mradermacher/Prog-3B-RL-lite-GGUF

Same weights, converted (fewer layers) vs Raymond-Qiancx/ProgressLM-3B-RL. mradermacher/Prog-3B-RL-lite-GGUF matches part of Raymond-Qiancx/ProgressLM-3B-RL (435 of its 825 tensors; the rest of Raymond-Qiancx/ProgressLM-3B-RL has no counterpart). On the shared part: Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: lm_head 0/1, Norms 0/73, MLP 0/108, Attention 0/252, Embeddings 0/1

On the Hub · Downloads on Model Pulse