llama : remove Persimmon (#7408)

* llama : remove Persimmon

* requirements : remove

Author: ggerganov

README.md

@@ -107,7 +107,6 @@ Typically finetunes of the base models below are supported as well.
 - [X] [Aquila 1 & 2](https://huggingface.co/models?search=BAAI/Aquila)
 - [X] [Starcoder models](https://github.com/ggerganov/llama.cpp/pull/3187)
 - [X] [Refact](https://huggingface.co/smallcloudai/Refact-1_6B-fim)
-- [X] [Persimmon 8B](https://github.com/ggerganov/llama.cpp/pull/3410)
 - [X] [MPT](https://github.com/ggerganov/llama.cpp/pull/3417)
 - [X] [Bloom](https://github.com/ggerganov/llama.cpp/pull/3553)
 - [x] [Yi models](https://huggingface.co/models?search=01-ai/Yi)

convert-hf-to-gguf.py

@@ -1148,45 +1148,6 @@ def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iter
         return tensors
 
 
-@Model.register("PersimmonForCausalLM")
-class PersimmonModel(Model):
-    model_arch = gguf.MODEL_ARCH.PERSIMMON
-
-    def set_gguf_parameters(self):
-        block_count = self.hparams.get("num_layers", self.hparams.get("num_hidden_layers"))
-        head_count = self.hparams["num_attention_heads"]
-        head_count_kv = head_count
-        hidden_size = self.hparams["hidden_size"]
-
-        self.gguf_writer.add_name('persimmon-8b-chat')
-        self.gguf_writer.add_context_length(self.hparams["max_position_embeddings"])
-        self.gguf_writer.add_embedding_length(hidden_size)
-        self.gguf_writer.add_block_count(block_count)
-        self.gguf_writer.add_feed_forward_length(self.hparams["intermediate_size"])
-
-        # NOTE: not sure about this change - why does the model not have a rope dimension count when it is smaller
-        #       than the head size?
-        #       ref: https://github.com/ggerganov/llama.cpp/pull/4889
-        # self.gguf_writer.add_rope_dimension_count(hidden_size // head_count)
-        self.gguf_writer.add_rope_dimension_count(hidden_size // head_count // 2)
-
-        self.gguf_writer.add_head_count(head_count)
-        self.gguf_writer.add_head_count_kv(head_count_kv)
-        self.gguf_writer.add_rope_freq_base(self.hparams["rope_theta"])
-        self.gguf_writer.add_layer_norm_eps(self.hparams["layer_norm_eps"])
-
-    def set_vocab(self):
-        self._set_vocab_sentencepiece()
-        # self.gguf_writer.add_bos_token_id(71013)
-        # self.gguf_writer.add_eos_token_id(71013)
-
-    def extra_f32_tensors(self, name: str, new_name: str, bid: int | None, n_dims: int) -> bool:
-        del name, new_name, bid, n_dims  # unused
-
-        # TODO: FP16 conversion produces garbage outputs. (Q8_0 does not, so..?)
-        return True
-
-
 @Model.register("StableLmForCausalLM", "StableLMEpochForCausalLM", "LlavaStableLMEpochForCausalLM")
 class StableLMModel(Model):
     model_arch = gguf.MODEL_ARCH.STABLELM

convert-persimmon-to-gguf.py

@@ -115,7 +115,6 @@ class MODEL_ARCH(IntEnum):
     GPTNEOX    = auto()
     MPT        = auto()
     STARCODER  = auto()
-    PERSIMMON  = auto()
     REFACT     = auto()
     BERT       = auto()
     NOMIC_BERT = auto()
@@ -193,7 +192,6 @@ class MODEL_TENSOR(IntEnum):
     MODEL_ARCH.GPTNEOX:        "gptneox",
     MODEL_ARCH.MPT:            "mpt",
     MODEL_ARCH.STARCODER:      "starcoder",
-    MODEL_ARCH.PERSIMMON:      "persimmon",
     MODEL_ARCH.REFACT:         "refact",
     MODEL_ARCH.BERT:           "bert",
     MODEL_ARCH.NOMIC_BERT:     "nomic-bert",
@@ -426,20 +424,6 @@ class MODEL_TENSOR(IntEnum):
         MODEL_TENSOR.FFN_DOWN,
         MODEL_TENSOR.FFN_UP,
     ],
-    MODEL_ARCH.PERSIMMON: [
-        MODEL_TENSOR.TOKEN_EMBD,
-        MODEL_TENSOR.OUTPUT,
-        MODEL_TENSOR.OUTPUT_NORM,
-        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_TENSOR.ATTN_Q_NORM,
-        MODEL_TENSOR.ATTN_K_NORM,
-        MODEL_TENSOR.ATTN_ROT_EMBD,
-    ],
     MODEL_ARCH.REFACT: [
         MODEL_TENSOR.TOKEN_EMBD,
         MODEL_TENSOR.OUTPUT_NORM,
@@ -756,9 +740,6 @@ class MODEL_TENSOR(IntEnum):
         MODEL_TENSOR.ROPE_FREQS,
         MODEL_TENSOR.ATTN_ROT_EMBD,
     ],
-    MODEL_ARCH.PERSIMMON: [
-        MODEL_TENSOR.ROPE_FREQS,
-    ],
     MODEL_ARCH.QWEN: [
         MODEL_TENSOR.ROPE_FREQS,
         MODEL_TENSOR.ATTN_ROT_EMBD,