tiiuae/Falcon3-10B-Instruct
Full fine-tune vs tiiuae/Falcon3-10B-Base. Fine-tune: 100% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 81/81, MLP 120/120, Attention 160/160, lm_head 1/1
22 derivatives checked
- bartowski/Falcon3-10B-Instruct-GGUF: Same weights, converted
- mradermacher/Falcon3-10B-Instruct-i1-GGUF: Quantization
- tiiuae/Falcon3-10B-Instruct-GGUF: Same weights, converted
- tiiuae/Falcon3-10B-Instruct-1.58bit: Quantization
- mradermacher/Falcon3-10B-Instruct-GGUF: Same weights, converted
- second-state/Falcon3-10B-Instruct-GGUF: Same weights, converted
- MaziyarPanahi/Falcon3-10B-Instruct-GGUF: Same weights, converted
- gaianet/Falcon3-10B-Instruct-GGUF: Same weights, converted
- mlx-community/Falcon3-10B-Instruct-4bit: Quantization
- s3dev-ai/Falcon3-10B-Instruct-gguf: Same weights, converted
- lmstudio-community/Falcon3-10B-Instruct-GGUF: Quantization
- EasierAI/Falcon-3-10B: Quantization
- tiiuae/Falcon3-10B-Instruct-GPTQ-Int4: Quantization
- DevQuasar-6/tiiuae.Falcon3-10B-Instruct-GGUF: Quantization
- tiiuae/Falcon3-10B-Instruct-AWQ: Quantization
- smarttasks/Falcon3-10B-Instruct-GGUF: Quantization
- Danielbrdz/Barcenas-10b: LoRA-style
- tensopolis/falcon3-10b-tensopolis-v1: LoRA-style
- fluently-sets/FalconThink3-10B-IT: LoRA-style
- ehristoforu/BigFalcon3-36B: Partial fine-tune (fewer layers)
- ehristoforu/BigFalcon3-18B: Partial fine-tune (fewer layers)
- ehristoforu/BigFalcon3-from10B: Partial fine-tune (fewer layers)