vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

gguf-py : export chat templates (#4125)

Browse source 
* gguf-py : export chat templates

* llama.cpp : escape new lines in gguf kv info prints

* gguf-py : bump version

* gguf-py : check chat_template type

* gguf-py : initialize chat_template
This commit is contained in:
slaren 2023-11-19 11:10:52 +01:00 • committed by GitHub
parent 28a2e6e7d4
commit e937066420
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 34 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

29
gguf-py/gguf/constants.py
View file

@ -56,20 +56,21 @@ class Keys:
SCALING_FINETUNED = "{arch}.rope.scaling.finetuned"
class Tokenizer:
MODEL = "tokenizer.ggml.model"
LIST = "tokenizer.ggml.tokens"
TOKEN_TYPE = "tokenizer.ggml.token_type"
SCORES = "tokenizer.ggml.scores"
MERGES = "tokenizer.ggml.merges"
BOS_ID = "tokenizer.ggml.bos_token_id"
EOS_ID = "tokenizer.ggml.eos_token_id"
UNK_ID = "tokenizer.ggml.unknown_token_id"
SEP_ID = "tokenizer.ggml.seperator_token_id"
PAD_ID = "tokenizer.ggml.padding_token_id"
ADD_BOS = "tokenizer.ggml.add_bos_token"
ADD_EOS = "tokenizer.ggml.add_eos_token"
HF_JSON = "tokenizer.huggingface.json"
RWKV = "tokenizer.rwkv.world"
MODEL = "tokenizer.ggml.model"
LIST = "tokenizer.ggml.tokens"
TOKEN_TYPE = "tokenizer.ggml.token_type"
SCORES = "tokenizer.ggml.scores"
MERGES = "tokenizer.ggml.merges"
BOS_ID = "tokenizer.ggml.bos_token_id"
EOS_ID = "tokenizer.ggml.eos_token_id"
UNK_ID = "tokenizer.ggml.unknown_token_id"
SEP_ID = "tokenizer.ggml.seperator_token_id"
PAD_ID = "tokenizer.ggml.padding_token_id"
ADD_BOS = "tokenizer.ggml.add_bos_token"
ADD_EOS = "tokenizer.ggml.add_eos_token"
HF_JSON = "tokenizer.huggingface.json"
RWKV = "tokenizer.rwkv.world"
CHAT_TEMPLATE = "tokenizer.chat_template"
#