Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Locutusque/gpt2-xl-conversational
|
| 3 |
+
datasets:
|
| 4 |
+
- Locutusque/InstructMix
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
license: mit
|
| 8 |
+
metrics:
|
| 9 |
+
- bleu
|
| 10 |
+
- perplexity
|
| 11 |
+
- loss
|
| 12 |
+
- accuracy
|
| 13 |
+
pipeline_tag: text-generation
|
| 14 |
+
tags:
|
| 15 |
+
- llama-cpp
|
| 16 |
+
- matrixportal
|
| 17 |
+
widget:
|
| 18 |
+
- text: '<|USER|> Design a Neo4j database and Cypher function snippet to Display Extreme
|
| 19 |
+
Dental hygiene: Using Mouthwash for Analysis for Beginners. Implement if/else
|
| 20 |
+
or switch/case statements to handle different conditions related to the Consent.
|
| 21 |
+
Provide detailed comments explaining your control flow and the reasoning behind
|
| 22 |
+
each decision. <|ASSISTANT|> '
|
| 23 |
+
- text: '<|USER|> Write me a story about a magical place. <|ASSISTANT|> '
|
| 24 |
+
- text: '<|USER|> Write me an essay about the life of George Washington <|ASSISTANT|> '
|
| 25 |
+
- text: '<|USER|> Solve the following equation 2x + 10 = 20 <|ASSISTANT|> '
|
| 26 |
+
- text: '<|USER|> Craft me a list of some nice places to visit around the world. <|ASSISTANT|> '
|
| 27 |
+
- text: '<|USER|> How to manage a lazy employee: Address the employee verbally. Don''t
|
| 28 |
+
allow an employee''s laziness or lack of enthusiasm to become a recurring issue.
|
| 29 |
+
Tell the employee you''re hoping to speak with them about workplace expectations
|
| 30 |
+
and performance, and schedule a time to sit down together. Question: To manage
|
| 31 |
+
a lazy employee, it is suggested to talk to the employee. True, False, or Neither?
|
| 32 |
+
<|ASSISTANT|> '
|
| 33 |
+
inference:
|
| 34 |
+
parameters:
|
| 35 |
+
temperature: 0.8
|
| 36 |
+
do_sample: true
|
| 37 |
+
top_p: 0.14
|
| 38 |
+
top_k: 41
|
| 39 |
+
max_new_tokens: 250
|
| 40 |
+
repetition_penalty: 1.176
|
| 41 |
+
---
|
| 42 |
+
|
| 43 |
+
# ysn-rfd/gpt2-xl-conversational-GGUF
|
| 44 |
+
This model was converted to GGUF format from [`Locutusque/gpt2-xl-conversational`](https://huggingface.co/Locutusque/gpt2-xl-conversational) using llama.cpp via the ggml.ai's [all-gguf-same-where](https://huggingface.co/spaces/matrixportal/all-gguf-same-where) space.
|
| 45 |
+
Refer to the [original model card](https://huggingface.co/Locutusque/gpt2-xl-conversational) for more details on the model.
|
| 46 |
+
|
| 47 |
+
## β
Quantized Models Download List
|
| 48 |
+
|
| 49 |
+
### π Recommended Quantizations
|
| 50 |
+
- **β¨ General CPU Use:** [`Q4_K_M`](https://huggingface.co/ysn-rfd/gpt2-xl-conversational-GGUF/resolve/main/gpt2-xl-conversational-q4_k_m.gguf) (Best balance of speed/quality)
|
| 51 |
+
- **π± ARM Devices:** [`Q4_0`](https://huggingface.co/ysn-rfd/gpt2-xl-conversational-GGUF/resolve/main/gpt2-xl-conversational-q4_0.gguf) (Optimized for ARM CPUs)
|
| 52 |
+
- **π Maximum Quality:** [`Q8_0`](https://huggingface.co/ysn-rfd/gpt2-xl-conversational-GGUF/resolve/main/gpt2-xl-conversational-q8_0.gguf) (Near-original quality)
|
| 53 |
+
|
| 54 |
+
### π¦ Full Quantization Options
|
| 55 |
+
| π Download | π’ Type | π Notes |
|
| 56 |
+
|:---------|:-----|:------|
|
| 57 |
+
| [Download](https://huggingface.co/ysn-rfd/gpt2-xl-conversational-GGUF/resolve/main/gpt2-xl-conversational-q2_k.gguf) |  | Basic quantization |
|
| 58 |
+
| [Download](https://huggingface.co/ysn-rfd/gpt2-xl-conversational-GGUF/resolve/main/gpt2-xl-conversational-q3_k_s.gguf) |  | Small size |
|
| 59 |
+
| [Download](https://huggingface.co/ysn-rfd/gpt2-xl-conversational-GGUF/resolve/main/gpt2-xl-conversational-q3_k_m.gguf) |  | Balanced quality |
|
| 60 |
+
| [Download](https://huggingface.co/ysn-rfd/gpt2-xl-conversational-GGUF/resolve/main/gpt2-xl-conversational-q3_k_l.gguf) |  | Better quality |
|
| 61 |
+
| [Download](https://huggingface.co/ysn-rfd/gpt2-xl-conversational-GGUF/resolve/main/gpt2-xl-conversational-q4_0.gguf) |  | Fast on ARM |
|
| 62 |
+
| [Download](https://huggingface.co/ysn-rfd/gpt2-xl-conversational-GGUF/resolve/main/gpt2-xl-conversational-q4_k_s.gguf) |  | Fast, recommended |
|
| 63 |
+
| [Download](https://huggingface.co/ysn-rfd/gpt2-xl-conversational-GGUF/resolve/main/gpt2-xl-conversational-q4_k_m.gguf) |  β | Best balance |
|
| 64 |
+
| [Download](https://huggingface.co/ysn-rfd/gpt2-xl-conversational-GGUF/resolve/main/gpt2-xl-conversational-q5_0.gguf) |  | Good quality |
|
| 65 |
+
| [Download](https://huggingface.co/ysn-rfd/gpt2-xl-conversational-GGUF/resolve/main/gpt2-xl-conversational-q5_k_s.gguf) |  | Balanced |
|
| 66 |
+
| [Download](https://huggingface.co/ysn-rfd/gpt2-xl-conversational-GGUF/resolve/main/gpt2-xl-conversational-q5_k_m.gguf) |  | High quality |
|
| 67 |
+
| [Download](https://huggingface.co/ysn-rfd/gpt2-xl-conversational-GGUF/resolve/main/gpt2-xl-conversational-q6_k.gguf) |  π | Very good quality |
|
| 68 |
+
| [Download](https://huggingface.co/ysn-rfd/gpt2-xl-conversational-GGUF/resolve/main/gpt2-xl-conversational-q8_0.gguf) |  β‘ | Fast, best quality |
|
| 69 |
+
| [Download](https://huggingface.co/ysn-rfd/gpt2-xl-conversational-GGUF/resolve/main/gpt2-xl-conversational-f16.gguf) |  | Maximum accuracy |
|
| 70 |
+
|
| 71 |
+
π‘ **Tip:** Use `F16` for maximum precision when quality is critical
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
---
|
| 75 |
+
# π Applications and Tools for Locally Quantized LLMs
|
| 76 |
+
## π₯οΈ Desktop Applications
|
| 77 |
+
|
| 78 |
+
| Application | Description | Download Link |
|
| 79 |
+
|-----------------|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------|
|
| 80 |
+
| **Llama.cpp** | A fast and efficient inference engine for GGUF models. | [GitHub Repository](https://github.com/ggml-org/llama.cpp) |
|
| 81 |
+
| **Ollama** | A streamlined solution for running LLMs locally. | [Website](https://ollama.com/) |
|
| 82 |
+
| **AnythingLLM** | An AI-powered knowledge management tool. | [GitHub Repository](https://github.com/Mintplex-Labs/anything-llm) |
|
| 83 |
+
| **Open WebUI** | A user-friendly web interface for running local LLMs. | [GitHub Repository](https://github.com/open-webui/open-webui) |
|
| 84 |
+
| **GPT4All** | A user-friendly desktop application supporting various LLMs, compatible with GGUF models. | [GitHub Repository](https://github.com/nomic-ai/gpt4all) |
|
| 85 |
+
| **LM Studio** | A desktop application designed to run and manage local LLMs, supporting GGUF format. | [Website](https://lmstudio.ai/) |
|
| 86 |
+
| **GPT4All Chat**| A chat application compatible with GGUF models for local, offline interactions. | [GitHub Repository](https://github.com/nomic-ai/gpt4all) |
|
| 87 |
+
|
| 88 |
+
---
|
| 89 |
+
|
| 90 |
+
## π± Mobile Applications
|
| 91 |
+
|
| 92 |
+
| Application | Description | Download Link |
|
| 93 |
+
|-------------------|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------|
|
| 94 |
+
| **ChatterUI** | A simple and lightweight LLM app for mobile devices. | [GitHub Repository](https://github.com/Vali-98/ChatterUI) |
|
| 95 |
+
| **Maid** | Mobile Artificial Intelligence Distribution for running AI models on mobile devices. | [GitHub Repository](https://github.com/Mobile-Artificial-Intelligence/maid) |
|
| 96 |
+
| **PocketPal AI** | A mobile AI assistant powered by local models. | [GitHub Repository](https://github.com/a-ghorbani/pocketpal-ai) |
|
| 97 |
+
| **Layla** | A flexible platform for running various AI models on mobile devices. | [Website](https://www.layla-network.ai/) |
|
| 98 |
+
|
| 99 |
+
---
|
| 100 |
+
|
| 101 |
+
## π¨ Image Generation Applications
|
| 102 |
+
|
| 103 |
+
| Application | Description | Download Link |
|
| 104 |
+
|-------------------------------------|----------------------------------------------------------------------------------------------|--------------------------------------------------------------------------------|
|
| 105 |
+
| **Stable Diffusion** | An open-source AI model for generating images from text. | [GitHub Repository](https://github.com/CompVis/stable-diffusion) |
|
| 106 |
+
| **Stable Diffusion WebUI** | A web application providing access to Stable Diffusion models via a browser interface. | [GitHub Repository](https://github.com/AUTOMATIC1111/stable-diffusion-webui) |
|
| 107 |
+
| **Local Dream** | Android Stable Diffusion with Snapdragon NPU acceleration. Also supports CPU inference. | [GitHub Repository](https://github.com/xororz/local-dream) |
|
| 108 |
+
| **Stable-Diffusion-Android (SDAI)** | An open-source AI art application for Android devices, enabling digital art creation. | [GitHub Repository](https://github.com/ShiftHackZ/Stable-Diffusion-Android) |
|
| 109 |
+
|
| 110 |
+
---
|
| 111 |
+
|