llama : support glm3 and glm4 (ggml-org#8031)

youth123 · xingxingqiao · Umpire2018 · Neo Zhang · commit bfa07c7003c3 · 2024-07-14T00:20:27.000+08:00
* add chatglm3-6b model support huggingface model: https://hf-mirror.com/THUDM/chatglm3-6b Signed-off-by: XingXing Qiao <qiaoxx@dingdao.com> * remove .rotary_pos_emb.inv_freq and unuse code for chatglm3 model Signed-off-by: XingXing Qiao <qiaoxx@dingdao.com> * fix lint error Signed-off-by: XingXing Qiao <qiaoxx@dingdao.com> * optimize convert-hf-to-gguf.py for chatglm model Signed-off-by: XingXing Qiao <qiaoxx@dingdao.com> * support glm-4-9b-chat Signed-off-by: XingXing Qiao <qiaoxx@dingdao.com> * fix eos tokens to glm4 * remove unused log * add preprocess to chatglm3 and chatglm4 * add eos_id_list to llama.cpp * fix code style * fix code style * fix conflicts * fix conflicts * Revert "add eos_id_list to llama.cpp" This reverts commit 3a4d579. * set <|endoftext|> as eos and <|user|> as eot * fix chat template bug * add comment to glm prefix and suffix * fix conflicts and add rope_ratio & ChatGLMForConditionalGeneration * fix chat template bug * fix codestyle * fix conflicts * modified the general name of glm model * fix conflicts * remove prefix and suffix * use normal glm4 chattempalte & use LLM_FFN_SWIGLU in phi3 * fix: resolve Flake8 errors in `convert-hf-to-gguf.py` - Fix E302 by adding two blank lines before top-level function definitions - Replace print statements to fix NP100 - Fix E303 by ensuring only one blank line between lines of code * fix rope ratio to solve incorrect answers * fix by comments --------- Signed-off-by: XingXing Qiao <qiaoxx@dingdao.com> Co-authored-by: XingXing Qiao <qiaoxx@dingdao.com> Co-authored-by: Umpire2018 <138990495+Umpire2018@users.noreply.github.com>
diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
@@ -487,6 +487,9 @@ def get_vocab_base_pre(self, tokenizer) -> str:
         if chkhsh == "7967bfa498ade6b757b064f31e964dddbb80f8f9a4d68d4ba7998fcf281c531a":
             # ref: https://huggingface.co/jinaai/jina-embeddings-v2-base-code
             res = "jina-v2-code"
+        if chkhsh == "b6e8e1518dc4305be2fe39c313ed643381c4da5db34a98f6a04c093f8afbe99b":
+            # ref: https://huggingface.co/THUDM/glm-4-9b-chat
+            res = "chatglm-bpe"
         if chkhsh == "7fc505bd3104ca1083b150b17d088b59534ede9bde81f0dd2090967d7fe52cee":
             # ref: https://huggingface.co/LumiOpen/Viking-7B
             res = "viking"
@@ -3176,6 +3179,190 @@ def write_tensors(self):
         self.gguf_writer.add_max_alibi_bias(self.max_alibi_bias)
 
 
+@Model.register("ChatGLMModel", "ChatGLMForConditionalGeneration")
+class ChatGLMModel(Model):
+    model_arch = gguf.MODEL_ARCH.CHATGLM
+
+    def set_vocab_chatglm3(self):
+        dir_model = self.dir_model
+        hparams = self.hparams
+        tokens: list[bytearray] = []
+        toktypes: list[int] = []
+        scores: list[float] = []
+
+        from transformers import AutoTokenizer
+        tokenizer = AutoTokenizer.from_pretrained(dir_model, trust_remote_code=True)
+        vocab_size = hparams.get("padded_vocab_size", len(tokenizer.get_vocab()))
+        assert max(tokenizer.get_vocab().values()) < vocab_size
+        role_special_tokens = ["<|system|>", "<|user|>", "<|assistant|>", "<|observation|>"]
+        special_tokens = ["[MASK]", "[gMASK]", "[sMASK]", "sop", "eop"] + role_special_tokens
+        for token_id in range(vocab_size):
+            piece = tokenizer._convert_id_to_token(token_id)
+            if token_id == 0:
+                piece = "<unk>"
+            elif token_id == 1:
+                piece = "<bos>"
+            elif token_id == 2:
+                piece = "<eos>"
+
+            text = piece.encode("utf-8")
+            score = 0.0
+            # Referencing the tokenizer Python implementation(https://huggingface.co/THUDM/chatglm3-6b/blob/main/tokenization_chatglm.py),
+            # it is only valid if it is less than tokenizer.tokenizer.sp_model.vocab_size()
+            if len(piece) != 0 and token_id < tokenizer.tokenizer.sp_model.vocab_size():
+                score = tokenizer.tokenizer.sp_model.get_score(token_id)
+
+            if len(piece) == 0:
+                text = f"[PAD{token_id}]".encode("utf-8")
+
+            if token_id >= tokenizer.tokenizer.sp_model.vocab_size():
+                if piece in special_tokens:
+                    # show special tokens in prompt
+                    toktype = SentencePieceTokenTypes.USER_DEFINED
+                else:
+                    toktype = SentencePieceTokenTypes.UNKNOWN
+                tokens.append(text)
+                scores.append(score)
+                toktypes.append(toktype)
+                continue
+
+            toktype = SentencePieceTokenTypes.NORMAL
+            if tokenizer.tokenizer.sp_model.is_unknown(token_id):
+                toktype = SentencePieceTokenTypes.UNKNOWN
+            elif tokenizer.tokenizer.sp_model.is_control(token_id):
+                toktype = SentencePieceTokenTypes.CONTROL
+            elif tokenizer.tokenizer.sp_model.is_unused(token_id):
+                toktype = SentencePieceTokenTypes.UNUSED
+            elif tokenizer.tokenizer.sp_model.is_byte(token_id):
+                toktype = SentencePieceTokenTypes.BYTE
+
+            tokens.append(text)
+            scores.append(score)
+            toktypes.append(toktype)
+
+        self.gguf_writer.add_tokenizer_model("llama")
+        # glm3 needs prefix and suffix formatted as:
+        # prompt = "[gMASK]sop<|user|>\n" + prompt + "<|assistant|>"
+        self.gguf_writer.add_tokenizer_pre("chatglm-spm")
+        self.gguf_writer.add_token_list(tokens)
+        self.gguf_writer.add_token_scores(scores)
+        self.gguf_writer.add_token_types(toktypes)
+
+        special_vocab = gguf.SpecialVocab(self.dir_model, n_vocab=len(tokens))
+        special_vocab.add_to_gguf(self.gguf_writer)
+
+    @staticmethod
+    def token_bytes_to_string(b):
+        from transformers.models.gpt2.tokenization_gpt2 import bytes_to_unicode
+        byte_encoder = bytes_to_unicode()
+        return ''.join([byte_encoder[ord(char)] for char in b.decode('latin-1')])
+
+    @staticmethod
+    def bpe(mergeable_ranks: dict[bytes, int], token: bytes, max_rank: int | None = None) -> list[bytes]:
+        parts = [bytes([b]) for b in token]
+        while True:
+            min_idx = None
+            min_rank = None
+            for i, pair in enumerate(zip(parts[:-1], parts[1:])):
+                rank = mergeable_ranks.get(pair[0] + pair[1])
+                if rank is not None and (min_rank is None or rank < min_rank):
+                    min_idx = i
+                    min_rank = rank
+            if min_rank is None or (max_rank is not None and min_rank >= max_rank):
+                break
+            assert min_idx is not None
+            parts = parts[:min_idx] + [parts[min_idx] + parts[min_idx + 1]] + parts[min_idx + 2:]
+        return parts
+
+    def set_vocab(self):
+        if "THUDM/chatglm3-6b" in self.hparams.get("_name_or_path", ""):
+            self.set_vocab_chatglm3()
+            return
+
+        dir_model = self.dir_model
+        hparams = self.hparams
+        tokens: list[str] = []
+        toktypes: list[int] = []
+
+        from transformers import AutoTokenizer
+        tokenizer = AutoTokenizer.from_pretrained(dir_model, trust_remote_code=True)
+        vocab_size = hparams["padded_vocab_size"]
+        assert max(tokenizer.get_vocab().values()) < vocab_size
+
+        tokpre = self.get_vocab_base_pre(tokenizer)
+
+        merges = []
+        vocab = {}
+        mergeable_ranks = tokenizer.mergeable_ranks
+        for token, rank in mergeable_ranks.items():
+            vocab[ChatGLMModel.token_bytes_to_string(token)] = rank
+            if len(token) == 1:
+                continue
+            merged = ChatGLMModel.bpe(mergeable_ranks, token, max_rank=rank)
+            assert len(merged) >= 2 and len(merged) <= 7
+            merges.append(' '.join(map(ChatGLMModel.token_bytes_to_string, merged)))
+
+        # for this kind of tokenizer, added_vocab is not a subset of vocab, so they need to be combined
+        added_vocab = tokenizer.get_added_vocab()
+        reverse_vocab = {id_ : encoded_tok for encoded_tok, id_ in {**vocab, **added_vocab}.items()}
+
+        for i in range(vocab_size):
+            if i not in reverse_vocab:
+                tokens.append(f"[PAD{i}]")
+                toktypes.append(gguf.TokenType.USER_DEFINED)
+            elif reverse_vocab[i] in added_vocab:
+                tokens.append(reverse_vocab[i])
+                if tokenizer.added_tokens_decoder[i].special:
+                    toktypes.append(gguf.TokenType.CONTROL)
+                else:
+                    toktypes.append(gguf.TokenType.USER_DEFINED)
+            else:
+                tokens.append(reverse_vocab[i])
+                toktypes.append(gguf.TokenType.NORMAL)
+
+        self.gguf_writer.add_tokenizer_model("gpt2")
+        self.gguf_writer.add_tokenizer_pre(tokpre)
+        self.gguf_writer.add_token_list(tokens)
+        self.gguf_writer.add_token_types(toktypes)
+
+        special_vocab = gguf.SpecialVocab(dir_model, load_merges=False)
+        special_vocab.merges = merges
+        # only add special tokens when they were not already loaded from config.json
+        special_vocab._set_special_token("eos", tokenizer.get_added_vocab()["<|endoftext|>"])
+        special_vocab._set_special_token("eot", tokenizer.get_added_vocab()["<|user|>"])
+        # this one is usually not in config.json anyway
+        special_vocab._set_special_token("unk", tokenizer.get_added_vocab()["<|endoftext|>"])
+        special_vocab.add_to_gguf(self.gguf_writer)
+
+    def set_gguf_parameters(self):
+        self.gguf_writer.add_name(self.hparams.get("_name_or_path").split("/")[1]) # THUDM/glm4-9b-chat or THUDM/chatglm3-6b
+        n_embed = self.hparams.get("hidden_size", self.hparams.get("n_embed"))
+        n_head = self.hparams.get("n_head", self.hparams.get("num_attention_heads"))
+        n_head_kv = self.hparams.get("multi_query_group_num", n_head)
+        self.gguf_writer.add_context_length(self.hparams.get("seq_length", n_embed))
+        self.gguf_writer.add_embedding_length(n_embed)
+        self.gguf_writer.add_feed_forward_length(self.hparams.get("ffn_hidden_size", 4 * n_embed))
+        self.gguf_writer.add_block_count(self.hparams["num_layers"])
+        self.gguf_writer.add_head_count(n_head)
+        self.gguf_writer.add_head_count_kv(n_head_kv)
+        self.gguf_writer.add_layer_norm_rms_eps(self.hparams["layernorm_epsilon"])
+        self.gguf_writer.add_file_type(self.ftype)
+        self.gguf_writer.add_rope_dimension_count(64)
+        self.gguf_writer.add_add_bos_token(False)
+        rope_freq = 10000
+        if "rope_ratio" in self.hparams:
+            rope_freq = rope_freq * self.hparams["rope_ratio"]
+        self.gguf_writer.add_rope_freq_base(rope_freq)
+
+    def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
+        del bid  # unused
+
+        if name.endswith(".rotary_pos_emb.inv_freq"):
+            return []
+
+        name = name.removeprefix("transformer.")
+        return [(self.map_tensor_name(name), data_torch)]
+
 ###### CONVERSION LOGIC ######
 
 
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py
@@ -120,7 +120,6 @@ class Tokenizer:
         MIDDLE_ID            = "tokenizer.ggml.middle_token_id"
         EOT_ID               = "tokenizer.ggml.eot_token_id"
 
-
 #
 # recommended mapping of model tensor names for storage in gguf
 #
@@ -163,6 +162,7 @@ class MODEL_ARCH(IntEnum):
     OPENELM      = auto()
     ARCTIC       = auto()
     DEEPSEEK2    = auto()
+    CHATGLM      = auto()
     BITNET       = auto()
     T5           = auto()
     JAIS         = auto()
@@ -289,6 +289,7 @@ class MODEL_TENSOR(IntEnum):
     MODEL_ARCH.OPENELM:        "openelm",
     MODEL_ARCH.ARCTIC:         "arctic",
     MODEL_ARCH.DEEPSEEK2:      "deepseek2",
+    MODEL_ARCH.CHATGLM:        "chatglm",
     MODEL_ARCH.BITNET:         "bitnet",
     MODEL_ARCH.T5:             "t5",
     MODEL_ARCH.JAIS:           "jais",
@@ -924,6 +925,18 @@ class MODEL_TENSOR(IntEnum):
         MODEL_TENSOR.FFN_DOWN_SHEXP,
         MODEL_TENSOR.FFN_UP_SHEXP,
     ],
+    MODEL_ARCH.CHATGLM : [
+        MODEL_TENSOR.TOKEN_EMBD,
+        MODEL_TENSOR.ROPE_FREQS,
+        MODEL_TENSOR.OUTPUT_NORM,
+        MODEL_TENSOR.OUTPUT,
+        MODEL_TENSOR.ATTN_NORM,
+        MODEL_TENSOR.ATTN_QKV,
+        MODEL_TENSOR.ATTN_OUT,
+        MODEL_TENSOR.FFN_NORM,
+        MODEL_TENSOR.FFN_DOWN,
+        MODEL_TENSOR.FFN_UP,
+    ],
     MODEL_ARCH.BITNET: [
         MODEL_TENSOR.ATTN_Q,
         MODEL_TENSOR.ATTN_K,
@@ -1020,6 +1033,9 @@ class MODEL_TENSOR(IntEnum):
         MODEL_TENSOR.ROPE_FREQS,
         MODEL_TENSOR.ATTN_ROT_EMBD,
     ],
+    MODEL_ARCH.CHATGLM: [
+        MODEL_TENSOR.ROPE_FREQS,
+    ],
 }
 
 #
diff --git a/gguf-py/gguf/tensor_mapping.py b/gguf-py/gguf/tensor_mapping.py
@@ -24,6 +24,7 @@ class TensorNameMap:
             "backbone.embedding",                        # mamba
             "backbone.embeddings",                       # mamba-hf
             "transformer.in_out_embed",                  # Grok
+            "embedding.word_embeddings",                 # chatglm
             "transformer.token_embeddings",              # openelm
             "shared",                                    # t5
         ),
@@ -55,6 +56,7 @@ class TensorNameMap:
             "output",                    # llama-pth bloom internlm2
             "word_embeddings_for_head",  # persimmon
             "lm_head.linear",            # phi2
+            "output_layer",              # chatglm
         ),
 
         # Output norm
@@ -71,12 +73,14 @@ class TensorNameMap:
             "model.norm_f",                            # mamba-qbert
             "backbone.norm_f",                         # mamba
             "transformer.rms_norm",                    # Grok
+            "encoder.final_layernorm",                 # chatglm
             "transformer.norm",                        # openelm
         ),
 
         # Rope frequencies
         MODEL_TENSOR.ROPE_FREQS: (
             "rope.freqs",  # llama-pth
+            "rotary_pos_emb.inv_freq",  # chatglm
         ),
     }
 
@@ -101,6 +105,7 @@ class TensorNameMap:
             "backbone.layers.{bid}.norm",                           # mamba
             "transformer.decoder_layer.{bid}.rms_norm",             # Grok
             "transformer.blocks.{bid}.norm_attn_norm.norm_1",       # dbrx
+            "encoder.layers.{bid}.input_layernorm",                 # chatglm
             "transformer.layers.{bid}.attn_norm",                   # openelm
         ),
 
@@ -124,6 +129,7 @@ class TensorNameMap:
             "transformer.h.{bid}.mixer.Wqkv",                                      # phi2
             "encoder.layers.{bid}.attn.Wqkv",                                      # nomic-bert
             "model.layers.{bid}.self_attn.qkv_proj",                               # phi3
+            "encoder.layers.{bid}.self_attention.query_key_value",                 # chatglm
             "transformer.layers.{bid}.attn.qkv_proj",                              # openelm
         ),
 
@@ -135,7 +141,7 @@ class TensorNameMap:
             "transformer.h.{bid}.attn.q_proj",                           # gpt-j
             "model.layers.layers.{bid}.self_attn.q_proj",                # plamo
             "model.layers.{bid}.attention.wq",                           # internlm2
-            "transformer.decoder_layer.{bid}.multi_head_attention.query" # Grok
+            "transformer.decoder_layer.{bid}.multi_head_attention.query",# Grok
         ),
 
         # Attention key
@@ -147,7 +153,7 @@ class TensorNameMap:
             "transformer.h.{bid}.attn.k",                              # refact
             "model.layers.layers.{bid}.self_attn.k_proj",              # plamo
             "model.layers.{bid}.attention.wk",                         # internlm2
-            "transformer.decoder_layer.{bid}.multi_head_attention.key" # Grok
+            "transformer.decoder_layer.{bid}.multi_head_attention.key",# Grok
         ),
 
         # Attention value
@@ -182,6 +188,7 @@ class TensorNameMap:
             "encoder.layers.{bid}.attn.out_proj",                           # nomic-bert
             "transformer.decoder_layer.{bid}.multi_head_attention.linear",  # Grok
             "transformer.blocks.{bid}.norm_attn_norm.attn.out_proj",        # dbrx
+            "encoder.layers.{bid}.self_attention.dense",                    # chatglm
             "transformer.layers.{bid}.attn.out_proj",                       # openelm
         ),
 
@@ -218,6 +225,7 @@ class TensorNameMap:
             "h.{bid}.ln_2",                                                  # gpt2
             "model.layers.{bid}.ffn_norm",                                   # internlm2
             "transformer.decoder_layer.{bid}.rms_norm_2",                    # Grok
+            "encoder.layers.{bid}.post_attention_layernorm",                 # chatglm
             "transformer.layers.{bid}.ffn_norm",                             # openelm
         ),
 
@@ -268,6 +276,7 @@ class TensorNameMap:
             "model.layers.{bid}.mlp.c_fc",                            # starcoder2
             "encoder.layer.{bid}.mlp.gated_layers_v",                 # jina-bert-v2
             "model.layers.{bid}.residual_mlp.w3",                     # arctic
+            "encoder.layers.{bid}.mlp.dense_h_to_4h",                 # chatglm
         ),
 
         MODEL_TENSOR.FFN_UP_EXP: (
@@ -337,6 +346,7 @@ class TensorNameMap:
             "transformer.layers.{bid}.ffn.proj_2",                    # openelm
             "model.layers.{bid}.residual_mlp.w2",                     # arctic
             "encoder.layer.{bid}.mlp.down_layer",                     # jina-bert-v2
+            "encoder.layers.{bid}.mlp.dense_4h_to_h",                 # chatglm
         ),
 
         MODEL_TENSOR.FFN_DOWN_EXP: (
diff --git a/include/llama.h b/include/llama.h
@@ -88,8 +88,10 @@ extern "C" {
         LLAMA_VOCAB_PRE_TYPE_DBRX           = 13,
         LLAMA_VOCAB_PRE_TYPE_SMAUG          = 14,
         LLAMA_VOCAB_PRE_TYPE_PORO           = 15,
-        LLAMA_VOCAB_PRE_TYPE_VIKING         = 16,
-        LLAMA_VOCAB_PRE_TYPE_JAIS           = 17,
+        LLAMA_VOCAB_PRE_TYPE_CHATGLM3       = 16,
+        LLAMA_VOCAB_PRE_TYPE_CHATGLM4       = 17,
+        LLAMA_VOCAB_PRE_TYPE_VIKING         = 18,
+        LLAMA_VOCAB_PRE_TYPE_JAIS           = 19,
     };
 
     // note: these values should be synchronized with ggml_rope
diff --git a/src/llama.cpp b/src/llama.cpp
diff --git a/tests/test-chat-template.cpp b/tests/test-chat-template.cpp
