root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 11:54:35 +00:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

cont

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-07-04 22:28:19 +03:00
parent d8f2da6b9f
commit c172b322c2
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
4 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ci/run.sh
View File

@ -287,7 +287,7 @@ function gg_run_open_llama_7b_v2 {
(time cmake -DCMAKE_BUILD_TYPE=Release ${CMAKE_EXTRA} -DGGML_CUDA=1 .. ) 2>&1 | tee -a $OUT/${ci}-cmake.log
(time make -j ) 2>&1 | tee -a $OUT/${ci}-make.log
python3 ../examples/convert-legacy-llama.py ${path_models} --outfile ${path_models}/ggml-model-f16.gguf
python3 ../examples/convert_legacy_llama.py ${path_models} --outfile ${path_models}/ggml-model-f16.gguf
model_f16="${path_models}/ggml-model-f16.gguf"
model_q8_0="${path_models}/ggml-model-q8_0.gguf"

2
convert_hf_to_gguf.py
View File

@ -1161,7 +1161,7 @@ class FalconModel(Model):
# So we rearrange them here,, so that we have n_head query weights
# followed by n_head_kv key weights followed by n_head_kv value weights,
# in contiguous fashion.
# ref: https://github.com/jploski/ggml/blob/falcon40b/examples/falcon/convert_hf_to_gguf.py
# ref: https://github.com/jploski/ggml/blob/falcon40b/examples/falcon/convert-hf-to-gguf.py
if "query_key_value" in name:
n_head = self.find_hparam(["num_attention_heads", "n_head"])

10
convert_hf_to_gguf_update.py
View File

@ -15,7 +15,7 @@
# - Add a new model to the "models" list
# - Run the script with your huggingface token:
#
# python3 convert_hf_to_gguf-update.py <huggingface_token>
# python3 convert_hf_to_gguf_update.py <huggingface_token>
#
# - Copy-paste the generated get_vocab_base_pre() function into convert_hf_to_gguf.py
# - Update llama.cpp with the new pre-tokenizer if necessary
@ -37,7 +37,7 @@ from enum import IntEnum, auto
from transformers import AutoTokenizer
logging.basicConfig(level=logging.DEBUG)
logger = logging.getLogger("convert_hf_to_gguf-update")
logger = logging.getLogger("convert_hf_to_gguf_update")
sess = requests.Session()
@ -56,10 +56,10 @@ if len(sys.argv) == 2:
token = sys.argv[1]
if not token.startswith("hf_"):
logger.info("Huggingface token seems invalid")
logger.info("Usage: python convert_hf_to_gguf-update.py <huggingface_token>")
logger.info("Usage: python convert_hf_to_gguf_update.py <huggingface_token>")
sys.exit(1)
else:
logger.info("Usage: python convert_hf_to_gguf-update.py <huggingface_token>")
logger.info("Usage: python convert_hf_to_gguf_update.py <huggingface_token>")
sys.exit(1)
# TODO: add models here, base models preferred
@ -201,7 +201,7 @@ src_func = f"""
res = None
# NOTE: if you get an error here, you need to update the convert_hf_to_gguf-update.py script
# NOTE: if you get an error here, you need to update the convert_hf_to_gguf_update.py script
# or pull the latest version of the model from Huggingface
# don't edit the hashes manually!
{src_ifs}

2
docs/HOWTO-add-model.md
View File

@ -17,7 +17,7 @@ Also, it is important to check that the examples and main ggml backends (CUDA, M
### 1. Convert the model to GGUF
This step is done in python with a `convert` script using the [gguf](https://pypi.org/project/gguf/) library.
Depending on the model architecture, you can use either [convert_hf_to_gguf.py](../convert_hf_to_gguf.py) or [examples/convert-legacy-llama.py](../examples/convert-legacy-llama.py) (for `llama/llama2` models in `.pth` format).
Depending on the model architecture, you can use either [convert_hf_to_gguf.py](../convert_hf_to_gguf.py) or [examples/convert_legacy_llama.py](../examples/convert_legacy_llama.py) (for `llama/llama2` models in `.pth` format).
The convert script reads the model configuration, tokenizer, tensor names+data and converts them to GGUF metadata and tensors.