Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • 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

jacob-ml
/
Jacob-2-E4B-prod

Text Generation
Safetensors
gemma4
fp8
vllm
lora-merged
conversational
compressed-tensors
Model card Files Files and versions
xet
Community
Jacob-2-E4B-prod
11.5 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 9 commits
mags0ft's picture
mags0ft
Update README.md
dd90758 verified about 1 month ago
  • .gitattributes
    1.66 kB
    Merge Jacob-2-E4B LoRA into gemma-4-E4B-it and quantize to FP8 (dynamic, compressed-tensors) about 1 month ago
  • README.md
    809 Bytes
    Update README.md about 1 month ago
  • chat_template.jinja
    17.5 kB
    Merge Jacob-2-E4B LoRA into gemma-4-E4B-it and quantize to FP8 (dynamic, compressed-tensors) about 1 month ago
  • config.json
    6.45 kB
    Merge Jacob-2-E4B LoRA into gemma-4-E4B-it and quantize to FP8 (dynamic, compressed-tensors) about 1 month ago
  • generation_config.json
    204 Bytes
    Merge Jacob-2-E4B LoRA into gemma-4-E4B-it and quantize to FP8 (dynamic, compressed-tensors) about 1 month ago
  • model.safetensors
    11.5 GB
    xet
    Merge Jacob-2-E4B LoRA into gemma-4-E4B-it and quantize to FP8 (dynamic, compressed-tensors) about 1 month ago
  • processor_config.json
    1.69 kB
    Merge Jacob-2-E4B LoRA into gemma-4-E4B-it and quantize to FP8 (dynamic, compressed-tensors) about 1 month ago
  • recipe.yaml
    215 Bytes
    Merge Jacob-2-E4B LoRA into gemma-4-E4B-it and quantize to FP8 (dynamic, compressed-tensors) about 1 month ago
  • tokenizer.json
    32.2 MB
    xet
    Merge Jacob-2-E4B LoRA into gemma-4-E4B-it and quantize to FP8 (dynamic, compressed-tensors) about 1 month ago
  • tokenizer_config.json
    2.74 kB
    Merge Jacob-2-E4B LoRA into gemma-4-E4B-it and quantize to FP8 (dynamic, compressed-tensors) about 1 month ago