commit 33e451fb75ed0a62dc88872abe5f931ad3b3af72 Author: ModelHub XC Date: Wed Aug 26 06:18:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/Meta-Llama-3.2-1B-GGUF-QX Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7b011e4 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,40 @@ +*.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 +Llama-3.2-1B-GGUF-QX.F16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-GGUF-QX.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-GGUF-QX.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-GGUF-QX.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-1B-GGUF.F16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-1B-GGUF-QX.Q4_K_M.gguf b/Llama-3.2-1B-GGUF-QX.Q4_K_M.gguf new file mode 100644 index 0000000..3094d4a --- /dev/null +++ b/Llama-3.2-1B-GGUF-QX.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a275f7932a0d14918d98ae481a2d5ce5d849cab3e666ee8d84f528c45ea29a4a +size 807694720 diff --git a/Llama-3.2-1B-GGUF-QX.Q5_K_M.gguf b/Llama-3.2-1B-GGUF-QX.Q5_K_M.gguf new file mode 100644 index 0000000..a4fedf5 --- /dev/null +++ b/Llama-3.2-1B-GGUF-QX.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:091304a748e8c709f207786e122ec21e1787645461923c5148037634606f3f90 +size 911503744 diff --git a/Llama-3.2-1B-GGUF-QX.Q8_0.gguf b/Llama-3.2-1B-GGUF-QX.Q8_0.gguf new file mode 100644 index 0000000..1845328 --- /dev/null +++ b/Llama-3.2-1B-GGUF-QX.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52599ec9926cb2bc02ff86885a4f1a43f194032cf9cbb228783f41298533d59c +size 1321083264 diff --git a/Llama-3.2-1B-GGUF.F16.gguf b/Llama-3.2-1B-GGUF.F16.gguf new file mode 100644 index 0000000..6e95def --- /dev/null +++ b/Llama-3.2-1B-GGUF.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3691f38dacfecfc9cc0119eaa2a7fad768fde91236ad615e79a0f90b1bb0d83 +size 2479595904 diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..e2337f6 --- /dev/null +++ b/Modelfile @@ -0,0 +1,57 @@ + +FROM /content/prithivMLmods/Meta-Llama-3.2-1B-GGUF-QX/Llama-3.2-1B-GGUF.F16.gguf +TEMPLATE """{{ if .Messages }} +{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|> +{{- if .System }} + +{{ .System }} +{{- end }} +{{- if .Tools }} + +You are a helpful assistant with tool calling capabilities. When you receive a tool call response, use the output to format an answer to the original use question. +{{- end }} +{{- end }}<|eot_id|> +{{- range $i, $_ := .Messages }} +{{- $last := eq (len (slice $.Messages $i)) 1 }} +{{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|> +{{- if and $.Tools $last }} + +Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt. + +Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables. + +{{ $.Tools }} +{{- end }} + +{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|> + +{{ end }} +{{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|> +{{- if .ToolCalls }} + +{{- range .ToolCalls }}{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }} +{{- else }} + +{{ .Content }}{{ if not $last }}<|eot_id|>{{ end }} +{{- end }} +{{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|> + +{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|> + +{{ end }} +{{- end }} +{{- end }} +{{- else }} +{{- if .System }}<|start_header_id|>system<|end_header_id|> + +{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|> + +{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|> + +{{ end }}{{ .Response }}{{ if .Response }}<|eot_id|>{{ end }}""" +PARAMETER stop "<|start_header_id|>" +PARAMETER stop "<|end_header_id|>" +PARAMETER stop "<|eot_id|>" +PARAMETER stop "<|eom_id|>" +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..6887d7f --- /dev/null +++ b/README.md @@ -0,0 +1,122 @@ +--- +base_model: meta-llama/Llama-3.2-1B +language: +- en +license: apache-2.0 +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- gguf +- Llama-3.2-1B +- Quants +pipeline_tag: text-generation +--- + +![Llama](img/llama321.png) +# Uploaded model + +- **Developed by:** prithivMLmods +- **License:** apache-2.0 +- **Finetuned from model :** meta-llama/Llama-3.2-1B + +Here's a well-structured README.md documentation for running models with Ollama: + +# Run with Ollama 🦙 + +## 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 + +| Section | Description | +|------------------------------|----------------------------------| +| [Download and Install Ollama](#download-and-install-ollama) | Instructions for downloading and installing Ollama. | +| [Steps to Run GGUF Models](#steps-to-run-gguf-models) | Guidelines for running GGUF models. | +| 1. [Create the Model File](#1-create-the-model-file) | Steps to create the model file. | +| 2. [Add the Template Command](#2-add-the-template-command) | Instructions for adding the template command. | +| 3. [Create and Patch the Model](#3-create-and-patch-the-model) | Process for creating and patching the model. | +| [Running the Model](#running-the-model) | How to run the model. | +| [Sample Usage](#sample-usage) | Examples of how to use the model. | + +## 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 + +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. + + + +https://huggingface.co/prithivMLmods/Llama-3.2-1B-GGUF/resolve/main/Demo/gguf.gif \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..352d34f --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "llama" +} 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 diff --git a/img/demo.txt b/img/demo.txt new file mode 100644 index 0000000..e69de29 diff --git a/img/llama321.png b/img/llama321.png new file mode 100644 index 0000000..733acc3 Binary files /dev/null and b/img/llama321.png differ