Lambent / danube2-upscale-1.1

huggingface.co
Total runs: 21
24-hour runs: 4
7-day runs: -1
30-day runs: 7
Model's Last Updated: April 12 2024
text-generation

Introduction of danube2-upscale-1.1

Model Details of danube2-upscale-1.1

Aim was to repair damage caused by duplicating the upscale with some additional training on completion from Cosmopedia.

Seemed to be converged at 50% epoch so I cut it off and used that adapter, which I hope actually did something because it wasn't a checkpoint.

eq_bench testing, as a quick reference, strongly suggests it did; but I'm not sure how much that one's just random on a small model like this.

It also seems to be generating completions much more smoothly than its predecessor, though, rather than getting stuck in a repeated word, which is certainly a good sign.

Nous evals:

Model AGIEval GPT4All TruthfulQA Bigbench Average
danube2-upscale-1.1 25.43 60.13 40.22 32.06 39.46

Original model:

Model AGIEval GPT4All TruthfulQA Bigbench Average
h2o-danube2-1.8b-base 25.65 62.26 38.05 32.89 39.71

Axolotl config was something like this:

base_model: Lambent/danube2-upscale-1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
trust_remote_code: false

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: HuggingFaceTB/cosmopedia-100k
    type: completion
dataset_prepared_path: prepared-pedia
val_set_size: 0.01
output_dir: ./qlora-out

sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

adapter: qlora
lora_model_dir:
lora_r: 128
lora_alpha: 128
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: qlora-danube-upscale
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.0002

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

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.002
fsdp:
fsdp_config:
special_tokens:

Runs of Lambent danube2-upscale-1.1 on huggingface.co

21
Total runs
4
24-hour runs
1
3-day runs
-1
7-day runs
7
30-day runs

More Information About danube2-upscale-1.1 huggingface.co Model

More danube2-upscale-1.1 license Visit here:

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

danube2-upscale-1.1 huggingface.co

danube2-upscale-1.1 huggingface.co is an AI model on huggingface.co that provides danube2-upscale-1.1's model effect (), which can be used instantly with this Lambent danube2-upscale-1.1 model. huggingface.co supports a free trial of the danube2-upscale-1.1 model, and also provides paid use of the danube2-upscale-1.1. Support call danube2-upscale-1.1 model through api, including Node.js, Python, http.

danube2-upscale-1.1 huggingface.co Url

https://huggingface.co/Lambent/danube2-upscale-1.1

Lambent danube2-upscale-1.1 online free

danube2-upscale-1.1 huggingface.co is an online trial and call api platform, which integrates danube2-upscale-1.1's modeling effects, including api services, and provides a free online trial of danube2-upscale-1.1, you can try danube2-upscale-1.1 online for free by clicking the link below.

Lambent danube2-upscale-1.1 online free url in huggingface.co:

https://huggingface.co/Lambent/danube2-upscale-1.1

danube2-upscale-1.1 install

danube2-upscale-1.1 is an open source model from GitHub that offers a free installation service, and any user can find danube2-upscale-1.1 on GitHub to install. At the same time, huggingface.co provides the effect of danube2-upscale-1.1 install, users can directly use danube2-upscale-1.1 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

danube2-upscale-1.1 install url in huggingface.co:

https://huggingface.co/Lambent/danube2-upscale-1.1

Url of danube2-upscale-1.1

danube2-upscale-1.1 huggingface.co Url

Provider of danube2-upscale-1.1 huggingface.co

Lambent
ORGANIZATIONS

Other API from Lambent

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