ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Qwen 2.5 Coder

Browse source
This commit is contained in:
Daniel Han 2024-11-11 18:46:05 -08:00
commit dd63acf1cc
2 changed files with 34 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
unsloth/models/llama.py
View file

@ -2317,7 +2317,8 @@ class FastLlamaModel:
layer.self_attn.apply_qkv = apply_lora_qkv
n_qkv += 1
else:
if model_type != "qwen2":
if model_type == "qwen2": n_qkv += 1
else:
logger.warning_once(
"Not an error, but Unsloth cannot patch Attention layers with our manual autograd engine since either LoRA adapters\n"\
"are not enabled or a bias term (like in Qwen) is used."

32
unsloth/models/mapper.py
View file

@ -384,22 +384,54 @@ __INT_TO_FLOAT_MAPPER = \
"unsloth/Qwen2.5-Math-72B-Instruct",
"Qwen/Qwen2.5-Math-72B-Instruct",
),
"unsloth/Qwen2.5-Coder-0.5B-bnb-4bit" : (
"unsloth/Qwen2.5-Coder-0.5B",
"Qwen/Qwen2.5-Coder-0.5B",
),
"unsloth/Qwen2.5-Coder-1.5B-bnb-4bit" : (
"unsloth/Qwen2.5-Coder-1.5B",
"Qwen/Qwen2.5-Coder-1.5B",
),
"unsloth/Qwen2.5-Coder-3B-bnb-4bit" : (
"unsloth/Qwen2.5-Coder-3B",
"Qwen/Qwen2.5-Coder-3B",
),
"unsloth/Qwen2.5-Coder-7B-bnb-4bit" : (
"unsloth/Qwen2.5-Coder-7B",
"Qwen/Qwen2.5-Coder-7B",
),
"unsloth/Qwen2.5-Coder-14B-bnb-4bit" : (
"unsloth/Qwen2.5-Coder-14B",
"Qwen/Qwen2.5-Coder-14B",
),
"unsloth/Qwen2.5-Coder-32B-bnb-4bit" : (
"unsloth/Qwen2.5-Coder-32B",
"Qwen/Qwen2.5-Coder-32B",
),
"unsloth/Qwen2.5-Coder-0.5B-Instruct-bnb-4bit" : (
"unsloth/Qwen2.5-Coder-Instruct-0.5B",
"Qwen/Qwen2.5-Coder-Instruct-0.5B",
),
"unsloth/Qwen2.5-Coder-1.5B-Instruct-bnb-4bit" : (
"unsloth/Qwen2.5-Coder-Instruct-1.5B",
"Qwen/Qwen2.5-Coder-Instruct-1.5B",
),
"unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit" : (
"unsloth/Qwen2.5-Coder-3B-Instruct",
"Qwen/Qwen2.5-Coder-3B-Instruct",
),
"unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit" : (
"unsloth/Qwen2.5-Coder-7B-Instruct",
"Qwen/Qwen2.5-Coder-7B-Instruct",
),
"unsloth/Qwen2.5-Coder-14B-Instruct-bnb-4bit" : (
"unsloth/Qwen2.5-Coder-14B-Instruct",
"Qwen/Qwen2.5-Coder-14B-Instruct",
),
"unsloth/Qwen2.5-Coder-32B-Instruct-bnb-4bit" : (
"unsloth/Qwen2.5-Coder-32B-Instruct",
"Qwen/Qwen2.5-Coder-32B-Instruct",
),
"unsloth/Llama-3.2-1B-bnb-4bit" : (
"unsloth/Llama-3.2-1B",
"meta-llama/Llama-3.2-1B",