commit af085331ae74e473789175bf8f1690e289616dc9 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-1.5-6B-Chat-iMat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f85eda2 --- /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-1.5-6b-chat-bf16.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-chat-imat-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-chat-imat-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-chat-imat-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-chat-imat-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-chat-imat-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-chat-imat-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-chat-imat-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-chat-imat-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-chat-imat-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-chat-imat-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-chat-imat-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-chat-imat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-chat-imat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-chat-imat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-chat-imat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-chat-imat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-chat-imat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +yi-1.5-6b-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..4978782 --- /dev/null +++ b/README.md @@ -0,0 +1,116 @@ +--- +license: apache-2.0 +pipeline_tag: text-generation +base_model: 01-ai/Yi-1.5-6B-Chat +tags: +- yi +- 01-ai +- instruct +- finetune +- chatml +- gguf +- imatrix +- importance matrix +model-index: +- name: 01-ai/Yi-1.5-6B-Chat-iMat-GGUF + results: [] +--- + +# Quant Infos + +- quants done with an importance matrix for improved quantization loss +- gguf & imatrix generated from bf16 for "optimal" accuracy loss (some say this is snake oil, but it can't hurt) +- 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..9e16785 --- /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": 32, + "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..5acbd67 --- /dev/null +++ b/imat-bf16-gmerged.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3ad9c8d573ea4bddc0212e45e64f9738f996f4b089fdd0bfe2f7153e655c481 +size 4562201 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-1.5-6b-chat-bf16.gguf b/yi-1.5-6b-chat-bf16.gguf new file mode 100644 index 0000000..1df8a85 --- /dev/null +++ b/yi-1.5-6b-chat-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a79bd54ce0ab813fb54da80aa1ed5e1bf72405b3268c44553b099bba28b93dc4 +size 12124098400 diff --git a/yi-1.5-6b-chat-imat-IQ1_S.gguf b/yi-1.5-6b-chat-imat-IQ1_S.gguf new file mode 100644 index 0000000..6431dc0 --- /dev/null +++ b/yi-1.5-6b-chat-imat-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ece6443521972c39948ed1e2c4bbf9590387fc19d3337b84dd488431fe0aa555 +size 1432293504 diff --git a/yi-1.5-6b-chat-imat-IQ2_M.gguf b/yi-1.5-6b-chat-imat-IQ2_M.gguf new file mode 100644 index 0000000..2adca34 --- /dev/null +++ b/yi-1.5-6b-chat-imat-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab487dbbb99499027ce08ce124ddc722f95a2660fa975bd6da49a181f7853f8b +size 2163527808 diff --git a/yi-1.5-6b-chat-imat-IQ2_S.gguf b/yi-1.5-6b-chat-imat-IQ2_S.gguf new file mode 100644 index 0000000..4a2370e --- /dev/null +++ b/yi-1.5-6b-chat-imat-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c81cba1f56896b77fe8980208b76d30c39891ddc5a3f41eee4ebaddb79a791a +size 2015023232 diff --git a/yi-1.5-6b-chat-imat-IQ2_XS.gguf b/yi-1.5-6b-chat-imat-IQ2_XS.gguf new file mode 100644 index 0000000..c7ab76d --- /dev/null +++ b/yi-1.5-6b-chat-imat-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ed5956bcfd4987230d745ff14c7af7e5f29a41e5a96be621b390ddb86ce2d34 +size 1894584448 diff --git a/yi-1.5-6b-chat-imat-IQ2_XXS.gguf b/yi-1.5-6b-chat-imat-IQ2_XXS.gguf new file mode 100644 index 0000000..dc807f7 --- /dev/null +++ b/yi-1.5-6b-chat-imat-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a0ae9ca0459383568db95d8abf97ef684409c4bba499d165af58191fe28d958 +size 1729302656 diff --git a/yi-1.5-6b-chat-imat-IQ3_M.gguf b/yi-1.5-6b-chat-imat-IQ3_M.gguf new file mode 100644 index 0000000..3c499b1 --- /dev/null +++ b/yi-1.5-6b-chat-imat-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2920a4e063d81b21186687a4145044e1e07222b00ba85ac2a87367257d1e9cec +size 2813366400 diff --git a/yi-1.5-6b-chat-imat-IQ3_S.gguf b/yi-1.5-6b-chat-imat-IQ3_S.gguf new file mode 100644 index 0000000..68c32bd --- /dev/null +++ b/yi-1.5-6b-chat-imat-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeedb16adf9ff1d83fa74edf16770be98a395115f9c3a69d423b50638ec650a3 +size 2718109824 diff --git a/yi-1.5-6b-chat-imat-IQ3_XS.gguf b/yi-1.5-6b-chat-imat-IQ3_XS.gguf new file mode 100644 index 0000000..ea77f36 --- /dev/null +++ b/yi-1.5-6b-chat-imat-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17998e899011a82472ae9b31e292d516f5edc7f8eed2d0515e71f75b8449e06f +size 2588348544 diff --git a/yi-1.5-6b-chat-imat-IQ3_XXS.gguf b/yi-1.5-6b-chat-imat-IQ3_XXS.gguf new file mode 100644 index 0000000..3c287b1 --- /dev/null +++ b/yi-1.5-6b-chat-imat-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc900a4495712106cfb56caa94a504da0e2150cfba522c63f5d47384dbdbff4 +size 2414334080 diff --git a/yi-1.5-6b-chat-imat-IQ4_NL.gguf b/yi-1.5-6b-chat-imat-IQ4_NL.gguf new file mode 100644 index 0000000..eee3713 --- /dev/null +++ b/yi-1.5-6b-chat-imat-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c7d6f46b1b3dc9c010c04474fced5d43e4861e7998d0b27946d4c7baf3fa98b +size 3487715456 diff --git a/yi-1.5-6b-chat-imat-IQ4_XS.gguf b/yi-1.5-6b-chat-imat-IQ4_XS.gguf new file mode 100644 index 0000000..4756c51 --- /dev/null +++ b/yi-1.5-6b-chat-imat-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc7add1995789254805b8c3519bb46dc37f390787dd6ecdd99f4d73b9c575460 +size 3308605568 diff --git a/yi-1.5-6b-chat-imat-Q4_0.gguf b/yi-1.5-6b-chat-imat-Q4_0.gguf new file mode 100644 index 0000000..e80262e --- /dev/null +++ b/yi-1.5-6b-chat-imat-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ebb26c49da7b96c2b2eee1f382b14877d7885b107e8bd31904f6b476eb14ce3 +size 3490599040 diff --git a/yi-1.5-6b-chat-imat-Q4_K_M.gguf b/yi-1.5-6b-chat-imat-Q4_K_M.gguf new file mode 100644 index 0000000..c54ba22 --- /dev/null +++ b/yi-1.5-6b-chat-imat-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0e4f53cd01cd35db4462e9acc49a35983e5d4467ca0caad39bfb21e2221e9de +size 3673968768 diff --git a/yi-1.5-6b-chat-imat-Q4_K_S.gguf b/yi-1.5-6b-chat-imat-Q4_K_S.gguf new file mode 100644 index 0000000..d51347f --- /dev/null +++ b/yi-1.5-6b-chat-imat-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c7b6dd3005ae588b3b1a5825c8930d24e572f8eda048f63aef91d97ac842c6f +size 3502919808 diff --git a/yi-1.5-6b-chat-imat-Q5_K_M.gguf b/yi-1.5-6b-chat-imat-Q5_K_M.gguf new file mode 100644 index 0000000..23fa612 --- /dev/null +++ b/yi-1.5-6b-chat-imat-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0591ea7fbbfab5342c7bce4f7e139482aa395d21fd5071564e2a650cb80add3 +size 4304425088 diff --git a/yi-1.5-6b-chat-imat-Q5_K_S.gguf b/yi-1.5-6b-chat-imat-Q5_K_S.gguf new file mode 100644 index 0000000..b014606 --- /dev/null +++ b/yi-1.5-6b-chat-imat-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f99b9c308423479f62abdb426b7c594312537784b917bb0a45ab9ac92261368 +size 4204155008 diff --git a/yi-1.5-6b-chat-imat-Q6_K.gguf b/yi-1.5-6b-chat-imat-Q6_K.gguf new file mode 100644 index 0000000..8476a81 --- /dev/null +++ b/yi-1.5-6b-chat-imat-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eb711ce9a456bfb3efa4adc04262f83edb5e769ca2fde943c74f96f8f51671d +size 4974284928 diff --git a/yi-1.5-6b-chat-imat-Q8_0.gguf b/yi-1.5-6b-chat-imat-Q8_0.gguf new file mode 100644 index 0000000..b63f3cb --- /dev/null +++ b/yi-1.5-6b-chat-imat-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd51ddda04f56b83e4807c88746552f3d1aad9770b2339483be42906a51b9eae +size 6442127488