llama : add PLM GGUF Conversion & Inference Support (#12457)
* add edgellm model arch[conversation feature doesn't work] * remove output.weight layer for edgellm arch * [Model] update the name of the model * update the name of model arch in convert gguf * [Model] Refarctor the model arch into llama-model * [Bug] Fix the bug in create attn kv * [Code] Fix editorconfig erros * [Code] Remove Trailing whitespace * [Code] Remove Trailing whitespace * [Code] Change the order of model arch in list * [Code] Fix flake8 Lint errors * Remove trailing white space * [Code] Remove call in model arch
This commit is contained in:
parent
953c2a62cf
commit
f125b8dccf
6 changed files with 274 additions and 0 deletions
|
@ -65,6 +65,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
|
|||
{ LLM_ARCH_GRANITE_MOE, "granitemoe" },
|
||||
{ LLM_ARCH_CHAMELEON, "chameleon" },
|
||||
{ LLM_ARCH_WAVTOKENIZER_DEC, "wavtokenizer-dec" },
|
||||
{ LLM_ARCH_PLM, "plm" },
|
||||
{ LLM_ARCH_UNKNOWN, "(unknown)" },
|
||||
};
|
||||
|
||||
|
@ -1043,6 +1044,22 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
|
|||
{ LLM_TENSOR_FFN_EXP_PROBS_B, "blk.%d.exp_probs_b" },
|
||||
},
|
||||
},
|
||||
{
|
||||
LLM_ARCH_PLM,
|
||||
{
|
||||
{ LLM_TENSOR_TOKEN_EMBD, "token_embd" },
|
||||
{ LLM_TENSOR_OUTPUT_NORM, "output_norm" },
|
||||
{ LLM_TENSOR_ATTN_NORM, "blk.%d.attn_norm" },
|
||||
{ LLM_TENSOR_ATTN_Q, "blk.%d.attn_q" },
|
||||
{ LLM_TENSOR_ATTN_KV_A_MQA, "blk.%d.attn_kv_a_mqa" },
|
||||
{ LLM_TENSOR_ATTN_KV_A_NORM, "blk.%d.attn_kv_a_norm" },
|
||||
{ LLM_TENSOR_ATTN_KV_B, "blk.%d.attn_kv_b" },
|
||||
{ LLM_TENSOR_ATTN_OUT, "blk.%d.attn_output" },
|
||||
{ LLM_TENSOR_FFN_NORM, "blk.%d.ffn_norm" },
|
||||
{ LLM_TENSOR_FFN_DOWN, "blk.%d.ffn_down" },
|
||||
{ LLM_TENSOR_FFN_UP, "blk.%d.ffn_up" },
|
||||
},
|
||||
},
|
||||
{
|
||||
LLM_ARCH_CHATGLM,
|
||||
{
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue