Skip to content
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

Jump to bottom

MPT : support GQA for replit-code-v1.5 #3627

Merged
merged 1 commit into from
Oct 15, 2023
Merged

MPT : support GQA for replit-code-v1.5 #3627

Show file tree
Hide file tree
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
2 changes: 2 additions & 0 deletions convert-mpt-hf-to-gguf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,6 +98,8 @@ def parse_args() -> argparse.Namespace:
gguf_writer.add_block_count(block_count)
gguf_writer.add_feed_forward_length(4 * hparams["d_model"])
gguf_writer.add_head_count(hparams["n_heads"])
if kv_n_heads := hparams["attn_config"].get("kv_n_heads"):
gguf_writer.add_head_count_kv(kv_n_heads)
gguf_writer.add_layer_norm_eps(1e-05)
if hparams["attn_config"]["clip_qkv"] is not None:
gguf_writer.add_clamp_kqv(hparams["attn_config"]["clip_qkv"])
Expand Down
6 changes: 3 additions & 3 deletions llama.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2839,8 +2839,8 @@ static void llm_load_tensors(
auto & layer = model.layers[i];

layer.attn_norm = ml.create_tensor(ctx, tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, backend);
layer.wqkv = ml.create_tensor(ctx, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, 3*n_embd}, backend_split);
layer.wo = ml.create_tensor(ctx, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}, backend_split);
layer.wqkv = ml.create_tensor(ctx, tn(LLM_TENSOR_ATTN_QKV, "weight", i), {n_embd, n_embd + 2*n_embd_gqa}, backend_split);
layer.wo = ml.create_tensor(ctx, tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_embd, n_embd}, backend_split);

layer.ffn_norm = ml.create_tensor(ctx, tn(LLM_TENSOR_FFN_NORM, "weight", i), {n_embd}, backend);

Expand Down Expand Up @@ -5368,7 +5368,7 @@ static struct ggml_cgraph * llm_build_mpt(
const int64_t n_layer = hparams.n_layer;
const int64_t n_ctx = cparams.n_ctx;
const int64_t n_head = hparams.n_head;
const int64_t n_head_kv = hparams.n_head_kv; // == n_head for MPT, as there's no MQA/GQA
const int64_t n_head_kv = hparams.n_head_kv;
const int64_t n_embd_head = hparams.n_embd_head();
const int64_t n_embd_gqa = hparams.n_embd_gqa();

Expand Down
Loading