prithivMLmods/FaithEyes-8B-RL-GGUF

Same weights, converted (fewer layers) vs Jackwang111/FaithEyes-8B-RL. prithivMLmods/FaithEyes-8B-RL-GGUF matches part of Jackwang111/FaithEyes-8B-RL (399 of its 750 tensors; the rest of Jackwang111/FaithEyes-8B-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