ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-04-28 18:32:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

Tool calls support from mainline (#723)

Browse Source 
* Tool calls support from mainline

* update cmake

* revert api for /completions

* Fix broken thinking process for gpt-oss

* add missing args and fix webui bugs

* add missing args and fix webui bugs2

* Fix reasoning format error

* add usage

* change default post_sampling_probs to true

* add back generated_text

* Remove server endpoints tests

* add log

* Chat fixes

* Remove logs

* webui: revert extra handling of thinking process

---------

Co-authored-by: firecoperana <firecoperana>
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
firecoperana
2025-09-01 00:38:49 -05:00
committed by GitHub
parent b66cecca45
commit 0f9ecaec04
87 changed files with 13581 additions and 2224 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
scripts/get_hf_chat_template.py
View File

@@ -4,12 +4,11 @@
If a model has multiple chat templates, you can specify the variant name.
Syntax:
./scripts/get_hf_chat_template.py model_id [variant]
./scripts/get_chat_template.py model_id [variant]
Examples:
./scripts/get_hf_chat_template.py NousResearch/Meta-Llama-3-8B-Instruct
./scripts/get_hf_chat_template.py NousResearch/Hermes-3-Llama-3.1-8B tool_use
./scripts/get_hf_chat_template.py meta-llama/Llama-3.2-3B-Instruct
./scripts/get_chat_template.py CohereForAI/c4ai-command-r-plus tool_use
./scripts/get_chat_template.py microsoft/Phi-3.5-mini-instruct
'''
import json
@@ -17,7 +16,7 @@ import re
import sys
def get_hf_chat_template(model_id, variant=None):
def get_chat_template(model_id, variant=None):
try:
# Use huggingface_hub library if available.
# Allows access to gated models if the user has access and ran `huggingface-cli login`.
@@ -69,7 +68,7 @@ def main(args):
model_id = args[0]
variant = None if len(args) < 2 else args[1]
template = get_hf_chat_template(model_id, variant)
template = get_chat_template(model_id, variant)
sys.stdout.write(template)