mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2025-09-11 09:34:37 +00:00
model : add support for Falcon-H1 family (#14534)
* v1 * push more fixes * another fix * fix * more fixes * minor fix * more cleaning on python code * python fixes * changed precision for multipliers float 32->64 * fixes * another fix * fix * pre-norm -> norm * fix * Revert "fix" This reverts commit 243e4d1a50bd73467d99f6b289b9a1826f83b94b. * fix * small fix ffn_norm * try * mix instead of max * fix vocab size * conflict solve * fixed multipliers * falcon-h1 specefic vocab resolved * read arch from gguf.MODEL_ARCH * mamba_d_ssm added to d_inner find_hparam * remove unused functions from gguf_writer.py * override modify_tensors instead of get_tensors * fix conversion and d_inner * added some cb functions for debugging puposes * inp_out_ids moved outside of layers loop * mup_vec create as float64 * fix rope_theta * injected mup * clean ups * rm extra space * rm unused MAMBA_CHUNK_SIZE * rm unused key * add bos False * changed ROPE_TYPE * cleaning debugging stuff * cleaning debug quant * fix comment * some cleanups * some cleanups * Update src/llama-model-loader.cpp * more cleanups * moe cleanuips * d_ssm -> d_inner; * cleaning unused hparams * cleanup * more cleanups * more cleanups on python conversion; * minor cleanups * Apply suggestions from code review Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * remove todo * added falcon-h1 * tensor not required * clean * remove unneeded attributes * more cleanups and fixed conversion * remove final_norm * flake8 fixes * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * flake8 fixes * Update src/llama-hparams.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-arch.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update convert_hf_to_gguf.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * added hashes * Update src/llama-arch.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * Update src/llama-vocab.cpp Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * update the update file * Revert "update the update file" This reverts commit 082ab4ad2a3927384d878666a5f8cae4eb15f577. * fix: address suggestions * fix: update convert_hf_to_gguf.py * Update gguf-py/gguf/constants.py Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update src/llama-model-loader.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * d_inner fixed * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * reshaping ssm_norm for 34B * removing generate_mup * remove duplicates metadata keys * rm comment * final comment * fix unused args * fix constants * fix bad merge * Update src/llama-model.cpp Co-authored-by: compilade <git@compilade.net> * falcon-h1: remove unused ssm_in_b and bad merge * Update src/llama-model.cpp Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * falcon-h1: fix last comment * Update convert_hf_to_gguf.py Co-authored-by: compilade <git@compilade.net> * falcon-h1: revert add_add_bos(False) * falcon-h1: fix tied weights * falcon-h1: remove whitespace * falcon-h1: fix wrong size param * falcon-h1: fix whitespace issues --------- Co-authored-by: younesbelkada <younes.belkada@tii.ae> Co-authored-by: Younes B <49240599+younesbelkada@users.noreply.github.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> Co-authored-by: compilade <git@compilade.net>
This commit is contained in:
ibrahim khadraoui
GitHub
parent
20b7bf8a32
commit
04655063c4
8 changed files with 585 additions and 9 deletions
|
|
@ -46,6 +46,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
|
|||
{ LLM_ARCH_STARCODER2, "starcoder2" },
|
||||
{ LLM_ARCH_MAMBA, "mamba" },
|
||||
{ LLM_ARCH_MAMBA2, "mamba2" },
|
||||
{ LLM_ARCH_FALCON_H1, "falcon-h1" },
|
||||
{ LLM_ARCH_XVERSE, "xverse" },
|
||||
{ LLM_ARCH_COMMAND_R, "command-r" },
|
||||
{ LLM_ARCH_COHERE2, "cohere2" },
|
||||
|
|
@ -1024,6 +1025,30 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
|
|||
{ LLM_TENSOR_SSM_OUT, "blk.%d.ssm_out" },
|
||||
},
|
||||
},
|
||||
{
|
||||
LLM_ARCH_FALCON_H1,
|
||||
{
|
||||
{ LLM_TENSOR_TOKEN_EMBD, "token_embd" },
|
||||
{ LLM_TENSOR_OUTPUT, "output" },
|
||||
{ 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_K, "blk.%d.attn_k" },
|
||||
{ LLM_TENSOR_ATTN_V, "blk.%d.attn_v" },
|
||||
{ LLM_TENSOR_ATTN_OUT, "blk.%d.attn_output" },
|
||||
{ LLM_TENSOR_SSM_IN, "blk.%d.ssm_in" },
|
||||
{ LLM_TENSOR_SSM_CONV1D, "blk.%d.ssm_conv1d" },
|
||||
{ LLM_TENSOR_SSM_DT, "blk.%d.ssm_dt" },
|
||||
{ LLM_TENSOR_SSM_A, "blk.%d.ssm_a" },
|
||||
{ LLM_TENSOR_SSM_D, "blk.%d.ssm_d" },
|
||||
{ LLM_TENSOR_SSM_NORM, "blk.%d.ssm_norm" },
|
||||
{ LLM_TENSOR_SSM_OUT, "blk.%d.ssm_out" },
|
||||
{ LLM_TENSOR_FFN_NORM, "blk.%d.ffn_norm" },
|
||||
{ LLM_TENSOR_FFN_GATE, "blk.%d.ffn_gate" },
|
||||
{ LLM_TENSOR_FFN_DOWN, "blk.%d.ffn_down" },
|
||||
{ LLM_TENSOR_FFN_UP, "blk.%d.ffn_up" },
|
||||
},
|
||||
},
|
||||
{
|
||||
LLM_ARCH_XVERSE,
|
||||
{
|
||||
|
|
@ -1967,9 +1992,10 @@ bool llm_arch_is_recurrent(const llm_arch & arch) {
|
|||
}
|
||||
|
||||
bool llm_arch_is_hybrid(const llm_arch & arch) {
|
||||
// TODO: There are currently no hybrid models! Once there are, this will be
|
||||
// the place to identify them
|
||||
// List all mamba-attention hybrid models here
|
||||
switch (arch) {
|
||||
case LLM_ARCH_FALCON_H1:
|
||||
return true;
|
||||
default:
|
||||
return false;
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue