From 460c852c81562fed7ae9d9282f7de9c836d48c83 Mon Sep 17 00:00:00 2001 From: ai-modelscope Date: Sat, 14 Sep 2024 13:03:43 +0800 Subject: [PATCH] Upload Llama-3-13B-Instruct-v0.1.Q4_K_S.gguf with huggingface_hub --- .gitattributes | 39 ++++--- Llama-3-13B-Instruct-v0.1.Q2_K.gguf | 3 + Llama-3-13B-Instruct-v0.1.Q3_K_L.gguf | 3 + Llama-3-13B-Instruct-v0.1.Q3_K_M.gguf | 3 + Llama-3-13B-Instruct-v0.1.Q3_K_S.gguf | 3 + Llama-3-13B-Instruct-v0.1.Q4_0.gguf | 3 + Llama-3-13B-Instruct-v0.1.Q4_1.gguf | 3 + Llama-3-13B-Instruct-v0.1.Q4_K_M.gguf | 3 + Llama-3-13B-Instruct-v0.1.Q4_K_S.gguf | 3 + Llama-3-13B-Instruct-v0.1.Q5_0.gguf | 3 + Llama-3-13B-Instruct-v0.1.Q5_1.gguf | 3 + Llama-3-13B-Instruct-v0.1.Q5_K_M.gguf | 3 + Llama-3-13B-Instruct-v0.1.Q5_K_S.gguf | 3 + Llama-3-13B-Instruct-v0.1.Q6_K.gguf | 3 + Llama-3-13B-Instruct-v0.1.Q8_0.gguf | 3 + README.md | 159 +++++++++++++++++++------- 16 files changed, 187 insertions(+), 53 deletions(-) create mode 100644 Llama-3-13B-Instruct-v0.1.Q2_K.gguf create mode 100644 Llama-3-13B-Instruct-v0.1.Q3_K_L.gguf create mode 100644 Llama-3-13B-Instruct-v0.1.Q3_K_M.gguf create mode 100644 Llama-3-13B-Instruct-v0.1.Q3_K_S.gguf create mode 100644 Llama-3-13B-Instruct-v0.1.Q4_0.gguf create mode 100644 Llama-3-13B-Instruct-v0.1.Q4_1.gguf create mode 100644 Llama-3-13B-Instruct-v0.1.Q4_K_M.gguf create mode 100644 Llama-3-13B-Instruct-v0.1.Q4_K_S.gguf create mode 100644 Llama-3-13B-Instruct-v0.1.Q5_0.gguf create mode 100644 Llama-3-13B-Instruct-v0.1.Q5_1.gguf create mode 100644 Llama-3-13B-Instruct-v0.1.Q5_K_M.gguf create mode 100644 Llama-3-13B-Instruct-v0.1.Q5_K_S.gguf create mode 100644 Llama-3-13B-Instruct-v0.1.Q6_K.gguf create mode 100644 Llama-3-13B-Instruct-v0.1.Q8_0.gguf diff --git a/.gitattributes b/.gitattributes index 886ac0c..0eb244a 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1,38 +1,49 @@ *.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 +*.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 -*.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 +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +Llama-3-13B-Instruct-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-13B-Instruct-v0.1.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-13B-Instruct-v0.1.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-13B-Instruct-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-13B-Instruct-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-13B-Instruct-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-13B-Instruct-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-13B-Instruct-v0.1.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-13B-Instruct-v0.1.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-13B-Instruct-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-13B-Instruct-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-13B-Instruct-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-13B-Instruct-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-13B-Instruct-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-13B-Instruct-v0.1.Q2_K.gguf b/Llama-3-13B-Instruct-v0.1.Q2_K.gguf new file mode 100644 index 0000000..5c43b76 --- /dev/null +++ b/Llama-3-13B-Instruct-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddd19a0b48c4d14df81d0ec59ade96d3cb6d81c3c2be148adf620e3ec5b7772d +size 5105116896 diff --git a/Llama-3-13B-Instruct-v0.1.Q3_K_L.gguf b/Llama-3-13B-Instruct-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..0e7bb83 --- /dev/null +++ b/Llama-3-13B-Instruct-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91ea467af2a795a953dff98224f5a453d13d1638b80c09a9806d6d4cbd01d805 +size 7065044704 diff --git a/Llama-3-13B-Instruct-v0.1.Q3_K_M.gguf b/Llama-3-13B-Instruct-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..c91095d --- /dev/null +++ b/Llama-3-13B-Instruct-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d273d4d3db7d7ea18112b507cb29895d4cd88ee45997af1719abfa0270f7e1d8 +size 6530270944 diff --git a/Llama-3-13B-Instruct-v0.1.Q3_K_S.gguf b/Llama-3-13B-Instruct-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..2c4e227 --- /dev/null +++ b/Llama-3-13B-Instruct-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69ae4c397fd4816ea9e771c9715f7538860ec019de9c1fab1e121ba2d08c7a44 +size 5914494688 diff --git a/Llama-3-13B-Instruct-v0.1.Q4_0.gguf b/Llama-3-13B-Instruct-v0.1.Q4_0.gguf new file mode 100644 index 0000000..335c3ea --- /dev/null +++ b/Llama-3-13B-Instruct-v0.1.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24594a630c961e80a31652395a73dca3a40ee0fc71b088b2a2064efbd7efeff7 +size 7606413024 diff --git a/Llama-3-13B-Instruct-v0.1.Q4_1.gguf b/Llama-3-13B-Instruct-v0.1.Q4_1.gguf new file mode 100644 index 0000000..d631930 --- /dev/null +++ b/Llama-3-13B-Instruct-v0.1.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6324ba3144b53b7399ec5cc9d9a27d4e034211cdd6b84033da95b3bb7d31ec7 +size 8402609888 diff --git a/Llama-3-13B-Instruct-v0.1.Q4_K_M.gguf b/Llama-3-13B-Instruct-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..1cf4bc5 --- /dev/null +++ b/Llama-3-13B-Instruct-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49f8a7daea75ad8ea326b056028d770cfa6286452031f91539d7e404504b0666 +size 8060577504 diff --git a/Llama-3-13B-Instruct-v0.1.Q4_K_S.gguf b/Llama-3-13B-Instruct-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..18b44bc --- /dev/null +++ b/Llama-3-13B-Instruct-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4194b58fdba3935edffddac22a1f3daafac761bc78bbdf6d1676ef162655ca0e +size 7659890400 diff --git a/Llama-3-13B-Instruct-v0.1.Q5_0.gguf b/Llama-3-13B-Instruct-v0.1.Q5_0.gguf new file mode 100644 index 0000000..2fef831 --- /dev/null +++ b/Llama-3-13B-Instruct-v0.1.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44ae3842b3569a5711bc2e4b1eaa468993cb64d4099fffcbc8fc391e7c0ad527 +size 9198806752 diff --git a/Llama-3-13B-Instruct-v0.1.Q5_1.gguf b/Llama-3-13B-Instruct-v0.1.Q5_1.gguf new file mode 100644 index 0000000..806ae73 --- /dev/null +++ b/Llama-3-13B-Instruct-v0.1.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0866c7f694fbcd35a60d7f268d97a6ab98c643430a8a5920c1a149202991821d +size 9995003616 diff --git a/Llama-3-13B-Instruct-v0.1.Q5_K_M.gguf b/Llama-3-13B-Instruct-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..5ccea5c --- /dev/null +++ b/Llama-3-13B-Instruct-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c14fa36ca074c7cc801ff1bd1841f6f488c7fbf25a3d8dbec0d969613793956 +size 9432770272 diff --git a/Llama-3-13B-Instruct-v0.1.Q5_K_S.gguf b/Llama-3-13B-Instruct-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..c0a9968 --- /dev/null +++ b/Llama-3-13B-Instruct-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:218f4a84d0c46f1a1dcaa3792faa49f626855e776065d8d61ef574ea347f0326 +size 9198806752 diff --git a/Llama-3-13B-Instruct-v0.1.Q6_K.gguf b/Llama-3-13B-Instruct-v0.1.Q6_K.gguf new file mode 100644 index 0000000..006b354 --- /dev/null +++ b/Llama-3-13B-Instruct-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b01b8073e63d0fe796f5e86b0bd64972fed8ca8c59c353e4ba132f85d31d701a +size 10890725088 diff --git a/Llama-3-13B-Instruct-v0.1.Q8_0.gguf b/Llama-3-13B-Instruct-v0.1.Q8_0.gguf new file mode 100644 index 0000000..6750b62 --- /dev/null +++ b/Llama-3-13B-Instruct-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:631e7dac6a49be11f942a478953b649b9b9d0874b439f90d66d17ffe9f32d47e +size 14103217888 diff --git a/README.md b/README.md index 8870a61..c865247 100644 --- a/README.md +++ b/README.md @@ -1,47 +1,128 @@ + --- -license: Apache License 2.0 -#model-type: -##如 gpt、phi、llama、chatglm、baichuan 等 -#- gpt +base_model: "meta-llama/Meta-Llama-3-8B-Instruct" +library_name: transformers +tags: + - mergekit + - merge + - facebook + - meta + - pytorch + - llama + - llama-3 +language: + - en +pipeline_tag: text-generation +license: other +license_name: llama3 +license_link: LICENSE +inference: false +model_creator: MaziyarPanahi +model_name: Llama-3-13B-Instruct-v0.1 +quantized_by: MaziyarPanahi -#domain: -##如 nlp、cv、audio、multi-modal -#- nlp - -#language: -##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa -#- cn - -#metrics: -##如 CIDEr、Blue、ROUGE 等 -#- CIDEr - -#tags: -##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他 -#- pretrained - -#tools: -##如 vllm、fastchat、llamacpp、AdaSeq 等 -#- vllm --- -### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。 -#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型 -SDK下载 -```bash -#安装ModelScope -pip install modelscope -``` +![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ) + +# QuantFactory/Llama-3-13B-Instruct-v0.1-GGUF +This is quantized version of [MaziyarPanahi/Llama-3-13B-Instruct-v0.1](https://huggingface.co/MaziyarPanahi/Llama-3-13B-Instruct-v0.1) created using llama.cpp + +# Original Model Card + + +Goku 8x22B v0.1 Logo + +# Llama-3-13B-Instruct-v0.1 + +This model is a self-merge of `meta-llama/Meta-Llama-3-8B-Instruct` model. + +# How to use + +You can use this model by using `MaziyarPanahi/Llama-3-13B-Instruct-v0.1` as the model name in Hugging Face's +transformers library. + ```python -#SDK模型下载 -from modelscope import snapshot_download -model_dir = snapshot_download('QuantFactory/Llama-3-13B-Instruct-v0.1-GGUF') -``` -Git下载 -``` -#Git模型下载 -git clone https://www.modelscope.cn/QuantFactory/Llama-3-13B-Instruct-v0.1-GGUF.git +from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer +from transformers import pipeline +import torch + +model_id = "MaziyarPanahi/Llama-3-13B-Instruct-v0.1" + +model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype=torch.float16, + device_map="auto", + trust_remote_code=True, + # attn_implementation="flash_attention_2" +) + +tokenizer = AutoTokenizer.from_pretrained( + model_id, + trust_remote_code=True +) + +streamer = TextStreamer(tokenizer) + +pipeline = pipeline( + "text-generation", + model=model, + tokenizer=tokenizer, + model_kwargs={"torch_dtype": torch.bfloat16}, + streamer=streamer +) + +# Then you can use the pipeline to generate text. + +messages = [ + {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"}, + {"role": "user", "content": "Who are you?"}, +] + +prompt = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True +) + +terminators = [ + tokenizer.eos_token_id, + tokenizer.convert_tokens_to_ids("<|eot_id|>") +] + +outputs = pipeline( + prompt, + max_new_tokens=256, + eos_token_id=terminators, + do_sample=True, + temperature=0.6, + top_p=0.95, +) +print(outputs[0]["generated_text"][len(prompt):]) ``` -

如果您是本模型的贡献者，我们邀请您根据模型贡献文档，及时完善模型卡片内容。

\ No newline at end of file +## Prompt template + +```text +<|begin_of_text|><|start_header_id|>system<|end_header_id|> + +You are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|> + +what's 25-4*2+3<|eot_id|><|start_header_id|>assistant<|end_header_id|> + +To evaluate this expression, we need to follow the order of operations (PEMDAS): + +1. First, multiply 4 and 2: 4*2 = 8 +2. Then, subtract 8 from 25: 25 - 8 = 17 +3. Finally, add 3: 17 + 3 = 20 + +So, 25-4*2+3 = 20!<|eot_id|> +To evaluate this expression, we need to follow the order of operations (PEMDAS): + +1. First, multiply 4 and 2: 4*2 = 8 +2. Then, subtract 8 from 25: 25 - 8 = 17 +3. Finally, add 3: 17 + 3 = 20 + +So, 25-4*2+3 = 20! +```