lamm-mit / LlaDA-8B-EditFlow-instruct-v500

huggingface.co
Total runs: 10
24-hour runs: 0
7-day runs: 2
30-day runs: 6
Model's Last Updated: January 07 2026

Introduction of LlaDA-8B-EditFlow-instruct-v500

Model Details of LlaDA-8B-EditFlow-instruct-v500

Edit Flows base model

Training

Trained on a single 8xH100 node:

accelerate launch \
   --config_file scripts/accelerate_configs/zero2.yaml \
   examples/editflow/llada/adapt.py --model_name_or_path "GSAI-ML/LLaDA-8B-Instruct" \
   --lm_head_key "model.transformer.ff_out" \
   --init_editflow_from_src True \
   --per_device_train_batch_size 1 \
   --per_device_eval_batch_size 1 \
   --gradient_accumulation_steps 4 \
   --dataset_args "allenai/tulu-3-sft-mixture[train:500000]|lamm-mit/bio-silk-mech-mix-q-a-35K-messages-only|lamm-mit/graph_reasoning_v3_messages" \
   --output_dir "models/LlaDA-8B-EditFlow-instruct-v500" \
   --x0_sampler "masks[length:128]"   --max_length 1500 \
   --num_train_epochs 4 \
   --learning_rate 1e-5  \
   --push_to_hub True --save_strategy "steps" --save_steps 1000  \
   --hub_model_id lamm-mit/LlaDA-8B-EditFlow-instruct-v500 \
   --hub_private_repo True --eval_strategy "no"  \
   --warmup_steps 50  
Sampling
python examples/editflow/sample.py \
  --model_name_or_path "odels/LlaDA-8B-EditFlow-instruct-v500" \
  --mask_length 128 --seed 7070 \
  --prompt "Define materiomics."

Runs of lamm-mit LlaDA-8B-EditFlow-instruct-v500 on huggingface.co

10
Total runs
0
24-hour runs
0
3-day runs
2
7-day runs
6
30-day runs

More Information About LlaDA-8B-EditFlow-instruct-v500 huggingface.co Model

More LlaDA-8B-EditFlow-instruct-v500 license Visit here:

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

LlaDA-8B-EditFlow-instruct-v500 huggingface.co

LlaDA-8B-EditFlow-instruct-v500 huggingface.co is an AI model on huggingface.co that provides LlaDA-8B-EditFlow-instruct-v500's model effect (), which can be used instantly with this lamm-mit LlaDA-8B-EditFlow-instruct-v500 model. huggingface.co supports a free trial of the LlaDA-8B-EditFlow-instruct-v500 model, and also provides paid use of the LlaDA-8B-EditFlow-instruct-v500. Support call LlaDA-8B-EditFlow-instruct-v500 model through api, including Node.js, Python, http.

LlaDA-8B-EditFlow-instruct-v500 huggingface.co Url

https://huggingface.co/lamm-mit/LlaDA-8B-EditFlow-instruct-v500

lamm-mit LlaDA-8B-EditFlow-instruct-v500 online free

LlaDA-8B-EditFlow-instruct-v500 huggingface.co is an online trial and call api platform, which integrates LlaDA-8B-EditFlow-instruct-v500's modeling effects, including api services, and provides a free online trial of LlaDA-8B-EditFlow-instruct-v500, you can try LlaDA-8B-EditFlow-instruct-v500 online for free by clicking the link below.

lamm-mit LlaDA-8B-EditFlow-instruct-v500 online free url in huggingface.co:

https://huggingface.co/lamm-mit/LlaDA-8B-EditFlow-instruct-v500

LlaDA-8B-EditFlow-instruct-v500 install

LlaDA-8B-EditFlow-instruct-v500 is an open source model from GitHub that offers a free installation service, and any user can find LlaDA-8B-EditFlow-instruct-v500 on GitHub to install. At the same time, huggingface.co provides the effect of LlaDA-8B-EditFlow-instruct-v500 install, users can directly use LlaDA-8B-EditFlow-instruct-v500 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

LlaDA-8B-EditFlow-instruct-v500 install url in huggingface.co:

https://huggingface.co/lamm-mit/LlaDA-8B-EditFlow-instruct-v500

Url of LlaDA-8B-EditFlow-instruct-v500

LlaDA-8B-EditFlow-instruct-v500 huggingface.co Url

Provider of LlaDA-8B-EditFlow-instruct-v500 huggingface.co

lamm-mit
ORGANIZATIONS

Other API from lamm-mit

huggingface.co

Total runs: 854
Run Growth: 289
Growth Rate: 33.84%
Updated:December 04 2023
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:December 31 2023
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:April 11 2026