prithivMLmods/Video-HopChain-8B-Standard-RL-GGUF

Same weights, converted (fewer layers) vs ngqtrung/Video-HopChain-8B-Standard-RL. prithivMLmods/Video-HopChain-8B-Standard-RL-GGUF matches part of ngqtrung/Video-HopChain-8B-Standard-RL (399 of its 750 tensors; the rest of ngqtrung/Video-HopChain-8B-Standard-RL has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → BF16/F32).

Tensors changed: MLP 0/108, Norms 0/145, Attention 0/144, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse