commit 70d5fd47ad0f56a0392e7e50407d6e12e3643285 Author: ModelHub XC Date: Sat Apr 25 03:05:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: itpossible/ClimateChat Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..eb67b19 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.lz4 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*.jsonl filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +# Audio files - uncompressed +*.pcm filter=lfs diff=lfs merge=lfs -text +*.sam filter=lfs diff=lfs merge=lfs -text +*.raw filter=lfs diff=lfs merge=lfs -text +# Audio files - compressed +*.aac filter=lfs diff=lfs merge=lfs -text +*.flac filter=lfs diff=lfs merge=lfs -text +*.mp3 filter=lfs diff=lfs merge=lfs -text +*.ogg filter=lfs diff=lfs merge=lfs -text +*.wav filter=lfs diff=lfs merge=lfs -text +# Image files - uncompressed +*.bmp filter=lfs diff=lfs merge=lfs -text +*.gif filter=lfs diff=lfs merge=lfs -text +*.png filter=lfs diff=lfs merge=lfs -text +*.tiff filter=lfs diff=lfs merge=lfs -text +# JSON files - uncompressed +*.json filter=lfs diff=lfs merge=lfs -text +*.log +# Image files - compressed +*.jpg filter=lfs diff=lfs merge=lfs -text +*.jpeg filter=lfs diff=lfs merge=lfs -text +*.webp filter=lfs diff=lfs merge=lfs -text +*.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d1888c7 --- /dev/null +++ b/README.md @@ -0,0 +1,37 @@ +--- +license: apache-2.0 +base_model: itpossible/JiuZhou-base +pipeline_tag: text-generation +library_name: transformers +tags: +- text-generation-inference +- inference endpoints +--- + +## 🎉 News +- **[2025-05]** Paper [*TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks*](https://arxiv.org/abs/2506.12473) has been accepted by the top NLP conference *ACL*. [Model Download](https://huggingface.co/itpossible/TagGenerator). +- **[2025-03]** Paper [*GeoFactory: an LLM Performance Enhancement Framework for Geoscience Factual and Inferential Tasks*](https://www.tandfonline.com/doi/full/10.1080/20964471.2025.2506291) has been accepted by the journal *Big Earth Data*. [Data Download](https://huggingface.co/datasets/itpossible/WikiRAG). +- **[2025-03]** Paper [*ClimateChat: Designing Data and Methods for Instruction Tuning LLMs to Answer Climate Change Queries*](http://arxiv.org/abs/2506.13796) has been accepted by the International Conference on Learning Representations (*ICLR*). [Model Download](https://huggingface.co/itpossible/ClimateChat). +- **[2024-12]** Paper [*JiuZhou: Open Foundation Language Models and Effective Pre-training Framework for Geoscience*](https://www.tandfonline.com/doi/full/10.1080/17538947.2025.2449708) has been accepted by the *International Journal of Digital Earth*. [Model Introduction](https://deepwiki.com/THU-ESIS/JiuZhou). [Project Repository](https://github.com/THU-ESIS/JiuZhou). +- **[2024-09]** Released chat model [ClimateChat](https://huggingface.co/itpossible/ClimateChat). +- **[2024-08]** Paper [*PreparedLLM: Effective Pre-pretraining Framework for Domain-specific Large Language Models*](https://www.tandfonline.com/doi/full/10.1080/20964471.2024.2396159) has been accepted by the journal *Big Earth Data*. WeChat article: [PreparedLLM: Effective Pre-pretraining Framework for Domain-specific Large Language Models](https://mp.weixin.qq.com/s/ugJQ9tbp6Y87xA3TOWteqw). [Model Download](https://huggingface.co/itpossible/Prepared-Llama). +- **[2024-08]** Released chat model [Chinese-Mistral-7B-Instruct-v0.2](https://huggingface.co/itpossible/Chinese-Mistral-7B-Instruct-v0.2), featuring significantly improved language understanding and multi-turn conversation capabilities. +- **[2024-06]** Released chat model [JiuZhou-Instruct-v0.2](https://huggingface.co/itpossible/JiuZhou-Instruct-v0.2), with significantly enhanced language understanding and multi-turn conversation capabilities. +- **[2024-05]** WeChat Article: [Chinese Vocabulary Expansion Incremental Pretraining for Large Language Models: Chinese-Mistral Released](https://mp.weixin.qq.com/s/PMQmRCZMWosWMfgKRBjLlQ). +- **[2024-03]** Released base model [Chinese-Mistral-7B-v0.1](https://huggingface.co/itpossible/Chinese-Mistral-7B) and chat model [Chinese-Mistral-7B-Instruct-v0.1](https://huggingface.co/itpossible/Chinese-Mistral-7B-Instruct-v0.1). [Model Introduction](https://deepwiki.com/THU-ESIS/Chinese-Mistral). [Project Repository](https://huggingface.co/itpossible/Chinese-Mistral). +- **[2024-03]** Released JiuZhou's base version [JiuZhou-base](https://huggingface.co/itpossible/JiuZhou-base), instruct version [JiuZhou-instruct-v0.1](https://huggingface.co/itpossible/JiuZhou-Instruct-v0.1), and [intermediate checkpoints](https://huggingface.co/itpossible). [Model Introduction](https://deepwiki.com/THU-ESIS/JiuZhou). [Project Repository](https://github.com/THU-ESIS/JiuZhou). +- **[2024-01]** Completed training of Chinese-Mistral and JiuZhou, and commenced model evaluation. + +## Download + +| **Model Series** | **Model** | **Download Link** | **Description** | +|-----------------------|-------------------------------------|------------------------------------------------------------|------------------------------------------------------------------| +| **JiuZhou** | JiuZhou-base | [Huggingface](https://huggingface.co/itpossible/JiuZhou-base) | Base model (Rich in geoscience knowledge) | +| **JiuZhou** | JiuZhou-Instruct-v0.1 | [Huggingface](https://huggingface.co/itpossible/Chinese-Mistral-7B-Instruct-v0.1) | Instruct model (Instruction alignment caused a loss of some geoscience knowledge, but it has instruction-following ability)
LoRA fine-tuned on Alpaca_GPT4 in both Chinese and English and GeoSignal | +| **JiuZhou** | JiuZhou-Instruct-v0.2 | [HuggingFace](https://huggingface.co/itpossible/Chinese-Mistral-7B-Instruct-v0.2)
[Wisemodel](https://wisemodel.cn/models/itpossible/Chinese-Mistral-7B-Instruct-v0.2) | Instruct model (Instruction alignment caused a loss of some geoscience knowledge, but it has instruction-following ability)
Fine-tuned with high-quality general instruction data | +| **ClimateChat** | ClimateChat | [HuggingFace](https://huggingface.co/itpossible/ClimateChat)
[Wisemodel](https://wisemodel.cn/models/itpossible/ClimateChat) | Instruct model
Fine-tuned on JiuZhou-base for instruction following | +| **Chinese-Mistral** | Chinese-Mistral-7B | [HuggingFace](https://huggingface.co/itpossible/Chinese-Mistral-7B-v0.1)
[Wisemodel](https://wisemodel.cn/models/itpossible/Chinese-Mistral-7B-v0.1)
[ModelScope](https://www.modelscope.cn/models/itpossible/Chinese-Mistral-7B-v0.1) | Base model | +| **Chinese-Mistral** | Chinese-Mistral-7B-Instruct-v0.1 | [HuggingFace](https://huggingface.co/itpossible/Chinese-Mistral-7B-Instruct-v0.1)
[Wisemodel](https://wisemodel.cn/models/itpossible/Chinese-Mistral-7B-Instruct-v0.1)
[ModelScope](https://www.modelscope.cn/models/itpossible/Chinese-Mistral-7B-Instruct-v0.1) | Instruct model
LoRA fine-tuned with Alpaca_GPT4 in both Chinese and English | +| **Chinese-Mistral** | Chinese-Mistral-7B-Instruct-v0.2 | [HuggingFace](https://huggingface.co/itpossible/Chinese-Mistral-7B-Instruct-v0.2)
[Wisemodel](https://wisemodel.cn/models/itpossible/Chinese-Mistral-7B-Instruct-v0.2) | Instruct model
LoRA fine-tuned with a million high-quality instructions | +| **PreparedLLM** | Prepared-Llama | [Huggingface](https://huggingface.co/itpossible/Prepared-Llama)
[Wisemodel](https://wisemodel.cn/models/itpossible/PREPARED-Llama) | Base model
Continual pretraining with a small number of geoscience data
Recommended to use JiuZhou | + diff --git a/config.json b/config.json new file mode 100644 index 0000000..ce441c9 --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9301c99672c7242ff542b7b197740208a0d58548d6ebc7d6609b49fcb119d9b9 +size 594 diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..86b3906 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daeebe28ce3b1af3fcd69bbd039b838616198b8a2cfc00a622130ef08a01972d +size 111 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..0903bf5 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07781e94acade4e01f2c17bb2f81bf701cbb95be9109f370a7d5bc51e0b46f1a +size 3895582632 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..3436fd7 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b515702ea7d425f7e8b448a8521dbab32dff6e13bf9ad13e6ca1f75142cef47 +size 3926025424 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..2f54513 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3343eec21e0fbc0aaf638219aa2d8684e36e42c755ea8ac00ad582321e73fef +size 3926025440 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..3875840 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a165ae4715aa30af72985ee54845854878983158225cba261a6e48a90444bac +size 3258055368 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..0c9ba60 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fe131a2500fbfc6162473fe4a7e340364d917e3160e6cd2b2c35e4df01baee1 +size 23950 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..38d37ea --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82d96d7a9e6ced037f12394b7ea6a5b02e6ca87e0d11edaa8d60d9be857ce7db +size 551 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..3f0e7f6 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:561d3879ed270f6b6f8e1ff5411eac1c315935e5f0b2318ca92ed6d1531c07f7 +size 991499 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..b212ff0 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ccdc0ce8661187d40828ae6b8857b3c244f15cc4eb56598f3e7eaa1176235b9 +size 1486