Qwen/Qwen2-0.5B-Instruct
Full fine-tune vs Qwen/Qwen2-0.5B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.
Tensors changed: Embeddings 1/1, Norms 29/49, MLP 72/72, Attention 168/168
37 derivatives checked
- Qwen/Qwen2-0.5B-Instruct-GGUF: Same weights, converted
- legraphista/Qwen2-0.5B-Instruct-IMat-GGUF: Same weights, converted
- mradermacher/Qwen2-0.5B-Instruct-GGUF: Same weights, converted
- QuantFactory/Qwen2-0.5B-Instruct-GGUF: Quantization
- featherless-ai-quants/Qwen-Qwen2-0.5B-Instruct-GGUF: Quantization
- second-state/Qwen2-0.5B-Instruct-GGUF: Same weights, converted
- lmstudio-community/Qwen2-500M-Instruct-GGUF: Quantization
- arzaan789/qwen2-0.5b-uncensored: Full fine-tune
- Zynerji/Ektome-Qwen2-0.5Bi-PristinelyUncensored: Abliterated
- Qwen/Qwen2-0.5B-Instruct-GPTQ-Int4: Quantization
- gaianet/Qwen2-0.5B-Instruct-GGUF: Same weights, converted
- Qwen/Qwen2-0.5B-Instruct-AWQ: Quantization
- Felladrin/gguf-Qwen2-0.5B-Instruct: Same weights, converted
- CHE-72-ZLab/Alibaba-Qwen2-0_5B-Instruct-GGUF: Quantization
- afrideva/Qwen2-0.5B-Instruct-GGUF: Same weights, converted
- Felladrin/gguf-sharded-Qwen2-0.5B-Instruct: Quantization
- Qwen/Qwen2-0.5B-Instruct-GPTQ-Int8: Quantization
- cattoroboto/Qwen2-0.5B-Instruct-GGUF-Q2_K: Quantization
- liodon-ai/Qwen2-0.5B-Instruct-imatrix-GGUF: Quantization
- trl-lib/Qwen2-0.5B-Reward: Full fine-tune
- Bruno0208/Qwen2.5-0.5B-Instruct-mate-q4_k_m.gguf: LoRA-style
- dharun2049/kaveri-stgrpo-0.5b: LoRA-style
- DireDreadlord/Dragon-1.5-0.5B: Full fine-tune
- trl-lib/Qwen2-0.5B-XPO: Full fine-tune
- trl-lib/Qwen2-0.5B-OnlineDPO: Full fine-tune
- iben/Abuja-01: Full fine-tune
- DireDreadlord/Dragon-1-0.5B: Full fine-tune
- stupidity-ai/Qwen_WhatTheFuck: Full fine-tune
- ericlewis/Qwen2-0.5B-Instruct-xLAM-0.1: LoRA-style
- trl-lib/Qwen2-0.5B-DPO: Full fine-tune
17 other repos hold byte-for-byte identical weight files.