commit 0ee10d25a43ac20519e33090af9848e56e85b569 Author: ModelHub XC Date: Wed May 27 01:12:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: qwp4w3hyb/Yi-1.5-9B-Chat-iMat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dee78e3 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,55 @@ +*.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 +*.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 +*.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 +*tfevents* filter=lfs diff=lfs merge=lfs -text +imat-bf16-gmerged.dat filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-bf16.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-9b-chat-imat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..006a9fd --- /dev/null +++ b/README.md @@ -0,0 +1,116 @@ +--- +license: apache-2.0 +pipeline_tag: text-generation +base_model: 01-ai/Yi-1.5-9B-Chat +tags: +- yi +- 01-ai +- instruct +- finetune +- chatml +- gguf +- imatrix +- importance matrix +model-index: +- name: 01-ai/Yi-1.5-9B-Chat-iMat-GGUF + results: [] +--- + +# Quant Infos + +- quants done with an importance matrix for improved quantization loss +- ggufs & imatrix generated from bf16 for "optimal" accuracy loss +- Wide coverage of different gguf quant types from Q\_8\_0 down to IQ1\_S +- Quantized with [llama.cpp](https://github.com/ggerganov/llama.cpp) commit [dc685be46622a8fabfd57cfa804237c8f15679b8](https://github.com/ggerganov/llama.cpp/commit/dc685be46622a8fabfd57cfa804237c8f15679b8) (master as of 2024-05-12) +- Imatrix generated with [this](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) multi-purpose dataset. + ``` + ./imatrix -c 512 -m $model_name-f16.gguf -f $llama_cpp_path/groups_merged.txt -o $out_path/imat-f16-gmerged.dat + ``` + +# Original Model Card: + +
+ + + + + +
+ +

+ 🐙 GitHub • + 👾 Discord • + 🐤 Twitter • + 💬 WeChat +
+ 📝 Paper • + 🙌 FAQ • + 📗 Learning Hub +

+ +# Intro + +Yi-1.5 is an upgraded version of Yi. It is continuously pre-trained on Yi with a high-quality corpus of 500B tokens and fine-tuned on 3M diverse fine-tuning samples. + +Compared with Yi, Yi-1.5 delivers stronger performance in coding, math, reasoning, and instruction-following capability, while still maintaining excellent capabilities in language understanding, commonsense reasoning, and reading comprehension. + +
+ +Model | Context Length | Pre-trained Tokens +| :------------: | :------------: | :------------: | +| Yi-1.5 | 4K | 3.6T + +
+ +# Models + +- Chat models + +
+ + | Name | Download | + | --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- | + | Yi-1.5-34B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) | + | Yi-1.5-9B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) | + | Yi-1.5-6B-Chat | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) | + +
+ +- Base models + +
+ + | Name | Download | + | ---------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- | + | Yi-1.5-34B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) | + | Yi-1.5-9B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) | + | Yi-1.5-6B | • [🤗 Hugging Face](https://huggingface.co/collections/01-ai/yi-15-2024-05-663f3ecab5f815a3eaca7ca8) • [🤖 ModelScope](https://www.modelscope.cn/organization/01ai) | + +
+ +# Benchmarks + +- Chat models + + Yi-1.5-34B-Chat is on par with or excels beyond larger models in most benchmarks. + + ![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/KcsJ9Oc1VnEmfCDEJc5cd.png) + + Yi-1.5-9B-Chat is the top performer among similarly sized open-source models. + + ![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/xf6pLg5jqRCwjlh6m3t6_.png) + +- Base models + + Yi-1.5-34B is on par with or excels beyond larger models in some benchmarks. + + ![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/BwU7QM-03dZvZzwdIE1xY.png) + + Yi-1.5-9B is the top performer among similarly sized open-source models. + + ![image/png](https://cdn-uploads.huggingface.co/production/uploads/656d9adce8bf55919aca7c3f/y-EYSYPT-3aWLJ0x8R94F.png) + +# Quick Start + +For getting up and running with Yi-1.5 models quickly, see [README](https://github.com/01-ai/Yi-1.5). + diff --git a/config.json b/config.json new file mode 100644 index 0000000..f41fec6 --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 48, + "num_key_value_heads": 4, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.40.0", + "use_cache": false, + "vocab_size": 64000 +} diff --git a/imat-bf16-gmerged.dat b/imat-bf16-gmerged.dat new file mode 100644 index 0000000..c980ab2 --- /dev/null +++ b/imat-bf16-gmerged.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01d42f1d802b1c4273653ea9f568093c649b0d772c58ac25ddc92fa6b7ac1aa6 +size 6843305 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..74f5a74 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..5d5dfd8 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,53 @@ +{ + "add_bos_token": false, + "add_eos_token": false, + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "7": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|startoftext|>", + "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "legacy": true, + "model_max_length": 4096, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "split_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/yi-1.5-9b-chat-bf16.gguf b/yi-1.5-9b-chat-bf16.gguf new file mode 100644 index 0000000..ee79a06 --- /dev/null +++ b/yi-1.5-9b-chat-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e52b0478e2c130787a83f115c5f87837924be91ccb5ea383977b4d9cc9fdb01f +size 17661112576 diff --git a/yi-1.5-9b-chat-imat-IQ1_S.gguf b/yi-1.5-9b-chat-imat-IQ1_S.gguf new file mode 100644 index 0000000..c65393a --- /dev/null +++ b/yi-1.5-9b-chat-imat-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29249d91a2b62565e59adb36f1119b92cfdc8ba82fd42f968b177b69a7428b08 +size 2014573088 diff --git a/yi-1.5-9b-chat-imat-IQ2_M.gguf b/yi-1.5-9b-chat-imat-IQ2_M.gguf new file mode 100644 index 0000000..dca48d9 --- /dev/null +++ b/yi-1.5-9b-chat-imat-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3366619f7f2b3889772bc32c17e64a567a8efc1525606cc6e1275615dc50130 +size 3098112544 diff --git a/yi-1.5-9b-chat-imat-IQ2_S.gguf b/yi-1.5-9b-chat-imat-IQ2_S.gguf new file mode 100644 index 0000000..9f19fa5 --- /dev/null +++ b/yi-1.5-9b-chat-imat-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a858702b2b3a38d64bb3f94121cd9cf415a6a3775a7b94c43a194deab3b10c6 +size 2875355680 diff --git a/yi-1.5-9b-chat-imat-IQ2_XS.gguf b/yi-1.5-9b-chat-imat-IQ2_XS.gguf new file mode 100644 index 0000000..f327135 --- /dev/null +++ b/yi-1.5-9b-chat-imat-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b8f1c48084e66b3439b48be855c1bb1318820e3a96b43d5728673d7bf83ecb +size 2708009504 diff --git a/yi-1.5-9b-chat-imat-IQ2_XXS.gguf b/yi-1.5-9b-chat-imat-IQ2_XXS.gguf new file mode 100644 index 0000000..9189206 --- /dev/null +++ b/yi-1.5-9b-chat-imat-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b7c8e730d27a18a733d3f21a9bea79c0df7ceca9a9cfb9ccc7b460a697af191 +size 2460086816 diff --git a/yi-1.5-9b-chat-imat-IQ3_M.gguf b/yi-1.5-9b-chat-imat-IQ3_M.gguf new file mode 100644 index 0000000..b381a3d --- /dev/null +++ b/yi-1.5-9b-chat-imat-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:618cf53c956809a288c687b350ce704ca31a86f6bb9f636fd22e5cbe192b4bc2 +size 4055462432 diff --git a/yi-1.5-9b-chat-imat-IQ3_S.gguf b/yi-1.5-9b-chat-imat-IQ3_S.gguf new file mode 100644 index 0000000..2754350 --- /dev/null +++ b/yi-1.5-9b-chat-imat-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd104b004844eddf532c1f1cf0c8735773f92dcb96c82321a347f668fab19316 +size 3912577568 diff --git a/yi-1.5-9b-chat-imat-IQ3_XS.gguf b/yi-1.5-9b-chat-imat-IQ3_XS.gguf new file mode 100644 index 0000000..8c00490 --- /dev/null +++ b/yi-1.5-9b-chat-imat-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f419f27d87e5ac07e0c3d0b1b1f628d60f63b5fb6e3489b17a199c3eec1aa7d0 +size 3717935648 diff --git a/yi-1.5-9b-chat-imat-IQ3_XXS.gguf b/yi-1.5-9b-chat-imat-IQ3_XXS.gguf new file mode 100644 index 0000000..9638557 --- /dev/null +++ b/yi-1.5-9b-chat-imat-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb0b612fa215f5dee01a2833e733582b5a26cef5ed90cb0699689ce095962694 +size 3474321952 diff --git a/yi-1.5-9b-chat-imat-IQ4_NL.gguf b/yi-1.5-9b-chat-imat-IQ4_NL.gguf new file mode 100644 index 0000000..cd03a82 --- /dev/null +++ b/yi-1.5-9b-chat-imat-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1af5b4f21cf8341c7c086a768816e82d3bd67dd1e2717bebfd4b973b1b20d785 +size 5049578016 diff --git a/yi-1.5-9b-chat-imat-IQ4_XS.gguf b/yi-1.5-9b-chat-imat-IQ4_XS.gguf new file mode 100644 index 0000000..34dfbce --- /dev/null +++ b/yi-1.5-9b-chat-imat-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c3966a4d7cee778aaf6f7308ced4512f6af922fcb3b5720e0f7bea5ac12e1b7 +size 4785009184 diff --git a/yi-1.5-9b-chat-imat-Q4_0.gguf b/yi-1.5-9b-chat-imat-Q4_0.gguf new file mode 100644 index 0000000..5bd1623 --- /dev/null +++ b/yi-1.5-9b-chat-imat-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2756c1cf961624a0dbc9b1716feb0d4cdfcde60f55d14e298f1fc16aaa5711ac +size 5053903392 diff --git a/yi-1.5-9b-chat-imat-Q4_K_M.gguf b/yi-1.5-9b-chat-imat-Q4_K_M.gguf new file mode 100644 index 0000000..ad5eeb7 --- /dev/null +++ b/yi-1.5-9b-chat-imat-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7cc5223ae5a9b0b3ee0d6dd8e9caf2d4daf507eaa50cff4f692ea869bbcf6a +size 5328957984 diff --git a/yi-1.5-9b-chat-imat-Q4_K_S.gguf b/yi-1.5-9b-chat-imat-Q4_K_S.gguf new file mode 100644 index 0000000..9c4f1d9 --- /dev/null +++ b/yi-1.5-9b-chat-imat-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52b0395ab19b78ceae958ae7f9c6fff3087780cc4ef942f31c3937fb02cc0f80 +size 5071860256 diff --git a/yi-1.5-9b-chat-imat-Q5_K_M.gguf b/yi-1.5-9b-chat-imat-Q5_K_M.gguf new file mode 100644 index 0000000..c889b7e --- /dev/null +++ b/yi-1.5-9b-chat-imat-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7684de17efcb3d502f1a6bffbf76f6bbb46ea6a2cf074c85863f999e43d037dd +size 6258258464 diff --git a/yi-1.5-9b-chat-imat-Q5_K_S.gguf b/yi-1.5-9b-chat-imat-Q5_K_S.gguf new file mode 100644 index 0000000..46c0ba2 --- /dev/null +++ b/yi-1.5-9b-chat-imat-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c943666efb6a4485af01101d59ef90228e3ecb51e00d62ce572298dbc2ba1007 +size 6107853344 diff --git a/yi-1.5-9b-chat-imat-Q6_K.gguf b/yi-1.5-9b-chat-imat-Q6_K.gguf new file mode 100644 index 0000000..1185fba --- /dev/null +++ b/yi-1.5-9b-chat-imat-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e3b7c25b1589e47439ec5a3eed5760b473c0c9b997f620f8673d8b00d0ec1fe +size 7245640224 diff --git a/yi-1.5-9b-chat-imat-Q8_0.gguf b/yi-1.5-9b-chat-imat-Q8_0.gguf new file mode 100644 index 0000000..df8e8e8 --- /dev/null +++ b/yi-1.5-9b-chat-imat-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b2cb4a5c53d51c95dde5fdbd15939f56537f61b8e8a283a1cde6a76539af1d7 +size 9383916064