Olmo-3-1025-7B
tokenizer_type: AutoTokenizer

# plugins:
#   - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin

# ── Data ──
datasets:
  - path: data/1b/all.jsonl
    type: completion
    field: completion
dataset_prepared_path: last_run_prepared

# ── Sequence / packing ──
sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true
# NOTE: do NOT enable group_by_length with sample_packing

# ── Batch sizing ──
# Per-GPU: 4 seqs × 2048 tok = 8k tokens/step/GPU
# Global:  4 × 4 accum × 8 GPUs = 128 effective seqs/step

# micro_batch_size: 4
# gradient_accumulation_steps: 4
micro_batch_size: 4
gradient_accumulation_steps: 1

# ── Training ──
train_on_inputs: true
optimizer: adamw_8bit
lr_scheduler: cosine
learning_rate: 3e-4
#warmup_steps: 20
#max_steps: 100
warmup_ratio: 0.03
num_epochs: 50 # apparently we can use this instead of max_steps?
weight_decay: 0.01

# ── Precision / memory ──
bf16: auto
tf32: true
flash_attention: true
gradient_checkpointing: true

# ── DeepSpeed ZeRO Stage 2 ──
deepspeed: train/axolotl-cpt/ds_stage2.json

# ── Logging ──
logging_steps: 1
save_strategy: steps
save_steps: 20
save_total_limit: 40

use_wandb: true
wandb_name: "olmo3-7b-exp1b-lora"
wandb_project: "out-of-context-chatbots"

# -- qlora --
load_in_8bit: false
load_in_4bit: false
adapter: lora

lora_r: 128
use_rslora: true
lora_alpha: 32
#lora_dropout: 0.05
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj



model-out

This model is a fine-tuned version of allenai/Olmo-3-1025-7B on the data/1b/all.jsonl dataset.

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: 0.0003
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • total_train_batch_size: 32
  • total_eval_batch_size: 32
  • optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 3
  • training_steps: 100
Training results
Framework versions
  • PEFT 0.18.1
  • Transformers 5.3.0
  • Pytorch 2.6.0+cu126
  • Datasets 4.5.0
  • Tokenizers 0.22.2

Runs of eac123 olmo3-7b-exp1b-lora128-e5 on huggingface.co

5
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
5
30-day runs

More Information About olmo3-7b-exp1b-lora128-e5 huggingface.co Model

More olmo3-7b-exp1b-lora128-e5 license Visit here:

https://choosealicense.com/licenses/apache-2.0

olmo3-7b-exp1b-lora128-e5 huggingface.co

olmo3-7b-exp1b-lora128-e5 huggingface.co is an AI model on huggingface.co that provides olmo3-7b-exp1b-lora128-e5's model effect (), which can be used instantly with this eac123 olmo3-7b-exp1b-lora128-e5 model. huggingface.co supports a free trial of the olmo3-7b-exp1b-lora128-e5 model, and also provides paid use of the olmo3-7b-exp1b-lora128-e5. Support call olmo3-7b-exp1b-lora128-e5 model through api, including Node.js, Python, http.

olmo3-7b-exp1b-lora128-e5 huggingface.co Url

https://huggingface.co/eac123/olmo3-7b-exp1b-lora128-e5

eac123 olmo3-7b-exp1b-lora128-e5 online free

olmo3-7b-exp1b-lora128-e5 huggingface.co is an online trial and call api platform, which integrates olmo3-7b-exp1b-lora128-e5's modeling effects, including api services, and provides a free online trial of olmo3-7b-exp1b-lora128-e5, you can try olmo3-7b-exp1b-lora128-e5 online for free by clicking the link below.

eac123 olmo3-7b-exp1b-lora128-e5 online free url in huggingface.co:

https://huggingface.co/eac123/olmo3-7b-exp1b-lora128-e5

olmo3-7b-exp1b-lora128-e5 install

olmo3-7b-exp1b-lora128-e5 is an open source model from GitHub that offers a free installation service, and any user can find olmo3-7b-exp1b-lora128-e5 on GitHub to install. At the same time, huggingface.co provides the effect of olmo3-7b-exp1b-lora128-e5 install, users can directly use olmo3-7b-exp1b-lora128-e5 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

olmo3-7b-exp1b-lora128-e5 install url in huggingface.co:

https://huggingface.co/eac123/olmo3-7b-exp1b-lora128-e5

Url of olmo3-7b-exp1b-lora128-e5

olmo3-7b-exp1b-lora128-e5 huggingface.co Url

Provider of olmo3-7b-exp1b-lora128-e5 huggingface.co

eac123
ORGANIZATIONS

Other API from eac123

huggingface.co

Total runs: 23
Run Growth: 21
Growth Rate: 91.30%
Updated:February 25 2026
huggingface.co

Total runs: 21
Run Growth: 15
Growth Rate: 71.43%
Updated:February 25 2026
huggingface.co

Total runs: 11
Run Growth: 10
Growth Rate: 100.00%
Updated:February 25 2026
huggingface.co

Total runs: 11
Run Growth: 10
Growth Rate: 100.00%
Updated:February 25 2026
huggingface.co

Total runs: 10
Run Growth: 5
Growth Rate: 50.00%
Updated:August 30 2025