commit 1af00a2e5ccebf19537d4b585bc622261cb36d3a Author: ModelHub XC Date: Wed Jun 17 22:22:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: MoxoffSrL/AzzurroQuantized Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2251036 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,39 @@ +*.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 +xxxx-ggml-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +xxxx-ggml-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Azzurro-ggml-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Azzurro-ggml-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Azzurro-ggml-Q4_K_M.gguf b/Azzurro-ggml-Q4_K_M.gguf new file mode 100644 index 0000000..f2c7ce9 --- /dev/null +++ b/Azzurro-ggml-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc813660f6d29d00de6a2418bc89d3f3122f9094d8fad85392230ff7c36ac68d +size 4368439584 diff --git a/Azzurro-ggml-Q8_0.gguf b/Azzurro-ggml-Q8_0.gguf new file mode 100644 index 0000000..3c5b9cb --- /dev/null +++ b/Azzurro-ggml-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6773df7256f9b4a7ad11d26e50bfc895eab01ff921a71a09af48ddfe46bd2d1e +size 7695857952 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1a18e97 --- /dev/null +++ b/README.md @@ -0,0 +1,111 @@ +--- +license: mit +language: +- it +- en +library_name: transformers +tags: +- sft +- it +- mistral +- chatml +--- + +# Model Information + +AzzurroQuantized is a compact iteration of the model [Azzurro](https://huggingface.co/MoxoffSpA/Azzurro), optimized for efficiency. + +It is offered in two distinct configurations: a 4-bit version and an 8-bit version, each designed to maintain the model's effectiveness while significantly reducing its size +and computational requirements. + +- It's trained both on publicly available datasets, like [SQUAD-it](https://huggingface.co/datasets/squad_it), and datasets we've created in-house. +- it's designed to understand and maintain context, making it ideal for Retrieval Augmented Generation (RAG) tasks and applications requiring contextual awareness. +- It is quantized in a 4-bit version and an 8-bit version following the procedure [here](https://github.com/ggerganov/llama.cpp). + +# Evaluation + +We evaluated the model using the same test sets as used for the [Open Ita LLM Leaderboard](https://huggingface.co/spaces/FinancialSupport/open_ita_llm_leaderboard): + +| hellaswag_it acc_norm | arc_it acc_norm | m_mmlu_it 5-shot acc | Average | +|:----------------------| :--------------- | :-------------------- | :------- | +| 0.6067 | 0.4405 | 0.5112 | 0,52 | + +## Usage + +You need to download the .gguf model first + +If you want to use the cpu install these dependencies: + +```python +pip install llama-cpp-python huggingface_hub +``` + +If you want to use the gpu instead: + +```python +CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install huggingface_hub llama-cpp-python --force-reinstall --upgrade --no-cache-dir +``` + +And then use this code to see a response to the prompt. + +```python +from huggingface_hub import hf_hub_download +from llama_cpp import Llama + +model_path = hf_hub_download( + repo_id="MoxoffSpA/AzzurroQuantized", + filename="Azzurro-ggml-Q4_K_M.gguf" +) + +# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. +llm = Llama( + model_path=model_path, + n_ctx=2048, # The max sequence length to use - note that longer sequence lengths require much more resources + n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance + n_gpu_layers=0 # The number of layers to offload to GPU, if you have GPU acceleration available +) + +# Simple inference example +question = """Quanto è alta la torre di Pisa?""" +context = """ +La Torre di Pisa è un campanile del XII secolo, famoso per la sua inclinazione. Alta circa 56 metri. +""" + +prompt = f"Domanda: {question}, contesto: {context}" + +output = llm( + f"[INST] {prompt} [/INST]", # Prompt + max_tokens=128, + stop=["\n"], + echo=True, + temperature=0.1, + top_p=0.95 +) + +# Chat Completion API + +print(output['choices'][0]['text']) +``` + +## Bias, Risks and Limitations + +AzzurroQuantized and its original model [Azzurro](https://huggingface.co/MoxoffSpA/Azzurro) have not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of +responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). It is also unknown what the size and composition +of the corpus were used to train the base model [mistralai/Mistral-7B-v0.2](https://huggingface.co/mistralai/Mistral-7B-v0.2), however, it is likely to have included a mix of Web data and technical sources +like books and code. + +## Links to resources + +- SQUAD-it dataset: https://huggingface.co/datasets/squad_it +- Mistral_7B_v0.2 original weights: https://models.mistralcdn.com/mistral-7b-v0-2/mistral-7B-v0.2.tar +- Mistral_7B_v0.2 model: https://huggingface.co/alpindale/Mistral-7B-v0.2-hf +- Open Ita LLM Leaderbord: https://huggingface.co/spaces/FinancialSupport/open_ita_llm_leaderboard + +## Base version + +We have the not quantized version here: +https://huggingface.co/MoxoffSpA/Azzurro + +## The Moxoff Team + +Jacopo Abate, Marco D'Ambra, Luigi Simeone, Gianpaolo Francesco Trotta \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..780bc96 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "alpindale/Mistral-7B-v0.2-hf", + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.38.0", + "use_cache": true, + "vocab_size": 32000 +}