Skip to content

llama : support OLMo-2-0325-32B (#12376) #12400

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Mar 16, 2025
Merged

llama : support OLMo-2-0325-32B (#12376) #12400

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion src/llama-model.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1005,6 +1005,7 @@ void llama_model::load_hparams(llama_model_loader & ml) {
case 16: type = LLM_TYPE_1B; break;
case 32: type = LLM_TYPE_7B; break;
case 40: type = LLM_TYPE_13B; break;
case 64: type = LLM_TYPE_32B; break;
default: type = LLM_TYPE_UNKNOWN;
}
} break;
Expand Down Expand Up @@ -2726,6 +2727,8 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
} break;
case LLM_ARCH_OLMO2:
{
const int64_t n_embd_head = n_embd / n_head;

tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);

// output
Expand All @@ -2740,7 +2743,7 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
layer.wv = create_tensor(tn(LLM_TENSOR_ATTN_V, "weight", i), {n_embd, n_embd_gqa}, 0);
layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}, 0);
layer.attn_q_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {n_embd}, 0);
layer.attn_k_norm = create_tensor(tn(LLM_TENSOR_ATTN_K_NORM, "weight", i), {n_embd}, 0);
layer.attn_k_norm = create_tensor(tn(LLM_TENSOR_ATTN_K_NORM, "weight", i), {n_head_kv * n_embd_head}, 0);
layer.attn_post_norm = create_tensor(tn(LLM_TENSOR_ATTN_POST_NORM, "weight", i), {n_embd}, 0);

layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", i), {n_embd, n_ff}, 0);
Expand Down
Loading