vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix model loading

Browse source
This commit is contained in:
Layl Bongers 2024-04-15 12:05:47 +02:00 • committed by Molly Sophia
parent 7cac72a80b
commit e92c74f4a1
1 changed files with 11 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

11
src/llama.cpp
View file

@ -1345,6 +1345,7 @@ static const std::map<llm_arch, std::map<llm_tensor, std::string>> LLM_TENSOR_NA
LLM_ARCH_RWKV, LLM_ARCH_RWKV,
{ {
{ LLM_TENSOR_TOKEN_EMBD, "token_embd" }, { LLM_TENSOR_TOKEN_EMBD, "token_embd" },
{ LLM_TENSOR_ATTN_NORM, "blk.%d.attn_norm" },
}, },
}, },
{ {
@ -8226,6 +8227,16 @@ static bool llm_load_tensors(
case LLM_ARCH_RWKV: case LLM_ARCH_RWKV:
{ {
model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}); model.tok_embd = ml.create_tensor(ctx_input, tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab});
for (int i = 0; i < n_layer; ++i) {
ggml_context * ctx_layer = ctx_for_layer(i);
auto & layer = model.layers[i];
layer.attn_norm = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd});
layer.attn_norm_b = ml.create_tensor(ctx_layer, tn(LLM_TENSOR_ATTN_NORM, "bias", i), {n_embd});
}
} }
default: default:
throw std::runtime_error("unknown architecture"); throw std::runtime_error("unknown architecture");