model : add LiquidAI/LFM3-1.7B and LiquidAI/LFM3-VL-2B (#31252)

* model : add LiquidAI/LFM3-1.7B and LiquidAI/LFM3-VL-2B

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>
Assisted-by: Claude Opus 5.5

* tests : set the SWA rope base of the LFM3 test model

Assisted-by: Claude Opus 5.5

* llama : enable recurrent state rollback for LFM3

Assisted-by: Claude Opus 5.5

* Apply batched suggestions from code review

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
Co-authored-by: Tarek Dakhran <github@dakhran.com>

* gguf-py : align the lfm3vl mapping comments

Assisted-by: Claude Opus 5.5

* llama : fix CRLF line endings from the review suggestions

Assisted-by: Claude Opus 5.5

* tests : add the LFM3 Metal fusion baseline

Assisted-by: Claude Opus 5.5

* llama : keep the LFM3-VL depthwise conv kernels in F32 when quantizing

Assisted-by: Claude Opus 5.5

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@huggingface.co>
Co-authored-by: Xuan-Son Nguyen <son@huggingface.co>
This commit is contained in:
authored and GitHub committed 2026-10-27 17:06:40 +01:00
1 parent e86f5fd1e9
commit 19cce69199
23 files changed
+1070 -5

No files matched your search

+41
View File
@@ -5589,6 +5589,47 @@ static void test_template_output_peg_parsers(bool detailed_debug) {
test_lfm2_parser(tmpl, detailed_debug);
}
{
auto tst = peg_tester("models/templates/LFM3.jinja", detailed_debug);
tst.test("Hello, world!\nWhat's up?")
.enable_thinking(false)
.reasoning_format(COMMON_REASONING_FORMAT_AUTO)
.expect(message_assist)
.run();
tst.test("I'm\nthinking</think>Hello, world!\nWhat's up?")
.enable_thinking(true)
.reasoning_format(COMMON_REASONING_FORMAT_AUTO)
.expect(message_assist_thoughts)
.run();
tst.test(
"<tool_call>\n"
"<function=special_function>\n"
"<parameter=arg1>\n1\n</parameter>\n"
"</function>\n"
"</tool_call>")
.enable_thinking(false)
.reasoning_format(COMMON_REASONING_FORMAT_AUTO)
.tools({ special_function_tool })
.expect(message_assist_call)
.run();
tst.test(
"I'm\nthinking</think>"
"<tool_call>\n"
"<function=special_function>\n"
"<parameter=arg1>\n1\n</parameter>\n"
"</function>\n"
"</tool_call>")
.enable_thinking(true)
.reasoning_format(COMMON_REASONING_FORMAT_AUTO)
.tools({ special_function_tool })
.expect(message_assist_call_thoughts)
.run();
}
// Thinking cases only apply to LFM2.5-8B-A1B, the one LFM2 template that emits <think>
{
auto tst = peg_tester("models/templates/LFM2.5-8B-A1B.jinja", detailed_debug);