初始化项目，由ModelHub XC社区提供模型

Model: unsloth/OLMo-2-0425-1B-Instruct-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,47 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

OLMo-2-0425-1B-Instruct-BF16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f959a2bbf86eaae11ebc0376b3f5e8a5fda2b67a89010ce7fd1d5ae210b268d
+size 2973651936

OLMo-2-0425-1B-Instruct-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7e531451ab91004c655a41e157f7d0c3b82f497987a706b41dfc0cad686247e
+size 892261600

OLMo-2-0425-1B-Instruct-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7b28a2e471d7a9d44d2b0bc848292facd19a0e0a7408ceb3b775d6ac116827f
+size 858707168

OLMo-2-0425-1B-Instruct-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6534fb78967e33285d5bb0b317c8481edbb6df81114279ed2112c6d990c9947d
+size 633328864

OLMo-2-0425-1B-Instruct-Q2_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7627a89cd20e94fde24e54b81a3ef459fda9de9a21663b9ac12782212558dfc5
+size 681497824

OLMo-2-0425-1B-Instruct-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0476aa2f9783d4e66e660b3161a33a8309d52ef458f8c33a37c3baa856444c9e
+size 778982624

OLMo-2-0425-1B-Instruct-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ab87b77efae69ea03541d7d103a4b79a672139ab782013483b8c744d45b721
+size 722359520

OLMo-2-0425-1B-Instruct-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa3c76929d6e10c36596468af41f57c2a4b42db8e75ed030fbf9addac7be463
+size 894358752

OLMo-2-0425-1B-Instruct-Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dfab68e7256d13ba8f87733d7785757cec4d5c0185a382d26a470734450ad44
+size 972215520

OLMo-2-0425-1B-Instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54b26d5388274d038608b42fdf1afb7544d2e51a0fac4d1abf4a8c54a813fbbc
+size 935515360

OLMo-2-0425-1B-Instruct-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83e7842cf3ebff4e9afcf8da3dcb075b29d5d35d903d5c139cae0078a6118a9a
+size 1074451680

OLMo-2-0425-1B-Instruct-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27e82b7d557db47f38d90a08e69638ec252ccd9cd178ff6b55de9308b958faa9
+size 1222071520

OLMo-2-0425-1B-Instruct-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00bcc207f9a12df065d2df7ace8042a07cc6463324533251d1bc36f7ff93ac5a
+size 1581667552

OLMo-2-0425-1B-Instruct-UD-IQ1_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:340cf2523701a967c8236723c27c4342257d7420f193d289619bb4cfc46777d7
+size 535647456

OLMo-2-0425-1B-Instruct-UD-IQ1_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da3c8405462219ef0ec7eab83cb1250fb05ad3e15036b09a4308d62616fcb3b
+size 517428448

OLMo-2-0425-1B-Instruct-UD-IQ2_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b26c8bba8fcee57ad9343efb9cbee5e1a85d5573797a74a70f2880f834629b32
+size 641225952

OLMo-2-0425-1B-Instruct-UD-IQ2_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c103cb3ecf2afce075fd8c33a6f91c2775e10ce17586f0b03bfe56b90ae6f27e
+size 565859552

OLMo-2-0425-1B-Instruct-UD-IQ3_XXS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e1e0688ca856813820e4ef5cd4c494828d5048d5d43a6c24897848e943ea6a7
+size 681530592

OLMo-2-0425-1B-Instruct-UD-Q2_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78be651ee5268a3a9044b3ea1ec8db5efa738ccd92f02a41ea2439cf52b3dd48
+size 709186784

OLMo-2-0425-1B-Instruct-UD-Q3_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:152262f25b7d45bdc6df9a7ba0aa006783b06b8b59c060d333552beec679de33
+size 841503968

OLMo-2-0425-1B-Instruct-UD-Q4_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17fa14fdf1b4952d92a959c5d1549d4dc38dd45a82c71dbd854ce289f0d418fa
+size 967202016

OLMo-2-0425-1B-Instruct-UD-Q5_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53e7e9fca05102d5e7456681f840e88eeedb2e413321748a272d44312f1f6a93
+size 1075533024

OLMo-2-0425-1B-Instruct-UD-Q6_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3c540944389bdf66a9bae9b331768b9718ebec8a796f98f19c97f1daef25478
+size 1451644128

OLMo-2-0425-1B-Instruct-UD-Q8_K_XL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95bfa6968928e1fe3c2f3281bf2c389ce9f7156283e91fbc71c8044286b93e7c
+size 2242270432

README.md

@@ -0,0 +1,130 @@
+---
+tags:
+- unsloth
+license: apache-2.0
+language:
+- en
+datasets:
+- allenai/RLVR-MATH
+base_model:
+- allenai/OLMo-2-0425-1B-Instruct
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+<img alt="OLMo Logo" src="https://huggingface.co/datasets/allenai/blog-images/resolve/main/olmo2/olmo.png" width="242px">
+
+OLMo 2 1B Instruct April 2025 is post-trained variant of the [allenai/OLMo-2-0425-1B-RLVR1](https://huggingface.co/allenai/OLMo-2-0425-1B-RLVR1) model, which has undergone supervised finetuning on an OLMo-specific variant of the [Tülu 3 dataset](https://huggingface.co/datasets/allenai/tulu-3-sft-olmo-2-mixture-0225), further DPO training on [this dataset](https://huggingface.co/datasets/allenai/olmo-2-0425-1b-preference-mix), and final RLVR training on [this dataset](https://huggingface.co/datasets/allenai/RLVR-MATH).
+Tülu 3 is designed for state-of-the-art performance on a diversity of tasks in addition to chat, such as MATH, GSM8K, and IFEval.
+Check out the [OLMo 2 paper](https://arxiv.org/abs/2501.00656) or [Tülu 3 paper](https://arxiv.org/abs/2411.15124) for more details!
+
+OLMo is a series of **O**pen **L**anguage **Mo**dels designed to enable the science of language models. 
+These models are trained on the Dolma dataset. We are releasing all code, checkpoints, logs, and associated training details. 
+
+
+## Model description
+
+- **Model type:** A model trained on a mix of publicly available, synthetic and human-created datasets.
+- **Language(s) (NLP):** Primarily English
+- **License:** Apache 2.0
+- **Finetuned from model:** allenai/OLMo-2-0425-1B-RLVR1
+
+### Model Sources
+
+- **Project Page:** https://allenai.org/olmo
+- **Repositories:** 
+    - Core repo (training, inference, fine-tuning etc.): https://github.com/allenai/OLMo-core
+    - Evaluation code: https://github.com/allenai/olmes
+    - Further fine-tuning code: https://github.com/allenai/open-instruct
+- **Paper:** https://arxiv.org/abs/2501.00656
+- **Demo:** https://playground.allenai.org/
+
+## Installation
+
+OLMo 2 1B is supported in transformers v4.48 or higher:
+```bash
+pip install transformers>=4.48
+```
+
+If using vLLM, you will need to install from the main branch until v0.7.4 is released. Please
+
+## Using the model
+
+### Loading with HuggingFace
+
+To load the model with HuggingFace, use the following snippet:
+```
+from transformers import AutoModelForCausalLM
+
+olmo_model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-0425-1B-Instruct")
+```
+
+### Chat template
+
+*NOTE: This is different than previous OLMo 2 and Tülu 3 models due to a minor change in configuration. It does NOT have the bos token before the rest. Our other models have <|endoftext|> at the beginning of the chat template.*
+
+The chat template for our models is formatted as:
+```
+<|user|>
+How are you doing?
+<|assistant|>
+I'm just a computer program, so I don't have feelings, but I'm functioning as expected. How can I assist you today?<|endoftext|>
+```
+Or with new lines expanded:
+```
+<|user|>
+How are you doing?
+<|assistant|>
+I'm just a computer program, so I don't have feelings, but I'm functioning as expected. How can I assist you today?<|endoftext|>
+```
+It is embedded within the tokenizer as well, for `tokenizer.apply_chat_template`.
+
+### Intermediate Checkpoints
+
+To facilitate research on RL finetuning, we have released our intermediate checkpoints during the model's RLVR training.
+The model weights are saved every 20 training steps, and can be accessible in the revisions of the HuggingFace repository.
+For example, you can load with:
+```
+olmo_model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-0425-1B-Instruct", revision="step_200")
+```
+
+### Bias, Risks, and Limitations
+
+The OLMo-2 models have limited safety training, but are not deployed automatically with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).
+
+
+## Performance
+
+| Model | Average | AlpacaEval 2 LC | BBH | DROP | GSM8K | IFEval | MATH | MMLU | Safety | PopQA | TruthQA |
+|-------|---------|-----------------|-----|------|-------|--------|------|------|--------|-------|---------|
+| **OLMo 1B 0724** | 24.4 | 2.4 | 29.9 | 27.9 | 10.8 | 25.3 | 2.2 | 36.6 | 52.0 | 12.1 | 44.3 |
+| **SmolLM2 1.7B** | 34.2 | 5.8 | 39.8 | 30.9 | 45.3 | 51.6 | 20.3 | 34.3 | 52.4 | 16.4 | 45.3 |
+| **Gemma 3 1B** | 38.3 | 20.4 | 39.4 | 25.1 | 35.0 | 60.6 | 40.3 | 38.9 | 70.2 | 9.6 | 43.8 |
+| **Llama 3.1 1B** | 39.3 | 10.1 | 40.2 | 32.2 | 45.4 | 54.0 | 21.6 | 46.7 | 87.2 | 13.8 | 41.5 |
+| **Qwen 2.5 1.5B** | 41.7 | 7.4 | 45.8 | 13.4 | 66.2 | 44.2 | 40.6 | 59.7 | 77.6 | 15.5 | 46.5 |
+| **---** |  |  |  |  |  |  |  |  |  |  |  |
+| **OLMo 2 1B SFT** | 36.9 | 2.4 | 32.8 | 33.8 | 52.1 | 50.5 | 13.2 | 36.4 | 93.2 | 12.7 | 42.1 |
+| **OLMo 2 1B DPO** | 40.6 | 9.5 | 33.0 | 34.5 | 59.0 | 67.1 | 14.1 | 39.9 | 89.9 | 12.3 | 46.4 |
+| **OLMo 2 1B** | 42.7 | 9.1 | 35.0 | 34.6 | 68.3 | 70.1 | 20.7 | 40.0 | 87.6 | 12.9 | 48.7 |
+
+
+
+## License and use
+
+OLMo 2 is licensed under the Apache 2.0 license.
+OLMo 2 is intended for research and educational use.
+For more information, please see our [Responsible Use Guidelines](https://allenai.org/responsible-use).
+
+## Citation
+
+```bibtex
+@article{olmo20242olmo2furious,
+      title={2 OLMo 2 Furious}, 
+      author={Team OLMo and Pete Walsh and Luca Soldaini and Dirk Groeneveld and Kyle Lo and Shane Arora and Akshita Bhagia and Yuling Gu and Shengyi Huang and Matt Jordan and Nathan Lambert and Dustin Schwenk and Oyvind Tafjord and Taira Anderson and David Atkinson and Faeze Brahman and Christopher Clark and Pradeep Dasigi and Nouha Dziri and Michal Guerquin and Hamish Ivison and Pang Wei Koh and Jiacheng Liu and Saumya Malik and William Merrill and Lester James V. Miranda and Jacob Morrison and Tyler Murray and Crystal Nam and Valentina Pyatkin and Aman Rangapur and Michael Schmitz and Sam Skjonsberg and David Wadden and Christopher Wilhelm and Michael Wilson and Luke Zettlemoyer and Ali Farhadi and Noah A. Smith and Hannaneh Hajishirzi},
+      year={2024},
+      eprint={2501.00656},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2501.00656}, 
+}
+```

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Olmo2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "model_type": "olmo2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 16,
+  "pad_token_id": 100277,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.0.dev0",
+  "unsloth_fixed": true,
+  "use_cache": false,
+  "vocab_size": 100352
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}