Hugging Face's logo

asiansoul
/
Joah-Llama-3-MAAL-MLP-KoEn-8B-Reborn-GGUF

GGUF
Inference Endpoints
conversational
Model card Files Community
1
asiansoul commited on
Commit
e30fe5f
·
verified ·
1 Parent(s): eeeaccf

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -24,7 +24,7 @@ reference_model_name = "MLP-KTLim/llama-3-Korean-Bllossom-8B"
24
  base_model_name = "NousResearch/Meta-Llama-3-8B-Instruct"
25
  target_model_name = "maum-ai/Llama-3-MAAL-8B-Instruct-v0.1"
26
 
27
- [interpolation mismatch]
28
  Interpolating tensor 'model.embed_tokens.weight' to match the shape: torch.Size([145088, 4096]) vs torch.Size([128256, 4096])
29
  Interpolating tensor 'lm_head.weight' to match the shape: torch.Size([145088, 4096]) vs torch.Size([128256, 4096])
30
  Interpolating tensor 'model.embed_tokens.weight' to match the shape: torch.Size([128256, 4096]) vs torch.Size([128257, 4096])
 
24
  base_model_name = "NousResearch/Meta-Llama-3-8B-Instruct"
25
  target_model_name = "maum-ai/Llama-3-MAAL-8B-Instruct-v0.1"
26
 
27
+ [interpolating mismatch part vocab]
28
  Interpolating tensor 'model.embed_tokens.weight' to match the shape: torch.Size([145088, 4096]) vs torch.Size([128256, 4096])
29
  Interpolating tensor 'lm_head.weight' to match the shape: torch.Size([145088, 4096]) vs torch.Size([128256, 4096])
30
  Interpolating tensor 'model.embed_tokens.weight' to match the shape: torch.Size([128256, 4096]) vs torch.Size([128257, 4096])