AMD-OLMo-1B-IT

AMD-OLMo-1B-IT

Fine-tune of AMD's 1B OLMo, optmized for instruction-following and creative writing.

Very confident personality.

Eager to use the <|im_end|> , <|im_start|> padding tokens.

I generally recommend a Q4_K_M quantization.

How to stop at the <|im_end|> special token (llama.cpp):

llama-server -m insert_model_here -ngl 99 -r "<|im_end|>"

Finetuned on a random set of 12000 rows from shibing624/sharegpt_gpt4 (2 epochs, 0.0002 learning rate)

License

Copyright (c) 2018-2024 Advanced Micro Devices, Inc. All Rights Reserved.

Copyright (c) 2026 aiuser3993

Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License at

http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions and limitations under the License.