Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B-MTP-GGUF
Update coding distillation roadmap for DeepSeek 0731 and 0813
Update README.md
Update README.md
Update dataset metadata reference to 200K
Add training dataset metadata references
Correct GSM8K score and add 4B comparison
Add Game Showcase (Star Skip by Kyle Hessling) to model card
Update model card with GSPO training path and RL tag
Update GGUF vision metadata for LM Studio
Add F32 vision projector for automatic multimodal discovery
Upload DeepSeek-V4-Pro-Qwen3.5-9B-MTP-BF16.gguf with huggingface_hub
Upload DeepSeek-V4-Pro-Qwen3.5-9B-MTP-Q8_0.gguf with huggingface_hub
Upload DeepSeek-V4-Pro-Qwen3.5-9B-MTP-Q6_K.gguf with huggingface_hub
Upload DeepSeek-V4-Pro-Qwen3.5-9B-MTP-Q5_K_M.gguf with huggingface_hub
Upload DeepSeek-V4-Pro-Qwen3.5-9B-MTP-Q5_K_S.gguf with huggingface_hub
Upload DeepSeek-V4-Pro-Qwen3.5-9B-MTP-Q4_K_M.gguf with huggingface_hub
Upload DeepSeek-V4-Pro-Qwen3.5-9B-MTP-Q4_K_S.gguf with huggingface_hub
Upload DeepSeek-V4-Pro-Qwen3.5-9B-MTP-IQ4_XS.gguf with huggingface_hub
Upload DeepSeek-V4-Pro-Qwen3.5-9B-MTP-Q3_K_L.gguf with huggingface_hub
Upload DeepSeek-V4-Pro-Qwen3.5-9B-MTP-Q3_K_M.gguf with huggingface_hub
Upload DeepSeek-V4-Pro-Qwen3.5-9B-MTP-Q3_K_S.gguf with huggingface_hub
Upload DeepSeek-V4-Pro-Qwen3.5-9B-MTP-Q2_K.gguf with huggingface_hub
Upload full model card
Upload README.md with huggingface_hub
Create README.md
initial commit