Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

Jnx03
/
kanitakorn-v49b-deepseek-v48b0106-from-v44c4-lr15e7-step2

PEFT
Safetensors
Thai
English
thai
kanitakorn
single-model
greedy-eval
Model card Files Files and versions
xet
Community

Instructions to use Jnx03/kanitakorn-v49b-deepseek-v48b0106-from-v44c4-lr15e7-step2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use Jnx03/kanitakorn-v49b-deepseek-v48b0106-from-v44c4-lr15e7-step2 with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("unsloth/DeepSeek-R1-Distill-Qwen-14B")
    model = PeftModel.from_pretrained(base_model, "Jnx03/kanitakorn-v49b-deepseek-v48b0106-from-v44c4-lr15e7-step2")
  • Notebooks
  • Google Colab
  • Kaggle
kanitakorn-v49b-deepseek-v48b0106-from-v44c4-lr15e7-step2
562 MB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
Jnx03's picture
Jnx03
v49b-deepseek-v48b0106-from-v44c4-lr15e7-step2: sft-lora
825e387 verified 3 months ago
  • .gitattributes
    1.57 kB
    v49b-deepseek-v48b0106-from-v44c4-lr15e7-step2: sft-lora 3 months ago
  • README.md
    1.31 kB
    v49b-deepseek-v48b0106-from-v44c4-lr15e7-step2: sft-lora 3 months ago
  • adapter_config.json
    1.25 kB
    v49b-deepseek-v48b0106-from-v44c4-lr15e7-step2: sft-lora 3 months ago
  • adapter_model.safetensors
    551 MB
    xet
    v49b-deepseek-v48b0106-from-v44c4-lr15e7-step2: sft-lora 3 months ago
  • chat_template.jinja
    2.25 kB
    v49b-deepseek-v48b0106-from-v44c4-lr15e7-step2: sft-lora 3 months ago
  • tokenizer.json
    11.4 MB
    xet
    v49b-deepseek-v48b0106-from-v44c4-lr15e7-step2: sft-lora 3 months ago
  • tokenizer_config.json
    4.67 kB
    v49b-deepseek-v48b0106-from-v44c4-lr15e7-step2: sft-lora 3 months ago
  • training_args.bin

    Detected Pickle imports (10)

    • "torch.device",
    • "transformers.training_args.OptimizerNames",
    • "transformers.trainer_utils.SchedulerType",
    • "transformers.trainer_utils.IntervalStrategy",
    • "transformers.trainer_utils.SaveStrategy",
    • "UnslothSFTTrainer.UnslothSFTConfig",
    • "accelerate.utils.dataclasses.DistributedType",
    • "transformers.trainer_utils.HubStrategy",
    • "transformers.trainer_pt_utils.AcceleratorConfig",
    • "accelerate.state.PartialState"

    How to fix it?

    5.78 kB
    xet
    v49b-deepseek-v48b0106-from-v44c4-lr15e7-step2: sft-lora 3 months ago