vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-12 01:54:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Rewrite history to fix bad vulkan shader commits without increasing repo size

Browse source 
added dpe colab (+8 squashed commit)

Squashed commit:

[b8362da4] updated lite

[ed6c037d] move nsigma into the regular sampler stack

[ac5f61c6] relative filepath fixed

[05fe96ab] export template

[ed0a5a3e] nix_example.md: refactor (#1401)

* nix_example.md: add override example

* nix_example.md: drop graphics example, already basic nixos knowledge

* nix_example.md: format

* nix_example.md: Vulkan is disabled on macOS

Disabled in: 1ccd253acc

* nix_examples.md: nixpkgs.config.cuda{Arches -> Capabilities}

Fixes: https://github.com/LostRuins/koboldcpp/issues/1367

[675c62f7] AutoGuess: Phi 4 (mini) (#1402)

[4bf56982] phrasing

[b8c0df04] Add Rep Pen to Top N Sigma sampler chain (#1397)

- place after nsigma and before xtc (+3 squashed commit)

Squashed commit:

[87c52b97] disable VMM from HIP

[ee8906f3] edit description

[e85c0e69] Remove Unnecessary Rep Counting (#1394)

* stop counting reps

* fix range-based initializer

* strike that - reverse it
This commit is contained in:
Concedo 2025-03-05 00:02:20 +08:00
parent 50eae1ffeb
commit 6b7d2349a7
114 changed files with 6666 additions and 2642 deletions
Download patch file Download diff file Expand all files Collapse all files

17
src/llama-model.cpp
View file

@ -2297,13 +2297,16 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
} break;
case LLM_ARCH_PHI3:
{
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
output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), { n_embd }, 0);
output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), { n_embd, n_vocab }, 0);
output = create_tensor(tn(LLM_TENSOR_OUTPUT, "weight"), {n_embd, n_vocab}, TENSOR_NOT_REQUIRED);
// if output is NULL, init from the input tok embed
if (output == NULL) {
output = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, TENSOR_DUPLICATED);
}
for (int i = 0; i < n_layer; ++i) {
auto & layer = layers[i];
@ -2318,8 +2321,8 @@ bool llama_model::load_tensors(llama_model_loader & ml) {
layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", i), { n_ff, n_embd }, 0);
layer.ffn_up = create_tensor(tn(LLM_TENSOR_FFN_UP, "weight", i), { n_embd, 2 * n_ff }, 0);
layer.rope_long = create_tensor(tn(LLM_TENSOR_ROPE_FACTORS_LONG, "weight", i), { n_embd_head/2 }, TENSOR_NOT_REQUIRED | (i != 0 ? TENSOR_DUPLICATED : 0));
layer.rope_short = create_tensor(tn(LLM_TENSOR_ROPE_FACTORS_SHORT, "weight", i), { n_embd_head/2 }, TENSOR_NOT_REQUIRED | (i != 0 ? TENSOR_DUPLICATED : 0));
layer.rope_long = create_tensor(tn(LLM_TENSOR_ROPE_FACTORS_LONG, "weight", i), { n_rot/2 }, TENSOR_NOT_REQUIRED | (i != 0 ? TENSOR_DUPLICATED : 0));
layer.rope_short = create_tensor(tn(LLM_TENSOR_ROPE_FACTORS_SHORT, "weight", i), { n_rot/2 }, TENSOR_NOT_REQUIRED | (i != 0 ? TENSOR_DUPLICATED : 0));
}
} break;
case LLM_ARCH_PHIMOE:
@ -3937,6 +3940,10 @@ int32_t llama_model_n_head(const struct llama_model * model) {
return model->hparams.n_head();
}
int32_t llama_model_n_head_kv(const struct llama_model * model) {
return model->hparams.n_head_kv();
}
// deprecated
int32_t llama_n_ctx_train(const struct llama_model * model) {
return llama_model_n_ctx_train(model);