Fintacorp55/football-llm-q4

Add LoRA adapter weights

Add Q3_K_M to available models table, fix filenames

Update model card

Add qwen2-7b.Q4_K_M.gguf — merged standalone GGUF (LM Studio ready, eos_token_id=151645)

Add qwen2-7b.Q3_K_M.gguf — merged standalone GGUF (LM Studio ready, eos_token_id=151645)

Add qwen2-7b.F16.gguf — merged standalone GGUF (LM Studio ready, eos_token_id=151645)

Remove adapter_model.safetensors — repo now contains standalone GGUFs

Remove adapter_config.json — repo now contains standalone GGUFs

Remove old broken GGUF: football-llm-q4_K_M.gguf

Remove old broken GGUF: football-llm-q3_K_M.gguf

Remove old broken GGUF: football-llm-f16.gguf

Add Q3_K_M GGUF for mobile (iPhone 13 compatible)

Remove old broken GGUF: model-q4_k_m.gguf

Remove old broken GGUF: football-llm-q4-f16.gguf

Add fixed f16 GGUF (eos_token_id=151645)

Fix eos_token, pad_token, embed chat_template

Fix eos_token_id: 151643->151645 (<|im_end|>), rebuild GGUF Q4_K_M

Add football-llm-q4-f16.gguf

Add football-llm-q4_K_M.gguf

Upload DPO v2 LoRA adapter (rank 32, SFT+DPO trained)

Add model card with YAML metadata

Upload model-q4_k_m.gguf with huggingface_hub

Upload README.md with huggingface_hub

initial commit