Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/Jaykef/mlx-rag-gguf
/ functions
Functions
42 in github.com/Jaykef/mlx-rag-gguf
⨍
Functions
42
◇
Types & classes
14
↓ 4 callers
Method
__init__
(self, dim, hidden_dim)
gguf.py:116
↓ 2 callers
Method
__init__
(self, config: ModelConfig)
model.py:101
↓ 2 callers
Method
decode
(self, toks: List[int])
gguf.py:245
↓ 2 callers
Method
run
(self, input_text: List[str])
model.py:138
↓ 1 callers
Function
average_pool
(last_hidden_state: mx.array, attention_mask: mx.array)
model.py:14
↓ 1 callers
Function
chunks_to_mx_array
(chunks: List[str])
vdb.py:41
↓ 1 callers
Method
encode
(self, s: str)
gguf.py:238
↓ 1 callers
Function
get_config
(metadata: dict)
gguf.py:217
↓ 1 callers
Method
ingest
(self, content: str)
vdb.py:74
↓ 1 callers
Function
mx_array_to_chunks
(data: mx.array, lengths: mx.array)
vdb.py:48
↓ 1 callers
Method
query
(self, text: str)
vdb.py:79
↓ 1 callers
Function
rag
( model: gguf.Model, tokenizer: gguf.GGUFTokenizer, prompt: str, max_tokens: int, temp: fl
rag_vdb.py:24
↓ 1 callers
Function
sample
(logits)
gguf.py:323
↓ 1 callers
Method
savez
(self, vdb_file)
vdb.py:85
↓ 1 callers
Function
split_text_into_chunks
Split text into chunks with a specified size and overlap. Parameters: - text (str): The input text to be split into chunks. - chunk_
vdb.py:11
↓ 1 callers
Function
translate_weight_names
(name)
gguf.py:249
↓ 1 callers
Function
vdb_from_pdf
(pdf_file: str)
vdb.py:95
Method
__call__
( self, x: mx.array, mask: Optional[mx.array] = None, cache: Optional[Tuple[mx
gguf.py:83
Method
__call__
(self, x)
gguf.py:122
Method
__call__
( self, x: mx.array, mask: Optional[mx.array] = None, cache: Optional[Tuple[mx
gguf.py:139
Method
__call__
( self, inputs: mx.array, cache=None, )
gguf.py:181
Method
__call__
( self, inputs: mx.array, cache=None, )
gguf.py:208
Method
__call__
(self, x, mask)
model.py:51
Method
__call__
(self, x, mask)
model.py:73
Method
__call__
(self, input_ids: mx.array, token_type_ids: mx.array)
model.py:89
Method
__call__
( self, input_ids: mx.array, token_type_ids: mx.array, attention_mask: mx.arra
model.py:110
Method
__init__
(self, vdb_file: Optional[str] = None)
vdb.py:60
Method
__init__
(self, args: ModelArgs)
gguf.py:55
Method
__init__
(self, args: ModelArgs)
gguf.py:127
Method
__init__
(self, args: ModelArgs)
gguf.py:153
Method
__init__
(self, args: ModelArgs)
gguf.py:203
Method
__init__
(self, metadata)
gguf.py:235
Method
__init__
( self, dims: int, num_heads: int, mlp_dims: Optional[int] = None, lay
model.py:35
Method
__init__
( self, num_layers: int, dims: int, num_heads: int, mlp_dims: Optional[int] = None )
model.py:64
Method
__init__
(self, config: ModelConfig)
model.py:81
Method
__init__
(self)
model.py:128
Method
__post_init__
(self)
gguf.py:31
Method
eos_token_id
(self)
gguf.py:242
Method
from_dict
(cls, params)
gguf.py:44
Function
generate
(prompt: mx.array, model: Model, temp: float = 0.0, max_tokens: int = 512, verbose: bool = False)
gguf.py:322
Function
load
(gguf_file: str, repo: str = None)
gguf.py:266
Function
spm_tokenizer
(metadata)
utils.py:7