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
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

TonyStarkD99
/
PerspectrumInstruct-Baseline-R_32-Alpha_64_Batch_4-Step_50-FT-Unsloth_Mistral7B

PEFT
Safetensors
adapter
instruct-tuning
Mistral7B
Batch_Size-4
Steps-50
trl
sft
unsloth
Generated from Trainer
Model card Files Files and versions
xet
Community

Instructions to use TonyStarkD99/PerspectrumInstruct-Baseline-R_32-Alpha_64_Batch_4-Step_50-FT-Unsloth_Mistral7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • PEFT

    How to use TonyStarkD99/PerspectrumInstruct-Baseline-R_32-Alpha_64_Batch_4-Step_50-FT-Unsloth_Mistral7B with PEFT:

    from peft import PeftModel
    from transformers import AutoModelForCausalLM
    
    base_model = AutoModelForCausalLM.from_pretrained("unsloth/mistral-7b-instruct-v0.2-bnb-4bit")
    model = PeftModel.from_pretrained(base_model, "TonyStarkD99/PerspectrumInstruct-Baseline-R_32-Alpha_64_Batch_4-Step_50-FT-Unsloth_Mistral7B")
  • Notebooks
  • Google Colab
  • Kaggle
  • Local Apps Settings
  • Unsloth Studio

    How to use TonyStarkD99/PerspectrumInstruct-Baseline-R_32-Alpha_64_Batch_4-Step_50-FT-Unsloth_Mistral7B with Unsloth Studio:

    Install Unsloth Studio (macOS, Linux, WSL)
    curl -fsSL https://unsloth.ai/install.sh | sh
    # Run unsloth studio
    unsloth studio -H 0.0.0.0 -p 8888
    # Then open http://localhost:8888 in your browser
    # Search for TonyStarkD99/PerspectrumInstruct-Baseline-R_32-Alpha_64_Batch_4-Step_50-FT-Unsloth_Mistral7B to start chatting
    Install Unsloth Studio (Windows)
    irm https://unsloth.ai/install.ps1 | iex
    # Run unsloth studio
    unsloth studio -H 0.0.0.0 -p 8888
    # Then open http://localhost:8888 in your browser
    # Search for TonyStarkD99/PerspectrumInstruct-Baseline-R_32-Alpha_64_Batch_4-Step_50-FT-Unsloth_Mistral7B to start chatting
    Using HuggingFace Spaces for Unsloth
    # No setup required
    # Open https://huggingface.co/spaces/unsloth/studio in your browser
    # Search for TonyStarkD99/PerspectrumInstruct-Baseline-R_32-Alpha_64_Batch_4-Step_50-FT-Unsloth_Mistral7B to start chatting
    Load model with FastModel
    pip install unsloth
    from unsloth import FastModel
    model, tokenizer = FastModel.from_pretrained(
        model_name="TonyStarkD99/PerspectrumInstruct-Baseline-R_32-Alpha_64_Batch_4-Step_50-FT-Unsloth_Mistral7B",
        max_seq_length=2048,
    )
PerspectrumInstruct-Baseline-R_32-Alpha_64_Batch_4-Step_50-FT-Unsloth_Mistral7B
Ctrl+K
Ctrl+K
  • 1 contributor
History: 2 commits
TonyStarkD99's picture
TonyStarkD99
Baseline Training completed BatchSize 4 steps 50
e580463 verified almost 2 years ago
  • .gitattributes
    1.52 kB
    initial commit almost 2 years ago
  • README.md
    1.76 kB
    Baseline Training completed BatchSize 4 steps 50 almost 2 years ago
  • adapter_config.json
    741 Bytes
    Baseline Training completed BatchSize 4 steps 50 almost 2 years ago
  • adapter_model.safetensors
    336 MB
    xet
    Baseline Training completed BatchSize 4 steps 50 almost 2 years ago
  • special_tokens_map.json
    552 Bytes
    Baseline Training completed BatchSize 4 steps 50 almost 2 years ago
  • tokenizer.json
    1.8 MB
    Baseline Training completed BatchSize 4 steps 50 almost 2 years ago
  • tokenizer.model
    493 kB
    xet
    Baseline Training completed BatchSize 4 steps 50 almost 2 years ago
  • tokenizer_config.json
    2.11 kB
    Baseline Training completed BatchSize 4 steps 50 almost 2 years ago
  • training_args.bin

    Detected Pickle imports (9)

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

    How to fix it?

    5.43 kB
    xet
    Baseline Training completed BatchSize 4 steps 50 almost 2 years ago