初始化项目，由ModelHub XC社区提供模型
Model: prithivMLmods/Llama-SmolTalk-3.2-1B-Instruct-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
39
.gitattributes
vendored
Normal file
39
.gitattributes
vendored
Normal file
@@ -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
|
||||
Llama-SmolTalk-3.2-1B-Instruct.F16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-SmolTalk-3.2-1B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-SmolTalk-3.2-1B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Llama-SmolTalk-3.2-1B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
3
Llama-SmolTalk-3.2-1B-Instruct.F16.gguf
Normal file
3
Llama-SmolTalk-3.2-1B-Instruct.F16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:286564f88abcb7b53408ee79c9b6d9161866d7847f3110a38209ee6a988a907f
|
||||
size 2479595904
|
||||
3
Llama-SmolTalk-3.2-1B-Instruct.Q4_K_M.gguf
Normal file
3
Llama-SmolTalk-3.2-1B-Instruct.Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:10c0d5e3b7b4373fac36dac07edc3462eb451716e5ba2df35625885810888e81
|
||||
size 807694720
|
||||
3
Llama-SmolTalk-3.2-1B-Instruct.Q5_K_M.gguf
Normal file
3
Llama-SmolTalk-3.2-1B-Instruct.Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:762012a5da87170a388cafa69f550ffaf6c96f3c237f6c824e84a1b0e334f4b3
|
||||
size 911503744
|
||||
3
Llama-SmolTalk-3.2-1B-Instruct.Q8_0.gguf
Normal file
3
Llama-SmolTalk-3.2-1B-Instruct.Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ba13bf20ed739aa0765af3b25b6886cb20c589af18e3a01dfdd0f906ed2c9d4a
|
||||
size 1321083264
|
||||
57
Modelfile
Normal file
57
Modelfile
Normal file
@@ -0,0 +1,57 @@
|
||||
|
||||
FROM /content/prithivMLmods/Llama-SmolTalk-3.2-1B-Instruct-GGUF/Llama-SmolTalk-3.2-1B-Instruct.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
|
||||
143
README.md
Normal file
143
README.md
Normal file
@@ -0,0 +1,143 @@
|
||||
---
|
||||
license: creativeml-openrail-m
|
||||
datasets:
|
||||
- HuggingFaceTB/smoltalk
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- prithivMLmods/Llama-SmolTalk-3.2-1B-Instruct
|
||||
library_name: transformers
|
||||
tags:
|
||||
- SmolTalk
|
||||
- Llama-Cpp
|
||||
- safetensors
|
||||
- Ollama
|
||||
- 8-bit
|
||||
- f16
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
## Llama-SmolTalk-3.2 Models Files
|
||||
|
||||
The **Llama-SmolTalk-3.2-1B-Instruct** model is a lightweight, instruction-tuned model designed for efficient text generation and conversational AI tasks. With a 1B parameter architecture, this model strikes a balance between performance and resource efficiency, making it ideal for applications requiring concise, contextually relevant outputs. The model has been fine-tuned to deliver robust instruction-following capabilities, catering to both structured and open-ended queries.
|
||||
|
||||
| File Name [ Updated Files ] | Size | Description | Upload Status |
|
||||
|----------------------------------------|----------|--------------------------------------------|----------------|
|
||||
| `.gitattributes` | 1.83 kB | Git attributes configuration file | Uploaded |
|
||||
| `README.md` | 42 Bytes | Initial README | Uploaded |
|
||||
| `config.json` | 31 Bytes | Configuration file | Uploaded |
|
||||
| `Modelfile` | 2.04 kB | Model information file | Uploaded |
|
||||
| `Llama-SmolTalk-3.2-1B-Instruct.F16.gguf` | 2.48 GB | Llama-SmolTalk model (F16 precision) | Uploaded (LFS) |
|
||||
| `Llama-SmolTalk-3.2-1B-Instruct.Q4_K_M.gguf` | 808 MB | Llama-SmolTalk model (Q4_K_M quantization) | Uploaded (LFS) |
|
||||
| `Llama-SmolTalk-3.2-1B-Instruct.Q5_K_M.gguf` | 912 MB | Llama-SmolTalk model (Q5_K_M quantization) | Uploaded (LFS) |
|
||||
| `Llama-SmolTalk-3.2-1B-Instruct.Q8_0.gguf` | 1.32 GB | Llama-SmolTalk model (Q8_0 quantization) | Uploaded (LFS) |
|
||||
|
||||
### Key Features:
|
||||
1. **Instruction-Tuned Performance**: Optimized to understand and execute user-provided instructions across diverse domains.
|
||||
2. **Lightweight Architecture**: With just 1 billion parameters, the model provides efficient computation and storage without compromising output quality.
|
||||
3. **Versatile Use Cases**: Suitable for tasks like content generation, conversational interfaces, and basic problem-solving.
|
||||
|
||||
### Intended Applications:
|
||||
- **Conversational AI**: Engage users with dynamic and contextually aware dialogue.
|
||||
- **Content Generation**: Produce summaries, explanations, or other creative text outputs efficiently.
|
||||
- **Instruction Execution**: Follow user commands to generate precise and relevant responses.
|
||||
|
||||
### Technical Details:
|
||||
The model leverages PyTorch for training and inference, with a tokenizer optimized for seamless text input processing. It comes with essential configuration files, including `config.json`, `generation_config.json`, and tokenization files (`tokenizer.json` and `special_tokens_map.json`). The primary weights are stored in a PyTorch binary format (`pytorch_model.bin`), ensuring easy integration with existing workflows.
|
||||
|
||||
**Model Type**: GGUF
|
||||
**Size**: 1B Parameters
|
||||
|
||||
The **Llama-SmolTalk-3.2-1B-Instruct** model is an excellent choice for lightweight text generation tasks, offering a blend of efficiency and effectiveness for a wide range of applications.
|
||||
|
||||
# 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.
|
||||
3
config.json
Normal file
3
config.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"model_type": "llama"
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
Reference in New Issue
Block a user