Upload Llama-PLLuM-8B-instruct-q8_0.gguf

Coverted model to gguf
python3 llama.cpp/convert_hf_to_gguf.py cyfra --outfile Llama-PLLuM-8B-instruct-q8_0.gguf --outtype q8_0
INFO:hf-to-gguf:Loading model: cyfra
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
INFO:hf-to-gguf:Exporting model...
INFO:hf-to-gguf:rope_freqs.weight, torch.float32 --> F32, shape = {64}
INFO:hf-to-gguf:gguf: loading model weight map from 'model.safetensors.index.json'
INFO:hf-to-gguf:gguf: loading model part 'model-00001-of-00004.safetensors'
INFO:hf-to-gguf:token_embd.weight, torch.bfloat16 --> Q8_0, shape = {4096, 128258}
INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.0.ffn_down.weight, torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.0.ffn_gate.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.0.ffn_up.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.0.ffn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.0.attn_k.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.0.attn_output.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.0.attn_q.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.0.attn_v.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.1.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.1.ffn_down.weight, torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.1.ffn_gate.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.1.ffn_up.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.1.ffn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.1.attn_k.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.1.attn_output.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.1.attn_q.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.1.attn_v.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.2.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.2.ffn_down.weight, torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.2.ffn_gate.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.2.ffn_up.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.2.ffn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.2.attn_k.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.2.attn_output.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.2.attn_q.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.2.attn_v.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.3.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.3.ffn_down.weight, torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.3.ffn_gate.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.3.ffn_up.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.3.ffn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.3.attn_k.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.3.attn_output.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.3.attn_q.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.3.attn_v.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.4.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.4.ffn_down.weight, torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.4.ffn_gate.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.4.ffn_up.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.4.ffn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.4.attn_k.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.4.attn_output.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.4.attn_q.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.4.attn_v.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.5.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.5.ffn_down.weight, torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.5.ffn_gate.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.5.ffn_up.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.5.ffn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.5.attn_k.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.5.attn_output.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.5.attn_q.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.5.attn_v.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.6.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.6.ffn_down.weight, torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.6.ffn_gate.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.6.ffn_up.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.6.ffn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.6.attn_k.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.6.attn_output.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.6.attn_q.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.6.attn_v.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.7.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.7.ffn_down.weight, torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.7.ffn_gate.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.7.ffn_up.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.7.ffn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.7.attn_k.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.7.attn_output.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.7.attn_q.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.7.attn_v.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.8.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.8.ffn_down.weight, torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.8.ffn_gate.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.8.ffn_up.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.8.ffn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.8.attn_k.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.8.attn_output.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.8.attn_q.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.8.attn_v.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:gguf: loading model part 'model-00002-of-00004.safetensors'
INFO:hf-to-gguf:blk.10.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.10.ffn_down.weight, torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.10.ffn_gate.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.10.ffn_up.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.10.ffn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.10.attn_k.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.10.attn_output.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.10.attn_q.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.10.attn_v.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.11.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.11.ffn_down.weight, torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.11.ffn_gate.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.11.ffn_up.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.11.ffn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.11.attn_k.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.11.attn_output.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.11.attn_q.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
INFO:hf-to-gguf:blk.11.attn_v.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.12.attn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.12.ffn_down.weight, torch.bfloat16 --> Q8_0, shape = {14336, 4096}
INFO:hf-to-gguf:blk.12.ffn_gate.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.12.ffn_up.weight, torch.bfloat16 --> Q8_0, shape = {4096, 14336}
INFO:hf-to-gguf:blk.12.ffn_norm.weight, torch.bfloat16 --> F32, shape = {4096}
INFO:hf-to-gguf:blk.12.attn_k.weight, torch.bfloat16 --> Q8_0, shape = {4096, 1024}
INFO:hf-to-gguf:blk.12.attn_output.weight, torch.bfloat16 --> Q8_0, shape = {4096, 4096}
IN

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Llama-PLLuM-8B-instruct-q8_0.gguf filter=lfs diff=lfs merge=lfs -text

Llama-PLLuM-8B-instruct-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637399d994dab3b31f7a91e82e4d149b68afcf5b2fbbc09dcb0c1fb4119e918e
+size 8540789248