Sponsored by PoYo.AI
Toolify Toolify logo
AI Models
glm-4.7-flash-lovable

baseten-admin / glm-4.7-flash-lovable

Run on huggingface.co
huggingface.co
Total runs: 10
24-hour runs: 0
7-day runs: 3
30-day runs: 3
Model's Last Updated: 2月 15 2026
text-generation

Introduction of glm-4.7-flash-lovable

Model Details of glm-4.7-flash-lovable

zai-org/GLM-4.7-Flash Fine-Tune

Fine-tuned with Whetstone v2 using the Megatron-LM backend.

Training details
Base model zai-org/GLM-4.7-Flash
Dataset baseten-admin/lovable-agent
Method LORA (rank=32, alpha=32)
Epochs ?
Learning rate 2e-4
Global batch size 8
Max length 200000
W&B run glm_4.7_flash_baseten-admin_lovable-agent_H200:8:2_v5
Full configuration

The exact training configuration used for this run: 

model: zai-org/GLM-4.7-Flash
dataset: baseten-admin/lovable-agent
use_hf: true
check_model: false
load_safetensors: true
template: glm4_7
response_prefix: ''
add_non_thinking_prefix: false
train_type: lora
lora_rank: 32
lora_alpha: 32
merge_lora: true
target_modules:
- all-linear
train_iters: 10
lr: 2e-4
lr_decay_style: constant
clip_grad: 1.0
bf16: true
packing: false
micro_batch_size: 1
global_batch_size: 8
max_length: 200000
tensor_model_parallel_size: 4
pipeline_model_parallel_size: 1
context_parallel_size: 1
expert_model_parallel_size: 2
sequence_parallel: true
cross_entropy_loss_fusion: true
cross_entropy_fusion_impl: te
recompute_granularity: full
save_interval: 5
save_safetensors: true
no_save_optim: true
no_save_rng: true
log_interval: 1
report_to: wandb
wandb_exp_name: glm_4.7_flash_baseten-admin_lovable-agent_H200:8:2_v5
num_workers: 8
dataset_num_proc: 8
lazy_tokenize: true
load_from_cache_file: true
recompute_method: block
recompute_num_layers: 47

Runs of baseten-admin glm-4.7-flash-lovable on huggingface.co

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

More Information About glm-4.7-flash-lovable huggingface.co Model

glm-4.7-flash-lovable huggingface.co

glm-4.7-flash-lovable huggingface.co is an AI model on huggingface.co that provides glm-4.7-flash-lovable's model effect (), which can be used instantly with this baseten-admin glm-4.7-flash-lovable model. huggingface.co supports a free trial of the glm-4.7-flash-lovable model, and also provides paid use of the glm-4.7-flash-lovable. Support call glm-4.7-flash-lovable model through api, including Node.js, Python, http.

glm-4.7-flash-lovable huggingface.co Url

https://huggingface.co/baseten-admin/glm-4.7-flash-lovable

baseten-admin glm-4.7-flash-lovable online free

glm-4.7-flash-lovable huggingface.co is an online trial and call api platform, which integrates glm-4.7-flash-lovable's modeling effects, including api services, and provides a free online trial of glm-4.7-flash-lovable, you can try glm-4.7-flash-lovable online for free by clicking the link below.

baseten-admin glm-4.7-flash-lovable online free url in huggingface.co:

https://huggingface.co/baseten-admin/glm-4.7-flash-lovable

glm-4.7-flash-lovable install

glm-4.7-flash-lovable is an open source model from GitHub that offers a free installation service, and any user can find glm-4.7-flash-lovable on GitHub to install. At the same time, huggingface.co provides the effect of glm-4.7-flash-lovable install, users can directly use glm-4.7-flash-lovable installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

glm-4.7-flash-lovable install url in huggingface.co:

https://huggingface.co/baseten-admin/glm-4.7-flash-lovable

Url of glm-4.7-flash-lovable

glm-4.7-flash-lovable huggingface.co Url

Provider of glm-4.7-flash-lovable huggingface.co

baseten-admin
ORGANIZATIONS
huggingface.co

Other API from baseten-admin