wehub-resource-sync
09a3d3ab17
Check Pre-Tokenizer Hashes / pre-tokenizer-hashes (push) Waiting to run
Python check requirements.txt / check-requirements (push) Waiting to run
Python Type-Check / python type-check (push) Waiting to run
Update Operations Documentation / update-ops-docs (push) Waiting to run
Copilot Setup Steps / copilot-setup-steps (push) Failing after 2s
24 lines
885 B
Python
24 lines
885 B
Python
from __future__ import annotations
|
|
|
|
from .base import ModelBase, TextModel, gguf
|
|
|
|
|
|
@ModelBase.register("GPTBigCodeForCausalLM")
|
|
class StarCoderModel(TextModel):
|
|
model_arch = gguf.MODEL_ARCH.STARCODER
|
|
|
|
def set_gguf_parameters(self):
|
|
self.gguf_writer.add_context_length(self.hparams["n_positions"])
|
|
self.gguf_writer.add_embedding_length(self.hparams["n_embd"])
|
|
self.gguf_writer.add_feed_forward_length(4 * self.hparams["n_embd"])
|
|
self.gguf_writer.add_block_count(self.block_count)
|
|
self.gguf_writer.add_head_count(self.hparams["n_head"])
|
|
self.gguf_writer.add_head_count_kv(1)
|
|
self.gguf_writer.add_layer_norm_eps(self.hparams["layer_norm_epsilon"])
|
|
self.gguf_writer.add_file_type(self.ftype)
|
|
|
|
|
|
@ModelBase.register("Starcoder2ForCausalLM")
|
|
class StarCoder2Model(TextModel):
|
|
model_arch = gguf.MODEL_ARCH.STARCODER2
|