commit 648de000976cef995f6f31d035eb9e55651b12a6 Author: ModelHub XC Date: Wed May 27 03:10:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/Acrux-500M-o1-Journey-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a189122 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +acrux-500m-o1-journey-f16.gguf filter=lfs diff=lfs merge=lfs -text +acrux-500m-o1-journey-q2_k.gguf filter=lfs diff=lfs merge=lfs -text +acrux-500m-o1-journey-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text +acrux-500m-o1-journey-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +acrux-500m-o1-journey-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text +acrux-500m-o1-journey-q4_0.gguf filter=lfs diff=lfs merge=lfs -text +acrux-500m-o1-journey-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +acrux-500m-o1-journey-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text +acrux-500m-o1-journey-q5_0.gguf filter=lfs diff=lfs merge=lfs -text +acrux-500m-o1-journey-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +acrux-500m-o1-journey-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text +acrux-500m-o1-journey-q6_k.gguf filter=lfs diff=lfs merge=lfs -text +acrux-500m-o1-journey-q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..bc95dbf --- /dev/null +++ b/Modelfile @@ -0,0 +1,56 @@ + +FROM /content/prithivMLmods/Acrux-500M-o1-Journey-GGUF/acrux-500m-o1-journey-f16.gguf +TEMPLATE """{{- if .Messages }} +{{- if or .System .Tools }}<|im_start|>system +{{- if .System }} +{{ .System }} +{{- end }} +{{- if .Tools }} + +# Tools + +You may call one or more functions to assist with the user query. + +You are provided with function signatures within XML tags: + +{{- range .Tools }} +{"type": "function", "function": {{ .Function }}} +{{- end }} + + +For each function call, return a json object with function name and arguments within XML tags: + +{"name": , "arguments": } + +{{- end }}<|im_end|> +{{ end }} +{{- range $i, $_ := .Messages }} +{{- $last := eq (len (slice $.Messages $i)) 1 -}} +{{- if eq .Role "user" }}<|im_start|>user +{{ .Content }}<|im_end|> +{{ else if eq .Role "assistant" }}<|im_start|>assistant +{{ if .Content }}{{ .Content }} +{{- else if .ToolCalls }} +{{ range .ToolCalls }}{"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}} +{{ end }} +{{- end }}{{ if not $last }}<|im_end|> +{{ end }} +{{- else if eq .Role "tool" }}<|im_start|>user + +{{ .Content }} +<|im_end|> +{{ end }} +{{- if and (ne .Role "assistant") $last }}<|im_start|>assistant +{{ end }} +{{- end }} +{{- else }} +{{- if .System }}<|im_start|>system +{{ .System }}<|im_end|> +{{ end }}{{ if .Prompt }}<|im_start|>user +{{ .Prompt }}<|im_end|> +{{ end }}<|im_start|>assistant +{{ end }}{{ .Response }}{{ if .Response }}<|im_end|>{{ end }}""" +PARAMETER stop "<|im_end|>" +PARAMETER stop "<|endoftext|>" +PARAMETER temperature 1.5 +PARAMETER min_p 0.1 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..7e641eb --- /dev/null +++ b/README.md @@ -0,0 +1,191 @@ +--- +license: creativeml-openrail-m +datasets: +- GAIR/o1-journey +language: +- en +base_model: +- prithivMLmods/Acrux-500M-o1-Journey +library_name: transformers +pipeline_tag: text-generation +tags: +- Qwen2.5 +- 500M +- Ollama +- Llama-cpp +- text-generation-inference +- o1-Journey +--- +### Acrux-500M-o1-Journey-GGUF Model Files + +The **Acrux-500M-o1-Journey** is a lightweight, instruction-tuned language model fine-tuned from the **Qwen2.5-0.5B-Instruct** base model. With a size of 500 million parameters, it is designed for **cost-effective deployment** and **fast text generation** while maintaining quality performance for instruction-following tasks. + +| **File Name** | **Size** | **Description** | **Upload Status** | +|-----------------------------------------|----------------|-----------------------------------------------|--------------------| +| `.gitattributes` | 2.42 kB | Specifies file tracking rules (e.g., LFS). | Uploaded | +| `Modelfile` | 1.69 kB | Metadata or additional information file. | Uploaded | +| `README.md` | 158 Bytes | Basic project description or instructions. | Updated | +| `acrux-500m-o1-journey-f16.gguf` | 994 MB | Base FP16 model file in GGUF format. | Uploaded (LFS) | +| `acrux-500m-o1-journey-q2_k.gguf` | 339 MB | Quantized model (Q2_K) for efficient usage. | Uploaded (LFS) | +| `acrux-500m-o1-journey-q3_k_l.gguf` | 369 MB | Quantized model (Q3_K_L). | Uploaded (LFS) | +| `acrux-500m-o1-journey-q3_k_m.gguf` | 355 MB | Quantized model (Q3_K_M). | Uploaded (LFS) | +| `acrux-500m-o1-journey-q3_k_s.gguf` | 338 MB | Quantized model (Q3_K_S). | Uploaded (LFS) | +| `acrux-500m-o1-journey-q4_0.gguf` | 352 MB | Quantized model (Q4_0). | Uploaded (LFS) | +| `acrux-500m-o1-journey-q4_k_m.gguf` | 398 MB | Quantized model (Q4_K_M). | Uploaded (LFS) | +| `acrux-500m-o1-journey-q4_k_s.gguf` | 385 MB | Quantized model (Q4_K_S). | Uploaded (LFS) | +| `acrux-500m-o1-journey-q5_0.gguf` | 397 MB | Quantized model (Q5_0). | Uploaded (LFS) | +| `acrux-500m-o1-journey-q5_k_m.gguf` | 420 MB | Quantized model (Q5_K_M). | Uploaded (LFS) | +| `acrux-500m-o1-journey-q5_k_s.gguf` | 413 MB | Quantized model (Q5_K_S). | Uploaded (LFS) | +| `acrux-500m-o1-journey-q6_k.gguf` | 506 MB | Quantized model (Q6_K). | Uploaded (LFS) | +| `acrux-500m-o1-journey-q8_0.gguf` | 531 MB | Quantized model (Q8_0). | Uploaded (LFS) | +| `config.json` | 29 Bytes | Basic configuration file for the model. | Uploaded | + +--- +### **Key Features:** + +1. **Compact Size with Efficient Performance:** + The smaller parameter count (500M) ensures faster inference and reduced hardware requirements. + +2. **Instruction Optimization:** + Fine-tuned to follow prompts effectively, making it suitable for interactive applications and prompt-based tasks. + +3. **Domain-Specific Training:** + Trained on the **GAIR/o1-journey** dataset, providing tailored capabilities for specific use cases. + +--- + +### **Training Details:** +- **Base Model:** [Qwen2.5-0.5B-Instruct](#) +- **Dataset Used for Fine-Tuning:** [GAIR/o1-journey](#) + - A compact dataset focusing on instruction-driven generation with 1.42k samples. + +--- +### **Capabilities:** + +1. **Instruction Following:** + - Generates accurate and coherent responses to user instructions. + - Handles summarization, question-answering, and conversational tasks. + +2. **Fast Inference:** + - Ideal for real-time applications due to reduced latency from its smaller size. + +3. **Interactive AI Development:** + - Suitable for chatbots, virtual assistants, and instructional interfaces. + +--- +### **Usage Instructions:** + +1. **Setup:** + Download all model files, ensuring compatibility with the Hugging Face Transformers library. + +2. **Loading the Model:** + ```python + from transformers import AutoModelForCausalLM, AutoTokenizer + + model_name = "prithivMLmods/Acrux-500M-o1-Journey" + tokenizer = AutoTokenizer.from_pretrained(model_name) + model = AutoModelForCausalLM.from_pretrained(model_name) + ``` +3. **Sample Generate Text:** + ```python + input_text = "Explain the concept of machine learning in simple terms." + inputs = tokenizer(input_text, return_tensors="pt") + outputs = model.generate(**inputs, max_length=100, temperature=0.7) + print(tokenizer.decode(outputs[0], skip_special_tokens=True)) + ``` +4. **Optimize Generation:** + Adjust parameters in `generation_config.json` for better control of output, such as: + - `temperature` for randomness. + - `top_p` for sampling diversity. + - `max_length` for output size. +--- +# Run with Ollama [ Ollama Run ] + +## Overview + +Ollama is a powerful tool that allows you to run machine learning models effortlessly. This guide will help you download, install, and run your own GGUF models in just a few minutes. + +## Table of Contents + +- [Download and Install Ollama](#download-and-install-ollama) +- [Steps to Run GGUF Models](#steps-to-run-gguf-models) + - [1. Create the Model File](#1-create-the-model-file) + - [2. Add the Template Command](#2-add-the-template-command) + - [3. Create and Patch the Model](#3-create-and-patch-the-model) +- [Running the Model](#running-the-model) +- [Sample Usage](#sample-usage) + +## Download and Install Ollama🦙 + +To get started, download Ollama from [https://ollama.com/download](https://ollama.com/download) and install it on your Windows or Mac system. + +## Steps to Run GGUF Models + +### 1. Create the Model File +First, create a model file and name it appropriately. For example, you can name your model file `metallama`. + +### 2. Add the Template Command +In your model file, include a `FROM` line that specifies the base model file you want to use. For instance: + +```bash +FROM Llama-3.2-1B.F16.gguf +``` + +Ensure that the model file is in the same directory as your script. + +### 3. Create and Patch the Model +Open your terminal and run the following command to create and patch your model: + +```bash +ollama create metallama -f ./metallama +``` + +Once the process is successful, you will see a confirmation message. + +To verify that the model was created successfully, you can list all models with: + +```bash +ollama list +``` + +Make sure that `metallama` appears in the list of models. + +--- + +## Running the Model + +To run your newly created model, use the following command in your terminal: + +```bash +ollama run metallama +``` + +### Sample Usage / Test + +In the command prompt, you can execute: + +```bash +D:\>ollama run metallama +``` + +You can interact with the model like this: + +```plaintext +>>> write a mini passage about space x +Space X, the private aerospace company founded by Elon Musk, is revolutionizing the field of space exploration. +With its ambitious goals to make humanity a multi-planetary species and establish a sustainable human presence in +the cosmos, Space X has become a leading player in the industry. The company's spacecraft, like the Falcon 9, have +demonstrated remarkable capabilities, allowing for the transport of crews and cargo into space with unprecedented +efficiency. As technology continues to advance, the possibility of establishing permanent colonies on Mars becomes +increasingly feasible, thanks in part to the success of reusable rockets that can launch multiple times without +sustaining significant damage. The journey towards becoming a multi-planetary species is underway, and Space X +plays a pivotal role in pushing the boundaries of human exploration and settlement. +``` +--- +## Conclusion + +With these simple steps, you can easily download, install, and run your own models using Ollama. Whether you're exploring the capabilities of Llama or building your own custom models, Ollama makes it accessible and efficient. + + +- This README provides clear instructions and structured information to help users navigate the process of using Ollama effectively. Adjust any sections as needed based on your specific requirements or additional details you may want to include. +--- \ No newline at end of file diff --git a/acrux-500m-o1-journey-f16.gguf b/acrux-500m-o1-journey-f16.gguf new file mode 100644 index 0000000..6b3cfb4 --- /dev/null +++ b/acrux-500m-o1-journey-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa89f2a3d315c0e00c2610931191165881606d27c95322243ce80c1250a67d99 +size 994156384 diff --git a/acrux-500m-o1-journey-q2_k.gguf b/acrux-500m-o1-journey-q2_k.gguf new file mode 100644 index 0000000..de61852 --- /dev/null +++ b/acrux-500m-o1-journey-q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:330cfbd78622a5866231a4ca239a09f382289a9b9d13b8f399e5507a860b9755 +size 338606944 diff --git a/acrux-500m-o1-journey-q3_k_l.gguf b/acrux-500m-o1-journey-q3_k_l.gguf new file mode 100644 index 0000000..199f633 --- /dev/null +++ b/acrux-500m-o1-journey-q3_k_l.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77c4f6543dd4adf08454b30063b43f53440bf9ceba017bde4fac53e342c186fc +size 369357664 diff --git a/acrux-500m-o1-journey-q3_k_m.gguf b/acrux-500m-o1-journey-q3_k_m.gguf new file mode 100644 index 0000000..1800ddd --- /dev/null +++ b/acrux-500m-o1-journey-q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1dd6423ee0cc5178f7073b186bbf215e1c0152924bfca8cbbc94a67e955cbbe +size 355466080 diff --git a/acrux-500m-o1-journey-q3_k_s.gguf b/acrux-500m-o1-journey-q3_k_s.gguf new file mode 100644 index 0000000..45fd255 --- /dev/null +++ b/acrux-500m-o1-journey-q3_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb641434bec8c16aaf2db6f837bde61fa036841aa14e967305052231173f9d76 +size 338262880 diff --git a/acrux-500m-o1-journey-q4_0.gguf b/acrux-500m-o1-journey-q4_0.gguf new file mode 100644 index 0000000..b08a43b --- /dev/null +++ b/acrux-500m-o1-journey-q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1202eac206279588bf37a385ae5300869d043a4cbe241ef11af944cb2ce97331 +size 352154464 diff --git a/acrux-500m-o1-journey-q4_k_m.gguf b/acrux-500m-o1-journey-q4_k_m.gguf new file mode 100644 index 0000000..08e9f11 --- /dev/null +++ b/acrux-500m-o1-journey-q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1640ced56e67a5e2ebc3018fcac94270c554779edbb5e425fa3169901fb39a8 +size 397807456 diff --git a/acrux-500m-o1-journey-q4_k_s.gguf b/acrux-500m-o1-journey-q4_k_s.gguf new file mode 100644 index 0000000..7e3d890 --- /dev/null +++ b/acrux-500m-o1-journey-q4_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3298274959460bfa998af2bc96518964783d2b42c27707640ba0f6048366e8a9 +size 385471328 diff --git a/acrux-500m-o1-journey-q5_0.gguf b/acrux-500m-o1-journey-q5_0.gguf new file mode 100644 index 0000000..1578f5e --- /dev/null +++ b/acrux-500m-o1-journey-q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bdaff379a4dccb045c8404ce419a12b16af3492d701545db1c70226151d924d +size 396882784 diff --git a/acrux-500m-o1-journey-q5_k_m.gguf b/acrux-500m-o1-journey-q5_k_m.gguf new file mode 100644 index 0000000..9db780f --- /dev/null +++ b/acrux-500m-o1-journey-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0becb6d45e05b42112ddb18453d57c97634cc030cfd200a33b752aa19ffcf66e +size 420085600 diff --git a/acrux-500m-o1-journey-q5_k_s.gguf b/acrux-500m-o1-journey-q5_k_s.gguf new file mode 100644 index 0000000..e03ab79 --- /dev/null +++ b/acrux-500m-o1-journey-q5_k_s.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d8bdea13e43cc1c9e485eaa8beafb5cacba7aac1bf99792b4e25afad04e2f08 +size 412709728 diff --git a/acrux-500m-o1-journey-q6_k.gguf b/acrux-500m-o1-journey-q6_k.gguf new file mode 100644 index 0000000..e7aa7bb --- /dev/null +++ b/acrux-500m-o1-journey-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d35415db5d4d97f4ff380097dd7a0244328d2353a576ff35b7cfd49540563769 +size 505736032 diff --git a/acrux-500m-o1-journey-q8_0.gguf b/acrux-500m-o1-journey-q8_0.gguf new file mode 100644 index 0000000..23f66f4 --- /dev/null +++ b/acrux-500m-o1-journey-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5c50a8ad0f56fde0f8d8f641043116d6a15af24fb73e9b858025fb9c6134640 +size 531067744 diff --git a/config.json b/config.json new file mode 100644 index 0000000..5ca493c --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "qwen2" +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file