From 18cfa8af892cb43d7d5df459024f8f5fc1556161 Mon Sep 17 00:00:00 2001 From: younesbelkada Date: Thu, 14 Nov 2024 14:51:09 +0000 Subject: [PATCH] add fc3 support --- setup_env.py | 5 ++++- utils/convert-hf-to-gguf-bitnet.py | 2 ++ 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/setup_env.py b/setup_env.py index 8a9c4b4..ab4beb9 100644 --- a/setup_env.py +++ b/setup_env.py @@ -19,6 +19,9 @@ SUPPORTED_HF_MODELS = { }, "HF1BitLLM/Llama3-8B-1.58-100B-tokens": { "model_name": "Llama3-8B-1.58-100B-tokens", + }, + "tiiuae/falcon3-7b-1.58bit": { + "model_name": "falcon3-7b-1.58bit", } } @@ -149,7 +152,7 @@ def gen_code(): shutil.copyfile(os.path.join(pretuned_kernels, "bitnet-lut-kernels-tl2.h"), "include/bitnet-lut-kernels.h") if get_model_name() == "bitnet_b1_58-large": run_command([sys.executable, "utils/codegen_tl2.py", "--model", "bitnet_b1_58-large", "--BM", "256,128,256", "--BK", "96,192,96", "--bm", "32,32,32"], log_step="codegen") - elif get_model_name() == "Llama3-8B-1.58-100B-tokens": + elif get_model_name() in ["Llama3-8B-1.58-100B-tokens", "falcon3-7b-1.58bit"]: run_command([sys.executable, "utils/codegen_tl2.py", "--model", "Llama3-8B-1.58-100B-tokens", "--BM", "256,128,256,128", "--BK", "96,96,96,96", "--bm", "32,32,32,32"], log_step="codegen") elif get_model_name() == "bitnet_b1_58-3B": run_command([sys.executable, "utils/codegen_tl2.py", "--model", "bitnet_b1_58-3B", "--BM", "160,320,320", "--BK", "96,96,96", "--bm", "32,32,32"], log_step="codegen") diff --git a/utils/convert-hf-to-gguf-bitnet.py b/utils/convert-hf-to-gguf-bitnet.py index 55b27ae..5621126 100644 --- a/utils/convert-hf-to-gguf-bitnet.py +++ b/utils/convert-hf-to-gguf-bitnet.py @@ -335,6 +335,8 @@ class Model(ABC): if chkhsh == "9c2227e4dd922002fb81bde4fc02b0483ca4f12911410dee2255e4987644e3f8": # ref: https://huggingface.co/CohereForAI/c4ai-command-r-v01 res = "command-r" + if chkhsh == "9d032fcbd5501f4a38150912590928bfb36091efb5df11b8e2124b0390e3fb1e": + res = "falcon3" if res is None: logger.warning("\n")