bigdl-core-cpp 2.6.0b20241204__py3-none-win_amd64.whl → 2.6.0b20241211__py3-none-win_amd64.whl

bigdl/cpp/convert_hf_to_gguf_update.py

@@ -31,6 +31,7 @@ import re
 import requests
 import sys
 import json
+import shutil
 
 from hashlib import sha256
 from enum import IntEnum, auto
@@ -80,6 +81,7 @@ models = [
     {"name": "qwen2",          "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/Qwen/Qwen1.5-7B", },
     {"name": "olmo",           "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/allenai/OLMo-1.7-7B-hf", },
     {"name": "dbrx",           "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/databricks/dbrx-base", },
+    {"name": "jina-v1-en",     "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-reranker-v1-tiny-en", },
     {"name": "jina-v2-en",     "tokt": TOKENIZER_TYPE.WPM, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-en", }, # WPM!
     {"name": "jina-v2-es",     "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-es", },
     {"name": "jina-v2-de",     "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/jinaai/jina-embeddings-v2-base-de", },
@@ -97,6 +99,8 @@ models = [
     {'name': "bloom",          "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/bigscience/bloom", },
     {'name': "gpt3-finnish",   "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/TurkuNLP/gpt3-finnish-small", },
     {"name": "exaone",         "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct", },
+    {"name": "phi-2",          "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/microsoft/phi-2", },
+    {"name": "chameleon",      "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/facebook/chameleon-7b", },
 ]
 
 
@@ -125,12 +129,27 @@ def download_model(model):
     if tokt == TOKENIZER_TYPE.UGM:
         files.append("spiece.model")
 
-    for file in files:
-        save_path = f"models/tokenizers/{name}/{file}"
-        if os.path.isfile(save_path):
-            logger.info(f"{name}: File {save_path} already exists - skipping")
-            continue
-        download_file_with_auth(f"{repo}/resolve/main/{file}", token, save_path)
+    if os.path.isdir(repo):
+        # If repo is a path on the file system, copy the directory
+        for file in files:
+            src_path = os.path.join(repo, file)
+            dst_path = f"models/tokenizers/{name}/{file}"
+            if os.path.isfile(dst_path):
+                logger.info(f"{name}: File {dst_path} already exists - skipping")
+                continue
+            if os.path.isfile(src_path):
+                shutil.copy2(src_path, dst_path)
+                logger.info(f"{name}: Copied {src_path} to {dst_path}")
+            else:
+                logger.warning(f"{name}: Source file {src_path} does not exist")
+    else:
+        # If repo is a URL, download the files
+        for file in files:
+            save_path = f"models/tokenizers/{name}/{file}"
+            if os.path.isfile(save_path):
+                logger.info(f"{name}: File {save_path} already exists - skipping")
+                continue
+            download_file_with_auth(f"{repo}/resolve/main/{file}", token, save_path)
 
 
 for model in models:

bigdl/cpp/convert_llama_ggml_to_gguf.py

@@ -294,11 +294,7 @@ class GGMLToGGUF:
         if self.vocab_override is not None:
             vo = self.vocab_override
             logger.info('* Adding vocab item(s)')
-<<<<<<< HEAD:convert-llama-ggml-to-gguf.py
-            for (idx, (vbytes, score, ttype)) in enumerate(vo.all_tokens()):
-=======
             for (_, (vbytes, score, ttype)) in enumerate(vo.all_tokens()):
->>>>>>> 1731d42:convert_llama_ggml_to_gguf.py
                 tokens.append(vbytes)
                 scores.append(score)
                 toktypes.append(ttype)

bigdl/cpp/convert_lora_to_gguf.py

@@ -331,6 +331,10 @@ if __name__ == '__main__':
                 self.gguf_writer.add_float32(gguf.Keys.Adapter.LORA_ALPHA, self.lora_alpha)
                 super().set_gguf_parameters()
 
+            def generate_extra_tensors(self) -> Iterable[tuple[str, Tensor]]:
+                # Never add extra tensors (e.g. rope_freqs) for LoRA adapters
+                return ()
+
             def get_tensors(self) -> Iterator[tuple[str, Tensor]]:
                 tensor_map: dict[str, PartialLoraTensor] = {}
 
@@ -363,7 +367,13 @@ if __name__ == '__main__':
                     yield (name, cast(torch.Tensor, LoraTorchTensor(tensor.A, tensor.B)))
 
             def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
-                dest = super().modify_tensors(data_torch, name, bid)
+                dest = list(super().modify_tensors(data_torch, name, bid))
+                # some archs may have the same tensor for lm_head and output (tie word embeddings)
+                # in this case, adapters targeting lm_head will fail when using llama-export-lora
+                # therefore, we ignore them for now
+                # see: https://github.com/ggerganov/llama.cpp/issues/9065
+                if name == "lm_head.weight" and len(dest) == 0:
+                    raise ValueError("lm_head is present in adapter, but is ignored in base model")
                 for dest_name, dest_data in dest:
                     assert isinstance(dest_data, LoraTorchTensor)
                     lora_a, lora_b = dest_data.get_lora_A_B()

bigdl/cpp/gguf-py/gguf/constants.py

@@ -94,6 +94,12 @@ class Keys:
         DECODER_START_TOKEN_ID            = "{arch}.decoder_start_token_id"
         ATTN_LOGIT_SOFTCAPPING            = "{arch}.attn_logit_softcapping"
         FINAL_LOGIT_SOFTCAPPING           = "{arch}.final_logit_softcapping"
+        SWIN_NORM                         = "{arch}.swin_norm"
+        RESCALE_EVERY_N_LAYERS            = "{arch}.rescale_every_n_layers"
+        TIME_MIX_EXTRA_DIM                = "{arch}.time_mix_extra_dim"
+        TIME_DECAY_EXTRA_DIM              = "{arch}.time_decay_extra_dim"
+        RESIDUAL_SCALE                    = "{arch}.residual_scale"
+        EMBEDDING_SCALE                   = "{arch}.embedding_scale"
 
     class Attention:
         HEAD_COUNT        = "{arch}.attention.head_count"
@@ -109,6 +115,7 @@ class Keys:
         KV_LORA_RANK      = "{arch}.attention.kv_lora_rank"
         REL_BUCKETS_COUNT = "{arch}.attention.relative_buckets_count"
         SLIDING_WINDOW    = "{arch}.attention.sliding_window"
+        SCALE             = "{arch}.attention.scale"
 
     class Rope:
         DIMENSION_COUNT         = "{arch}.rope.dimension_count"
@@ -132,6 +139,9 @@ class Keys:
         TIME_STEP_RANK = "{arch}.ssm.time_step_rank"
         DT_B_C_RMS     = "{arch}.ssm.dt_b_c_rms"
 
+    class WKV:
+        HEAD_SIZE = "{arch}.wkv.head_size"
+
     class Tokenizer:
         MODEL                = "tokenizer.ggml.model"
         PRE                  = "tokenizer.ggml.pre"
@@ -204,14 +214,17 @@ class MODEL_ARCH(IntEnum):
     ORION        = auto()
     INTERNLM2    = auto()
     MINICPM      = auto()
+    MINICPM3     = auto()
     GEMMA        = auto()
     GEMMA2       = auto()
     STARCODER2   = auto()
+    RWKV6        = auto()
     MAMBA        = auto()
     XVERSE       = auto()
     COMMAND_R    = auto()
     DBRX         = auto()
     OLMO         = auto()
+    OLMOE        = auto()
     OPENELM      = auto()
     ARCTIC       = auto()
     DEEPSEEK2    = auto()
@@ -222,6 +235,9 @@ class MODEL_ARCH(IntEnum):
     JAIS         = auto()
     NEMOTRON     = auto()
     EXAONE       = auto()
+    GRANITE      = auto()
+    GRANITE_MOE  = auto()
+    CHAMELEON    = auto()
 
 
 class MODEL_TENSOR(IntEnum):
@@ -270,6 +286,29 @@ class MODEL_TENSOR(IntEnum):
     SSM_A                = auto()
     SSM_D                = auto()
     SSM_OUT              = auto()
+    TIME_MIX_W1          = auto()
+    TIME_MIX_W2          = auto()
+    TIME_MIX_LERP_X      = auto()
+    TIME_MIX_LERP_K      = auto()
+    TIME_MIX_LERP_V      = auto()
+    TIME_MIX_LERP_R      = auto()
+    TIME_MIX_LERP_G      = auto()
+    TIME_MIX_LERP_W      = auto()
+    TIME_MIX_FIRST       = auto()
+    TIME_MIX_DECAY       = auto()
+    TIME_MIX_DECAY_W1    = auto()
+    TIME_MIX_DECAY_W2    = auto()
+    TIME_MIX_KEY         = auto()
+    TIME_MIX_VALUE       = auto()
+    TIME_MIX_RECEPTANCE  = auto()
+    TIME_MIX_GATE        = auto()
+    TIME_MIX_LN          = auto()
+    TIME_MIX_OUTPUT      = auto()
+    CHANNEL_MIX_LERP_K   = auto()
+    CHANNEL_MIX_LERP_R   = auto()
+    CHANNEL_MIX_KEY      = auto()
+    CHANNEL_MIX_RECEPTANCE = auto()
+    CHANNEL_MIX_VALUE    = auto()
     ATTN_Q_A             = auto()
     ATTN_Q_B             = auto()
     ATTN_KV_A_MQA        = auto()
@@ -306,6 +345,8 @@ class MODEL_TENSOR(IntEnum):
     ENC_FFN_DOWN         = auto()
     ENC_FFN_UP           = auto()
     ENC_OUTPUT_NORM      = auto()
+    CLS                  = auto() # classifier
+    CLS_OUT              = auto() # classifier output projection
 
 
 MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
@@ -334,14 +375,17 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
     MODEL_ARCH.ORION:          "orion",
     MODEL_ARCH.INTERNLM2:      "internlm2",
     MODEL_ARCH.MINICPM:        "minicpm",
+    MODEL_ARCH.MINICPM3:       "minicpm3",
     MODEL_ARCH.GEMMA:          "gemma",
     MODEL_ARCH.GEMMA2:         "gemma2",
     MODEL_ARCH.STARCODER2:     "starcoder2",
+    MODEL_ARCH.RWKV6:          "rwkv6",
     MODEL_ARCH.MAMBA:          "mamba",
     MODEL_ARCH.XVERSE:         "xverse",
     MODEL_ARCH.COMMAND_R:      "command-r",
     MODEL_ARCH.DBRX:           "dbrx",
     MODEL_ARCH.OLMO:           "olmo",
+    MODEL_ARCH.OLMOE:          "olmoe",
     MODEL_ARCH.OPENELM:        "openelm",
     MODEL_ARCH.ARCTIC:         "arctic",
     MODEL_ARCH.DEEPSEEK2:      "deepseek2",
@@ -352,90 +396,118 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
     MODEL_ARCH.JAIS:           "jais",
     MODEL_ARCH.NEMOTRON:       "nemotron",
     MODEL_ARCH.EXAONE:         "exaone",
+    MODEL_ARCH.GRANITE:        "granite",
+    MODEL_ARCH.GRANITE_MOE:    "granitemoe",
+    MODEL_ARCH.CHAMELEON:      "chameleon",
 }
 
 TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
-    MODEL_TENSOR.TOKEN_EMBD:           "token_embd",
-    MODEL_TENSOR.TOKEN_EMBD_NORM:      "token_embd_norm",
-    MODEL_TENSOR.TOKEN_TYPES:          "token_types",
-    MODEL_TENSOR.POS_EMBD:             "position_embd",
-    MODEL_TENSOR.OUTPUT_NORM:          "output_norm",
-    MODEL_TENSOR.OUTPUT:               "output",
-    MODEL_TENSOR.ROPE_FREQS:           "rope_freqs",
-    MODEL_TENSOR.ROPE_FACTORS_LONG:    "rope_factors_long",
-    MODEL_TENSOR.ROPE_FACTORS_SHORT:   "rope_factors_short",
-    MODEL_TENSOR.ATTN_NORM:            "blk.{bid}.attn_norm",
-    MODEL_TENSOR.ATTN_NORM_2:          "blk.{bid}.attn_norm_2",
-    MODEL_TENSOR.ATTN_QKV:             "blk.{bid}.attn_qkv",
-    MODEL_TENSOR.ATTN_Q:               "blk.{bid}.attn_q",
-    MODEL_TENSOR.ATTN_K:               "blk.{bid}.attn_k",
-    MODEL_TENSOR.ATTN_V:               "blk.{bid}.attn_v",
-    MODEL_TENSOR.ATTN_OUT:             "blk.{bid}.attn_output",
-    MODEL_TENSOR.ATTN_ROT_EMBD:        "blk.{bid}.attn_rot_embd",
-    MODEL_TENSOR.ATTN_Q_NORM:          "blk.{bid}.attn_q_norm",
-    MODEL_TENSOR.ATTN_K_NORM:          "blk.{bid}.attn_k_norm",
-    MODEL_TENSOR.ATTN_OUT_NORM:        "blk.{bid}.attn_output_norm",
-    MODEL_TENSOR.ATTN_POST_NORM:       "blk.{bid}.post_attention_norm",
-    MODEL_TENSOR.FFN_GATE_INP:         "blk.{bid}.ffn_gate_inp",
-    MODEL_TENSOR.FFN_GATE_INP_SHEXP:   "blk.{bid}.ffn_gate_inp_shexp",
-    MODEL_TENSOR.FFN_NORM:             "blk.{bid}.ffn_norm",
-    MODEL_TENSOR.FFN_PRE_NORM:         "blk.{bid}.ffn_norm",
-    MODEL_TENSOR.FFN_POST_NORM:        "blk.{bid}.post_ffw_norm",
-    MODEL_TENSOR.FFN_GATE:             "blk.{bid}.ffn_gate",
-    MODEL_TENSOR.FFN_DOWN:             "blk.{bid}.ffn_down",
-    MODEL_TENSOR.FFN_UP:               "blk.{bid}.ffn_up",
-    MODEL_TENSOR.FFN_GATE_SHEXP:       "blk.{bid}.ffn_gate_shexp",
-    MODEL_TENSOR.FFN_DOWN_SHEXP:       "blk.{bid}.ffn_down_shexp",
-    MODEL_TENSOR.FFN_UP_SHEXP:         "blk.{bid}.ffn_up_shexp",
-    MODEL_TENSOR.FFN_ACT:              "blk.{bid}.ffn",
-    MODEL_TENSOR.FFN_NORM_EXP:         "blk.{bid}.ffn_norm_exps",
-    MODEL_TENSOR.FFN_GATE_EXP:         "blk.{bid}.ffn_gate_exps",
-    MODEL_TENSOR.FFN_DOWN_EXP:         "blk.{bid}.ffn_down_exps",
-    MODEL_TENSOR.FFN_UP_EXP:           "blk.{bid}.ffn_up_exps",
-    MODEL_TENSOR.LAYER_OUT_NORM:       "blk.{bid}.layer_output_norm",
-    MODEL_TENSOR.SSM_IN:               "blk.{bid}.ssm_in",
-    MODEL_TENSOR.SSM_CONV1D:           "blk.{bid}.ssm_conv1d",
-    MODEL_TENSOR.SSM_X:                "blk.{bid}.ssm_x",
-    MODEL_TENSOR.SSM_DT:               "blk.{bid}.ssm_dt",
-    MODEL_TENSOR.SSM_A:                "blk.{bid}.ssm_a",
-    MODEL_TENSOR.SSM_D:                "blk.{bid}.ssm_d",
-    MODEL_TENSOR.SSM_OUT:              "blk.{bid}.ssm_out",
-    MODEL_TENSOR.ATTN_Q_A:             "blk.{bid}.attn_q_a",
-    MODEL_TENSOR.ATTN_Q_B:             "blk.{bid}.attn_q_b",
-    MODEL_TENSOR.ATTN_KV_A_MQA:        "blk.{bid}.attn_kv_a_mqa",
-    MODEL_TENSOR.ATTN_KV_B:            "blk.{bid}.attn_kv_b",
-    MODEL_TENSOR.ATTN_Q_A_NORM:        "blk.{bid}.attn_q_a_norm",
-    MODEL_TENSOR.ATTN_KV_A_NORM:       "blk.{bid}.attn_kv_a_norm",
-    MODEL_TENSOR.ATTN_SUB_NORM:        "blk.{bid}.attn_sub_norm",
-    MODEL_TENSOR.FFN_SUB_NORM:         "blk.{bid}.ffn_sub_norm",
-    MODEL_TENSOR.DEC_ATTN_NORM:        "dec.blk.{bid}.attn_norm",
-    MODEL_TENSOR.DEC_ATTN_Q:           "dec.blk.{bid}.attn_q",
-    MODEL_TENSOR.DEC_ATTN_K:           "dec.blk.{bid}.attn_k",
-    MODEL_TENSOR.DEC_ATTN_V:           "dec.blk.{bid}.attn_v",
-    MODEL_TENSOR.DEC_ATTN_OUT:         "dec.blk.{bid}.attn_o",
-    MODEL_TENSOR.DEC_ATTN_REL_B:       "dec.blk.{bid}.attn_rel_b",
-    MODEL_TENSOR.DEC_CROSS_ATTN_NORM:  "dec.blk.{bid}.cross_attn_norm",
-    MODEL_TENSOR.DEC_CROSS_ATTN_Q:     "dec.blk.{bid}.cross_attn_q",
-    MODEL_TENSOR.DEC_CROSS_ATTN_K:     "dec.blk.{bid}.cross_attn_k",
-    MODEL_TENSOR.DEC_CROSS_ATTN_V:     "dec.blk.{bid}.cross_attn_v",
-    MODEL_TENSOR.DEC_CROSS_ATTN_OUT:   "dec.blk.{bid}.cross_attn_o",
-    MODEL_TENSOR.DEC_CROSS_ATTN_REL_B: "dec.blk.{bid}.cross_attn_rel_b",
-    MODEL_TENSOR.DEC_FFN_NORM:         "dec.blk.{bid}.ffn_norm",
-    MODEL_TENSOR.DEC_FFN_GATE:         "dec.blk.{bid}.ffn_gate",
-    MODEL_TENSOR.DEC_FFN_DOWN:         "dec.blk.{bid}.ffn_down",
-    MODEL_TENSOR.DEC_FFN_UP:           "dec.blk.{bid}.ffn_up",
-    MODEL_TENSOR.DEC_OUTPUT_NORM:      "dec.output_norm",
-    MODEL_TENSOR.ENC_ATTN_NORM:        "enc.blk.{bid}.attn_norm",
-    MODEL_TENSOR.ENC_ATTN_Q:           "enc.blk.{bid}.attn_q",
-    MODEL_TENSOR.ENC_ATTN_K:           "enc.blk.{bid}.attn_k",
-    MODEL_TENSOR.ENC_ATTN_V:           "enc.blk.{bid}.attn_v",
-    MODEL_TENSOR.ENC_ATTN_OUT:         "enc.blk.{bid}.attn_o",
-    MODEL_TENSOR.ENC_ATTN_REL_B:       "enc.blk.{bid}.attn_rel_b",
-    MODEL_TENSOR.ENC_FFN_NORM:         "enc.blk.{bid}.ffn_norm",
-    MODEL_TENSOR.ENC_FFN_GATE:         "enc.blk.{bid}.ffn_gate",
-    MODEL_TENSOR.ENC_FFN_DOWN:         "enc.blk.{bid}.ffn_down",
-    MODEL_TENSOR.ENC_FFN_UP:           "enc.blk.{bid}.ffn_up",
-    MODEL_TENSOR.ENC_OUTPUT_NORM:      "enc.output_norm",
+    MODEL_TENSOR.TOKEN_EMBD:                "token_embd",
+    MODEL_TENSOR.TOKEN_EMBD_NORM:           "token_embd_norm",
+    MODEL_TENSOR.TOKEN_TYPES:               "token_types",
+    MODEL_TENSOR.POS_EMBD:                  "position_embd",
+    MODEL_TENSOR.OUTPUT_NORM:               "output_norm",
+    MODEL_TENSOR.OUTPUT:                    "output",
+    MODEL_TENSOR.ROPE_FREQS:                "rope_freqs",
+    MODEL_TENSOR.ROPE_FACTORS_LONG:         "rope_factors_long",
+    MODEL_TENSOR.ROPE_FACTORS_SHORT:        "rope_factors_short",
+    MODEL_TENSOR.ATTN_NORM:                 "blk.{bid}.attn_norm",
+    MODEL_TENSOR.ATTN_NORM_2:               "blk.{bid}.attn_norm_2",
+    MODEL_TENSOR.ATTN_QKV:                  "blk.{bid}.attn_qkv",
+    MODEL_TENSOR.ATTN_Q:                    "blk.{bid}.attn_q",
+    MODEL_TENSOR.ATTN_K:                    "blk.{bid}.attn_k",
+    MODEL_TENSOR.ATTN_V:                    "blk.{bid}.attn_v",
+    MODEL_TENSOR.ATTN_OUT:                  "blk.{bid}.attn_output",
+    MODEL_TENSOR.ATTN_ROT_EMBD:             "blk.{bid}.attn_rot_embd",
+    MODEL_TENSOR.ATTN_Q_NORM:               "blk.{bid}.attn_q_norm",
+    MODEL_TENSOR.ATTN_K_NORM:               "blk.{bid}.attn_k_norm",
+    MODEL_TENSOR.ATTN_OUT_NORM:             "blk.{bid}.attn_output_norm",
+    MODEL_TENSOR.ATTN_POST_NORM:            "blk.{bid}.post_attention_norm",
+    MODEL_TENSOR.FFN_GATE_INP:              "blk.{bid}.ffn_gate_inp",
+    MODEL_TENSOR.FFN_GATE_INP_SHEXP:        "blk.{bid}.ffn_gate_inp_shexp",
+    MODEL_TENSOR.FFN_NORM:                  "blk.{bid}.ffn_norm",
+    MODEL_TENSOR.FFN_PRE_NORM:              "blk.{bid}.ffn_norm",
+    MODEL_TENSOR.FFN_POST_NORM:             "blk.{bid}.post_ffw_norm",
+    MODEL_TENSOR.FFN_GATE:                  "blk.{bid}.ffn_gate",
+    MODEL_TENSOR.FFN_DOWN:                  "blk.{bid}.ffn_down",
+    MODEL_TENSOR.FFN_UP:                    "blk.{bid}.ffn_up",
+    MODEL_TENSOR.FFN_GATE_SHEXP:            "blk.{bid}.ffn_gate_shexp",
+    MODEL_TENSOR.FFN_DOWN_SHEXP:            "blk.{bid}.ffn_down_shexp",
+    MODEL_TENSOR.FFN_UP_SHEXP:              "blk.{bid}.ffn_up_shexp",
+    MODEL_TENSOR.FFN_ACT:                   "blk.{bid}.ffn",
+    MODEL_TENSOR.FFN_NORM_EXP:              "blk.{bid}.ffn_norm_exps",
+    MODEL_TENSOR.FFN_GATE_EXP:              "blk.{bid}.ffn_gate_exps",
+    MODEL_TENSOR.FFN_DOWN_EXP:              "blk.{bid}.ffn_down_exps",
+    MODEL_TENSOR.FFN_UP_EXP:                "blk.{bid}.ffn_up_exps",
+    MODEL_TENSOR.LAYER_OUT_NORM:            "blk.{bid}.layer_output_norm",
+    MODEL_TENSOR.SSM_IN:                    "blk.{bid}.ssm_in",
+    MODEL_TENSOR.SSM_CONV1D:                "blk.{bid}.ssm_conv1d",
+    MODEL_TENSOR.SSM_X:                     "blk.{bid}.ssm_x",
+    MODEL_TENSOR.SSM_DT:                    "blk.{bid}.ssm_dt",
+    MODEL_TENSOR.SSM_A:                     "blk.{bid}.ssm_a",
+    MODEL_TENSOR.SSM_D:                     "blk.{bid}.ssm_d",
+    MODEL_TENSOR.SSM_OUT:                   "blk.{bid}.ssm_out",
+    MODEL_TENSOR.TIME_MIX_W1:               "blk.{bid}.time_mix_w1",
+    MODEL_TENSOR.TIME_MIX_W2:               "blk.{bid}.time_mix_w2",
+    MODEL_TENSOR.TIME_MIX_LERP_X:           "blk.{bid}.time_mix_lerp_x",
+    MODEL_TENSOR.TIME_MIX_LERP_K:           "blk.{bid}.time_mix_lerp_k",
+    MODEL_TENSOR.TIME_MIX_LERP_V:           "blk.{bid}.time_mix_lerp_v",
+    MODEL_TENSOR.TIME_MIX_LERP_R:           "blk.{bid}.time_mix_lerp_r",
+    MODEL_TENSOR.TIME_MIX_LERP_G:           "blk.{bid}.time_mix_lerp_g",
+    MODEL_TENSOR.TIME_MIX_LERP_W:           "blk.{bid}.time_mix_lerp_w",
+    MODEL_TENSOR.TIME_MIX_FIRST:            "blk.{bid}.time_mix_first",
+    MODEL_TENSOR.TIME_MIX_DECAY:            "blk.{bid}.time_mix_decay",
+    MODEL_TENSOR.TIME_MIX_DECAY_W1:         "blk.{bid}.time_mix_decay_w1",
+    MODEL_TENSOR.TIME_MIX_DECAY_W2:         "blk.{bid}.time_mix_decay_w2",
+    MODEL_TENSOR.TIME_MIX_KEY:              "blk.{bid}.time_mix_key",
+    MODEL_TENSOR.TIME_MIX_VALUE:            "blk.{bid}.time_mix_value",
+    MODEL_TENSOR.TIME_MIX_RECEPTANCE:       "blk.{bid}.time_mix_receptance",
+    MODEL_TENSOR.TIME_MIX_GATE:             "blk.{bid}.time_mix_gate",
+    MODEL_TENSOR.TIME_MIX_LN:               "blk.{bid}.time_mix_ln",
+    MODEL_TENSOR.TIME_MIX_OUTPUT:           "blk.{bid}.time_mix_output",
+    MODEL_TENSOR.CHANNEL_MIX_LERP_K:        "blk.{bid}.channel_mix_lerp_k",
+    MODEL_TENSOR.CHANNEL_MIX_LERP_R:        "blk.{bid}.channel_mix_lerp_r",
+    MODEL_TENSOR.CHANNEL_MIX_KEY:           "blk.{bid}.channel_mix_key",
+    MODEL_TENSOR.CHANNEL_MIX_RECEPTANCE:    "blk.{bid}.channel_mix_receptance",
+    MODEL_TENSOR.CHANNEL_MIX_VALUE:         "blk.{bid}.channel_mix_value",
+    MODEL_TENSOR.ATTN_Q_A:                  "blk.{bid}.attn_q_a",
+    MODEL_TENSOR.ATTN_Q_B:                  "blk.{bid}.attn_q_b",
+    MODEL_TENSOR.ATTN_KV_A_MQA:             "blk.{bid}.attn_kv_a_mqa",
+    MODEL_TENSOR.ATTN_KV_B:                 "blk.{bid}.attn_kv_b",
+    MODEL_TENSOR.ATTN_Q_A_NORM:             "blk.{bid}.attn_q_a_norm",
+    MODEL_TENSOR.ATTN_KV_A_NORM:            "blk.{bid}.attn_kv_a_norm",
+    MODEL_TENSOR.ATTN_SUB_NORM:             "blk.{bid}.attn_sub_norm",
+    MODEL_TENSOR.FFN_SUB_NORM:              "blk.{bid}.ffn_sub_norm",
+    MODEL_TENSOR.DEC_ATTN_NORM:             "dec.blk.{bid}.attn_norm",
+    MODEL_TENSOR.DEC_ATTN_Q:                "dec.blk.{bid}.attn_q",
+    MODEL_TENSOR.DEC_ATTN_K:                "dec.blk.{bid}.attn_k",
+    MODEL_TENSOR.DEC_ATTN_V:                "dec.blk.{bid}.attn_v",
+    MODEL_TENSOR.DEC_ATTN_OUT:              "dec.blk.{bid}.attn_o",
+    MODEL_TENSOR.DEC_ATTN_REL_B:            "dec.blk.{bid}.attn_rel_b",
+    MODEL_TENSOR.DEC_CROSS_ATTN_NORM:       "dec.blk.{bid}.cross_attn_norm",
+    MODEL_TENSOR.DEC_CROSS_ATTN_Q:          "dec.blk.{bid}.cross_attn_q",
+    MODEL_TENSOR.DEC_CROSS_ATTN_K:          "dec.blk.{bid}.cross_attn_k",
+    MODEL_TENSOR.DEC_CROSS_ATTN_V:          "dec.blk.{bid}.cross_attn_v",
+    MODEL_TENSOR.DEC_CROSS_ATTN_OUT:        "dec.blk.{bid}.cross_attn_o",
+    MODEL_TENSOR.DEC_CROSS_ATTN_REL_B:      "dec.blk.{bid}.cross_attn_rel_b",
+    MODEL_TENSOR.DEC_FFN_NORM:              "dec.blk.{bid}.ffn_norm",
+    MODEL_TENSOR.DEC_FFN_GATE:              "dec.blk.{bid}.ffn_gate",
+    MODEL_TENSOR.DEC_FFN_DOWN:              "dec.blk.{bid}.ffn_down",
+    MODEL_TENSOR.DEC_FFN_UP:                "dec.blk.{bid}.ffn_up",
+    MODEL_TENSOR.DEC_OUTPUT_NORM:           "dec.output_norm",
+    MODEL_TENSOR.ENC_ATTN_NORM:             "enc.blk.{bid}.attn_norm",
+    MODEL_TENSOR.ENC_ATTN_Q:                "enc.blk.{bid}.attn_q",
+    MODEL_TENSOR.ENC_ATTN_K:                "enc.blk.{bid}.attn_k",
+    MODEL_TENSOR.ENC_ATTN_V:                "enc.blk.{bid}.attn_v",
+    MODEL_TENSOR.ENC_ATTN_OUT:              "enc.blk.{bid}.attn_o",
+    MODEL_TENSOR.ENC_ATTN_REL_B:            "enc.blk.{bid}.attn_rel_b",
+    MODEL_TENSOR.ENC_FFN_NORM:              "enc.blk.{bid}.ffn_norm",
+    MODEL_TENSOR.ENC_FFN_GATE:              "enc.blk.{bid}.ffn_gate",
+    MODEL_TENSOR.ENC_FFN_DOWN:              "enc.blk.{bid}.ffn_down",
+    MODEL_TENSOR.ENC_FFN_UP:                "enc.blk.{bid}.ffn_up",
+    MODEL_TENSOR.ENC_OUTPUT_NORM:           "enc.output_norm",
+    MODEL_TENSOR.CLS:                       "cls",
+    MODEL_TENSOR.CLS_OUT:                   "cls.output",
 }
 
 MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
@@ -545,6 +617,8 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
         MODEL_TENSOR.FFN_DOWN,
         MODEL_TENSOR.FFN_UP,
         MODEL_TENSOR.LAYER_OUT_NORM,
+        MODEL_TENSOR.CLS,
+        MODEL_TENSOR.CLS_OUT,
     ],
     MODEL_ARCH.NOMIC_BERT: [
         MODEL_TENSOR.TOKEN_EMBD,
@@ -576,6 +650,7 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
         MODEL_TENSOR.FFN_GATE,
         MODEL_TENSOR.FFN_DOWN,
         MODEL_TENSOR.LAYER_OUT_NORM,
+        MODEL_TENSOR.CLS,
     ],
     MODEL_ARCH.MPT: [
         MODEL_TENSOR.TOKEN_EMBD,
@@ -739,6 +814,8 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
         MODEL_TENSOR.TOKEN_EMBD,
         MODEL_TENSOR.OUTPUT_NORM,
         MODEL_TENSOR.OUTPUT,
+        MODEL_TENSOR.ROPE_FACTORS_LONG,
+        MODEL_TENSOR.ROPE_FACTORS_SHORT,
         MODEL_TENSOR.ATTN_NORM,
         MODEL_TENSOR.ATTN_QKV,
         MODEL_TENSOR.ATTN_Q,
@@ -813,6 +890,25 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
         MODEL_TENSOR.FFN_DOWN_EXP,
         MODEL_TENSOR.FFN_UP_EXP,
     ],
+    MODEL_ARCH.MINICPM3: [
+        MODEL_TENSOR.TOKEN_EMBD,
+        MODEL_TENSOR.OUTPUT_NORM,
+        MODEL_TENSOR.OUTPUT,
+        MODEL_TENSOR.ROPE_FACTORS_LONG,
+        MODEL_TENSOR.ROPE_FACTORS_SHORT,
+        MODEL_TENSOR.ATTN_NORM,
+        MODEL_TENSOR.ATTN_Q_A,
+        MODEL_TENSOR.ATTN_Q_B,
+        MODEL_TENSOR.ATTN_KV_A_MQA,
+        MODEL_TENSOR.ATTN_KV_B,
+        MODEL_TENSOR.ATTN_Q_A_NORM,
+        MODEL_TENSOR.ATTN_KV_A_NORM,
+        MODEL_TENSOR.ATTN_OUT,
+        MODEL_TENSOR.FFN_NORM,
+        MODEL_TENSOR.FFN_GATE,
+        MODEL_TENSOR.FFN_DOWN,
+        MODEL_TENSOR.FFN_UP,
+    ],
     MODEL_ARCH.GEMMA: [
         MODEL_TENSOR.TOKEN_EMBD,
         MODEL_TENSOR.OUTPUT_NORM,
@@ -856,6 +952,37 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
         MODEL_TENSOR.FFN_DOWN,
         MODEL_TENSOR.FFN_UP,
     ],
+    MODEL_ARCH.RWKV6: [
+        MODEL_TENSOR.TOKEN_EMBD,
+        MODEL_TENSOR.TOKEN_EMBD_NORM,
+        MODEL_TENSOR.OUTPUT_NORM,
+        MODEL_TENSOR.OUTPUT,
+        MODEL_TENSOR.ATTN_NORM,
+        MODEL_TENSOR.ATTN_NORM_2,
+        MODEL_TENSOR.TIME_MIX_W1,
+        MODEL_TENSOR.TIME_MIX_W2,
+        MODEL_TENSOR.TIME_MIX_LERP_X,
+        MODEL_TENSOR.TIME_MIX_LERP_K,
+        MODEL_TENSOR.TIME_MIX_LERP_V,
+        MODEL_TENSOR.TIME_MIX_LERP_R,
+        MODEL_TENSOR.TIME_MIX_LERP_G,
+        MODEL_TENSOR.TIME_MIX_LERP_W,
+        MODEL_TENSOR.TIME_MIX_FIRST,
+        MODEL_TENSOR.TIME_MIX_DECAY,
+        MODEL_TENSOR.TIME_MIX_DECAY_W1,
+        MODEL_TENSOR.TIME_MIX_DECAY_W2,
+        MODEL_TENSOR.TIME_MIX_KEY,
+        MODEL_TENSOR.TIME_MIX_VALUE,
+        MODEL_TENSOR.TIME_MIX_RECEPTANCE,
+        MODEL_TENSOR.TIME_MIX_GATE,
+        MODEL_TENSOR.TIME_MIX_LN,
+        MODEL_TENSOR.TIME_MIX_OUTPUT,
+        MODEL_TENSOR.CHANNEL_MIX_LERP_K,
+        MODEL_TENSOR.CHANNEL_MIX_LERP_R,
+        MODEL_TENSOR.CHANNEL_MIX_KEY,
+        MODEL_TENSOR.CHANNEL_MIX_RECEPTANCE,
+        MODEL_TENSOR.CHANNEL_MIX_VALUE,
+    ],
     MODEL_ARCH.MAMBA: [
         MODEL_TENSOR.TOKEN_EMBD,
         MODEL_TENSOR.OUTPUT_NORM,
@@ -923,6 +1050,23 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
         MODEL_TENSOR.FFN_DOWN,
         MODEL_TENSOR.FFN_UP,
     ],
+    MODEL_ARCH.OLMOE: [
+        MODEL_TENSOR.TOKEN_EMBD,
+        MODEL_TENSOR.OUTPUT_NORM,
+        MODEL_TENSOR.OUTPUT,
+        MODEL_TENSOR.ATTN_OUT,
+        MODEL_TENSOR.ATTN_Q,
+        MODEL_TENSOR.ATTN_K,
+        MODEL_TENSOR.ATTN_V,
+        MODEL_TENSOR.ATTN_NORM,
+        MODEL_TENSOR.ATTN_Q_NORM,
+        MODEL_TENSOR.ATTN_K_NORM,
+        MODEL_TENSOR.FFN_NORM,
+        MODEL_TENSOR.FFN_GATE_INP,
+        MODEL_TENSOR.FFN_GATE_EXP,
+        MODEL_TENSOR.FFN_UP_EXP,
+        MODEL_TENSOR.FFN_DOWN_EXP,
+    ],
     MODEL_ARCH.OPENELM: [
         MODEL_TENSOR.TOKEN_EMBD,
         MODEL_TENSOR.OUTPUT_NORM,
@@ -1101,6 +1245,51 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
         MODEL_TENSOR.FFN_DOWN,
         MODEL_TENSOR.FFN_UP,
     ],
+    MODEL_ARCH.GRANITE: [
+        MODEL_TENSOR.TOKEN_EMBD,
+        MODEL_TENSOR.OUTPUT_NORM,
+        MODEL_TENSOR.OUTPUT,
+        MODEL_TENSOR.ATTN_NORM,
+        MODEL_TENSOR.ATTN_Q,
+        MODEL_TENSOR.ATTN_K,
+        MODEL_TENSOR.ATTN_V,
+        MODEL_TENSOR.ATTN_OUT,
+        MODEL_TENSOR.FFN_NORM,
+        MODEL_TENSOR.FFN_GATE,
+        MODEL_TENSOR.FFN_DOWN,
+        MODEL_TENSOR.FFN_UP,
+    ],
+    MODEL_ARCH.GRANITE_MOE: [
+        MODEL_TENSOR.TOKEN_EMBD,
+        MODEL_TENSOR.OUTPUT_NORM,
+        MODEL_TENSOR.OUTPUT,
+        MODEL_TENSOR.ATTN_NORM,
+        MODEL_TENSOR.ATTN_Q,
+        MODEL_TENSOR.ATTN_K,
+        MODEL_TENSOR.ATTN_V,
+        MODEL_TENSOR.ATTN_OUT,
+        MODEL_TENSOR.FFN_NORM,
+        MODEL_TENSOR.FFN_GATE_INP,
+        MODEL_TENSOR.FFN_GATE_EXP,
+        MODEL_TENSOR.FFN_DOWN_EXP,
+        MODEL_TENSOR.FFN_UP_EXP,
+    ],
+    MODEL_ARCH.CHAMELEON: [
+        MODEL_TENSOR.TOKEN_EMBD,
+        MODEL_TENSOR.OUTPUT_NORM,
+        MODEL_TENSOR.OUTPUT,
+        MODEL_TENSOR.ATTN_NORM,
+        MODEL_TENSOR.ATTN_Q,
+        MODEL_TENSOR.ATTN_Q_NORM,
+        MODEL_TENSOR.ATTN_K,
+        MODEL_TENSOR.ATTN_K_NORM,
+        MODEL_TENSOR.ATTN_V,
+        MODEL_TENSOR.ATTN_OUT,
+        MODEL_TENSOR.FFN_NORM,
+        MODEL_TENSOR.FFN_GATE,
+        MODEL_TENSOR.FFN_DOWN,
+        MODEL_TENSOR.FFN_UP,
+    ],
     # TODO
 }
 
@@ -1206,6 +1395,8 @@ class GGMLQuantizationType(IntEnum):
     Q4_0_4_4 = 31
     Q4_0_4_8 = 32
     Q4_0_8_8 = 33
+    TQ1_0   = 34
+    TQ2_0   = 35
 
 
 # TODO: add GGMLFileType from ggml_ftype in ggml.h
@@ -1250,6 +1441,8 @@ class LlamaFileType(IntEnum):
     MOSTLY_Q4_0_4_4      = 33  # except 1d tensors
     MOSTLY_Q4_0_4_8      = 34  # except 1d tensors
     MOSTLY_Q4_0_8_8      = 35  # except 1d tensors
+    MOSTLY_TQ1_0         = 36  # except 1d tensors
+    MOSTLY_TQ2_0         = 37  # except 1d tensors
 
     GUESSED              = 1024  # not specified in the model file
 
@@ -1326,6 +1519,8 @@ GGML_QUANT_SIZES: dict[GGMLQuantizationType, tuple[int, int]] = {
     GGMLQuantizationType.Q4_0_4_4:(32, 2 + 16),
     GGMLQuantizationType.Q4_0_4_8:(32, 2 + 16),
     GGMLQuantizationType.Q4_0_8_8:(32, 2 + 16),
+    GGMLQuantizationType.TQ1_0:   (256, 2 + 4 * 13),
+    GGMLQuantizationType.TQ2_0:   (256, 2 + 64),
 }
 
 

bigdl/cpp/gguf-py/gguf/gguf_writer.py

@@ -670,6 +670,27 @@ class GGUFWriter:
     def add_expert_weights_scale(self, value: float) -> None:
         self.add_float32(Keys.LLM.EXPERT_WEIGHTS_SCALE.format(arch=self.arch), value)
 
+    def add_swin_norm(self, value: bool) -> None:
+        self.add_bool(Keys.LLM.SWIN_NORM.format(arch=self.arch), value)
+
+    def add_rescale_every_n_layers(self, count: int) -> None:
+        self.add_uint32(Keys.LLM.RESCALE_EVERY_N_LAYERS.format(arch=self.arch), count)
+
+    def add_time_mix_extra_dim(self, dim: int) -> None:
+        self.add_uint32(Keys.LLM.TIME_MIX_EXTRA_DIM.format(arch=self.arch), dim)
+
+    def add_time_decay_extra_dim(self, dim: int) -> None:
+        self.add_uint32(Keys.LLM.TIME_DECAY_EXTRA_DIM.format(arch=self.arch), dim)
+
+    def add_residual_scale(self, value: float) -> None:
+        self.add_float32(Keys.LLM.RESIDUAL_SCALE.format(arch=self.arch), value)
+
+    def add_embedding_scale(self, value: float) -> None:
+        self.add_float32(Keys.LLM.EMBEDDING_SCALE.format(arch=self.arch), value)
+
+    def add_wkv_head_size(self, size: int) -> None:
+        self.add_uint32(Keys.WKV.HEAD_SIZE.format(arch=self.arch), size)
+
     def add_layer_norm_eps(self, value: float) -> None:
         self.add_float32(Keys.Attention.LAYERNORM_EPS.format(arch=self.arch), value)
 
@@ -691,6 +712,9 @@ class GGUFWriter:
     def add_sliding_window(self, value: int) -> None:
         self.add_uint32(Keys.Attention.SLIDING_WINDOW.format(arch=self.arch), value)
 
+    def add_attention_scale(self, value: float) -> None:
+        self.add_float32(Keys.Attention.SCALE.format(arch=self.arch), value)
+
     def add_pooling_type(self, value: PoolingType) -> None:
         self.add_uint32(Keys.LLM.POOLING_TYPE.format(arch=self.arch), value.value)
 
@@ -885,4 +909,4 @@ class GGUFWriter:
             if abs(fnum) < 1000.0:
                 return f"{fnum:3.1f}{unit}"
             fnum /= 1000.0
-        return f"{fnum:.1f}T - over 1TB, split recommended"
+        return f"{fnum:.1f}T - over 1TB, split recommended"

bigdl/cpp/gguf-py/gguf/lazy.py

@@ -210,5 +210,4 @@ class LazyNumpyTensor(LazyBase):
         eager = LazyNumpyTensor.to_eager(self)
         return eager.tofile(*args, **kwargs)
 
-
     # TODO: __array_function__