Qwen/Qwen2.5-Coder-14B-Instruct
Full fine-tune vs Qwen/Qwen2.5-Coder-14B. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 336/336, lm_head 1/1
101 derivatives checked
- Qwen/Qwen2.5-Coder-14B-Instruct-AWQ: Quantization
- Qwen/Qwen2.5-Coder-14B-Instruct-GGUF: Partial fine-tune
- lmstudio-community/Qwen2.5-Coder-14B-Instruct-MLX-4bit: Quantization
- lmstudio-community/Qwen2.5-Coder-14B-Instruct-MLX-8bit: Quantization
- lmstudio-community/Qwen2.5-Coder-14B-Instruct-GGUF: Quantization
- bartowski/Qwen2.5-Coder-14B-Instruct-GGUF: Same weights, converted
- unsloth/Qwen2.5-Coder-14B-Instruct-bnb-4bit: Quantization
- Qwen/Qwen2.5-Coder-14B-Instruct-GPTQ-Int4: Quantization
- unsloth/Qwen2.5-Coder-14B-Instruct-128K-GGUF: Same weights, converted
- Goekdeniz-Guelmez/Josiefied-Qwen2.5-Coder-14B-Instruct-abliterated-v1: Abliterated
- unsloth/Qwen2.5-Coder-14B-Instruct-GGUF: Same weights, converted
- mlx-community/Qwen2.5-Coder-14B-Instruct-4bit: Quantization
- Mungert/Strand-Rust-Coder-14B-v1-GGUF: LoRA-style
- BlossomsAI/Qwen2.5-Coder-14B-Instruct-Uncensored-GGUF: Quantization
- mlx-community/Qwen2.5-Coder-14B-Instruct-8bit: Quantization
- gaianet/Qwen2.5-Coder-14B-Instruct-GGUF: Same weights, converted
- mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator: Adapter
- ApolloRaines/Qwen2.5-Coder-14B-Instruct-Jbliterated: Full fine-tune
- Mungert/NextCoder-14B-GGUF: Full fine-tune
- zipaltrivedi/dotnet-coder-14b: LoRA-style
- itlwas/Qwen2.5-Coder-14B-Instruct-Q4_K_M-GGUF: Quantization
- unsloth/Qwen2.5-Coder-14B-Instruct: Identical copy
- EasierAI/Qwen-2.5-Coder-14B: Full fine-tune
- sigmanih/Qwen-Qwen2.5-Coder-14B-Instruct-GGUF-Q4_K_M: Quantization
- featherless-ai-quants/Qwen-Qwen2.5-Coder-14B-Instruct-GGUF: Quantization
- evansanih/Qwen2.5-Coder-14B-n8n-Workflow-Generator: Adapter
- dawsaryahmad-jpg/Qwen2.5-Coder-14B-n8n-Workflow-Generator: Adapter
- ggml-org/Qwen2.5-Coder-14B-Instruct-Q8_0-GGUF: Quantization
- SSDD145/Qwen2.5-Coder-14B-Instruct-Uncensored-Patched: Full fine-tune
- 3MPER0RR/Qwen2.5-Coder-14B-Instruct-3MPER0RR-abliterated: Abliterated
6 other repos hold byte-for-byte identical weight files.