model : add dots.llm1 architecture support (ggml-org#14044) (ggml-org#14118)

Adds:

* Dots1Model to convert_hf_to_gguf.py

* Computation graph code to llama-model.cpp

* Chat template to llama-chat.cpp to detect this model's template.

---

The model is called "dots.llm1" (I decided to shorten it to dots1 or
DOTS1 in the code generally) architecture.

The only models that exist as of writing of this commit that follow this
architecture are "dots.llm1.inst" and "dots.llm1.base" from here:

* https://huggingface.co/rednote-hilab/dots.llm1.inst

* https://huggingface.co/rednote-hilab/dots.llm1.base

The model architecture is a combination of Qwen and Deepseek parts, as
seen here:

https://github.com/huggingface/transformers/blob/ffe12627b4e84489d2ab91dd0ec00614855edc79/src/transformers/models/dots1/modular_dots1.py

Author: Noeda

gguf-py/gguf/constants.py

@@ -353,8 +353,6 @@ class MODEL_ARCH(IntEnum):
     PLM              = auto()
     BAILINGMOE       = auto()
     DOTS1            = auto()
-    ARCEE            = auto()
-    ERNIE4_5         = auto()
 
 
 class VISION_PROJECTOR_TYPE(IntEnum):
@@ -653,9 +651,7 @@ class MODEL_TENSOR(IntEnum):
     MODEL_ARCH.WAVTOKENIZER_DEC: "wavtokenizer-dec",
     MODEL_ARCH.PLM:              "plm",
     MODEL_ARCH.BAILINGMOE:       "bailingmoe",
-    MODEL_ARCH.DOTS1:            "dots1",
-    MODEL_ARCH.ARCEE:            "arcee",
-    MODEL_ARCH.ERNIE4_5:         "ernie4_5",
+    MODEL_ARCH.DOTS1:            "dots1"
 }
 
 VISION_PROJECTOR_TYPE_NAMES: dict[VISION_PROJECTOR_TYPE, str] = {
@@ -2164,35 +2160,6 @@ class MODEL_TENSOR(IntEnum):
         MODEL_TENSOR.FFN_UP_EXP,
         MODEL_TENSOR.FFN_UP_SHEXP,
     ],
-    MODEL_ARCH.ARCEE: [
-        MODEL_TENSOR.TOKEN_EMBD,
-        MODEL_TENSOR.OUTPUT_NORM,
-        MODEL_TENSOR.OUTPUT,
-        MODEL_TENSOR.ROPE_FREQS,
-        MODEL_TENSOR.ATTN_NORM,
-        MODEL_TENSOR.ATTN_Q,
-        MODEL_TENSOR.ATTN_K,
-        MODEL_TENSOR.ATTN_V,
-        MODEL_TENSOR.ATTN_OUT,
-        MODEL_TENSOR.ATTN_ROT_EMBD,
-        MODEL_TENSOR.FFN_NORM,
-        MODEL_TENSOR.FFN_DOWN,
-        MODEL_TENSOR.FFN_UP,
-    ],
-    MODEL_ARCH.ERNIE4_5: [
-        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,
-    ],
     # TODO
 }
 

src/llama-arch.cpp

@@ -75,8 +75,6 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
     { LLM_ARCH_PLM,              "plm"              },
     { LLM_ARCH_BAILINGMOE,       "bailingmoe"       },
     { LLM_ARCH_DOTS1,            "dots1"            },
-    { LLM_ARCH_ARCEE,            "arcee"            },
-    { LLM_ARCH_ERNIE4_5,         "ernie4_5"         },
     { LLM_ARCH_UNKNOWN,          "(unknown)"        },
 };
 
@@ -1659,23 +1657,6 @@ static const std::map<llm_arch, std::map<llm_tensor, const char *>> LLM_TENSOR_N
             { LLM_TENSOR_FFN_EXP_PROBS_B,    "blk.%d.exp_probs_b" },
         }
     },
-    {
-        LLM_ARCH_ERNIE4_5,
-        {
-            { LLM_TENSOR_TOKEN_EMBD,         "token_embd" },
-            { LLM_TENSOR_OUTPUT_NORM,        "output_norm" },
-            { LLM_TENSOR_OUTPUT,             "output" },
-            { 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_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_UNKNOWN,
         {

src/llama-arch.h

@@ -79,8 +79,6 @@ enum llm_arch {
     LLM_ARCH_PLM,
     LLM_ARCH_BAILINGMOE,
     LLM_ARCH_DOTS1,
-    LLM_ARCH_ARCEE,
-    LLM_ARCH_ERNIE4_5,
     LLM_ARCH_UNKNOWN,
 };