TheBloke/dopeystableplats-3b-v1-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Upload README.md

Browse Source
This commit is contained in:
ai-modelscope
2025-02-08 22:37:22 +08:00
parent 6863f77648
commit d5e91c6d02
16 changed files with 393 additions and 56 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
.gitattributes vendored
View File

@@ -1,47 +1,47 @@
*.7z filter=lfs diff=lfs merge=lfs -text *.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text *.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text *.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 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 *.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text *.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text *.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text *.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* 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 *.model filter=lfs diff=lfs merge=lfs -text
*.msgpack 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 *.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text *.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text *.parquet filter=lfs diff=lfs merge=lfs -text
*.pb 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 *.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text *.pth filter=lfs diff=lfs merge=lfs -text
*.rar 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 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
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text *.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz 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 *.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text
dopeystableplats-3b-v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
dopeystableplats-3b-v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
dopeystableplats-3b-v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
dopeystableplats-3b-v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
dopeystableplats-3b-v1.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
dopeystableplats-3b-v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
dopeystableplats-3b-v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
dopeystableplats-3b-v1.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
dopeystableplats-3b-v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
dopeystableplats-3b-v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
dopeystableplats-3b-v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
dopeystableplats-3b-v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

365
README.md
View File

@@ -1,47 +1,344 @@
--- ---
license: Apache License 2.0 base_model: vihangd/dopeystableplats-3b-v1
inference: false
license: cc-by-sa-4.0
model_creator: Vihang D
model_name: Dopeystableplats 3B v1
model_type: stablelm
prompt_template: 'Below is an instruction that describes a task. Write a response
that appropriately completes the request.
#model-type:
##如 gpt、phi、llama、chatglm、baichuan 等
#- gpt
#domain: ### Instruction:
##如 nlp、cv、audio、multi-modal
#- nlp
#language: {prompt}
##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
#- cn
#metrics:
##如 CIDEr、Blue、ROUGE 等
#- CIDEr
#tags: ### Response:
##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
#- pretrained
#tools: '
##如 vllm、fastchat、llamacpp、AdaSeq 等 quantized_by: TheBloke
#- vllm
--- ---
### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。 <!-- markdownlint-disable MD041 -->
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->
# Dopeystableplats 3B v1 - GGUF
- Model creator: [Vihang D](https://huggingface.co/vihangd)
- Original model: [Dopeystableplats 3B v1](https://huggingface.co/vihangd/dopeystableplats-3b-v1)
<!-- description start -->
## Description
This repo contains GGUF format model files for [Vihang D's Dopeystableplats 3B v1](https://huggingface.co/vihangd/dopeystableplats-3b-v1).
These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
<!-- description end -->
<!-- README_GGUF.md-about-gguf start -->
### About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.
<!-- README_GGUF.md-about-gguf end -->
<!-- repositories-available start -->
## Repositories available
* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/dopeystableplats-3b-v1-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/dopeystableplats-3b-v1-GGUF)
* [Vihang D's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/vihangd/dopeystableplats-3b-v1)
<!-- repositories-available end -->
<!-- prompt-template start -->
## Prompt template: Alpaca
SDK下载
```bash
#安装ModelScope
pip install modelscope
``` ```
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
```
<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
## Explanation of quantisation methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->
<!-- README_GGUF.md-provided-files start -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [dopeystableplats-3b-v1.Q2_K.gguf](https://huggingface.co/TheBloke/dopeystableplats-3b-v1-GGUF/blob/main/dopeystableplats-3b-v1.Q2_K.gguf) | Q2_K | 2 | 1.20 GB| 3.70 GB | smallest, significant quality loss - not recommended for most purposes |
| [dopeystableplats-3b-v1.Q3_K_S.gguf](https://huggingface.co/TheBloke/dopeystableplats-3b-v1-GGUF/blob/main/dopeystableplats-3b-v1.Q3_K_S.gguf) | Q3_K_S | 3 | 1.25 GB| 3.75 GB | very small, high quality loss |
| [dopeystableplats-3b-v1.Q3_K_M.gguf](https://huggingface.co/TheBloke/dopeystableplats-3b-v1-GGUF/blob/main/dopeystableplats-3b-v1.Q3_K_M.gguf) | Q3_K_M | 3 | 1.39 GB| 3.89 GB | very small, high quality loss |
| [dopeystableplats-3b-v1.Q3_K_L.gguf](https://huggingface.co/TheBloke/dopeystableplats-3b-v1-GGUF/blob/main/dopeystableplats-3b-v1.Q3_K_L.gguf) | Q3_K_L | 3 | 1.51 GB| 4.01 GB | small, substantial quality loss |
| [dopeystableplats-3b-v1.Q4_0.gguf](https://huggingface.co/TheBloke/dopeystableplats-3b-v1-GGUF/blob/main/dopeystableplats-3b-v1.Q4_0.gguf) | Q4_0 | 4 | 1.61 GB| 4.11 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [dopeystableplats-3b-v1.Q4_K_S.gguf](https://huggingface.co/TheBloke/dopeystableplats-3b-v1-GGUF/blob/main/dopeystableplats-3b-v1.Q4_K_S.gguf) | Q4_K_S | 4 | 1.62 GB| 4.12 GB | small, greater quality loss |
| [dopeystableplats-3b-v1.Q4_K_M.gguf](https://huggingface.co/TheBloke/dopeystableplats-3b-v1-GGUF/blob/main/dopeystableplats-3b-v1.Q4_K_M.gguf) | Q4_K_M | 4 | 1.71 GB| 4.21 GB | medium, balanced quality - recommended |
| [dopeystableplats-3b-v1.Q5_0.gguf](https://huggingface.co/TheBloke/dopeystableplats-3b-v1-GGUF/blob/main/dopeystableplats-3b-v1.Q5_0.gguf) | Q5_0 | 5 | 1.94 GB| 4.44 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [dopeystableplats-3b-v1.Q5_K_S.gguf](https://huggingface.co/TheBloke/dopeystableplats-3b-v1-GGUF/blob/main/dopeystableplats-3b-v1.Q5_K_S.gguf) | Q5_K_S | 5 | 1.94 GB| 4.44 GB | large, low quality loss - recommended |
| [dopeystableplats-3b-v1.Q5_K_M.gguf](https://huggingface.co/TheBloke/dopeystableplats-3b-v1-GGUF/blob/main/dopeystableplats-3b-v1.Q5_K_M.gguf) | Q5_K_M | 5 | 1.99 GB| 4.49 GB | large, very low quality loss - recommended |
| [dopeystableplats-3b-v1.Q6_K.gguf](https://huggingface.co/TheBloke/dopeystableplats-3b-v1-GGUF/blob/main/dopeystableplats-3b-v1.Q6_K.gguf) | Q6_K | 6 | 2.30 GB| 4.80 GB | very large, extremely low quality loss |
| [dopeystableplats-3b-v1.Q8_0.gguf](https://huggingface.co/TheBloke/dopeystableplats-3b-v1-GGUF/blob/main/dopeystableplats-3b-v1.Q8_0.gguf) | Q8_0 | 8 | 2.97 GB| 5.47 GB | very large, extremely low quality loss - not recommended |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->
<!-- README_GGUF.md-how-to-download start -->
## How to download GGUF files
**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
* LM Studio
* LoLLMS Web UI
* Faraday.dev
### In `text-generation-webui`
Under Download Model, you can enter the model repo: TheBloke/dopeystableplats-3b-v1-GGUF and below it, a specific filename to download, such as: dopeystableplats-3b-v1.Q4_K_M.gguf.
Then click Download.
### On the command line, including multiple files at once
I recommend using the `huggingface-hub` Python library:
```shell
pip3 install huggingface-hub
```
Then you can download any individual model file to the current directory, at high speed, with a command like this:
```shell
huggingface-cli download TheBloke/dopeystableplats-3b-v1-GGUF dopeystableplats-3b-v1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
<details>
<summary>More advanced huggingface-cli download usage (click to read)</summary>
You can also download multiple files at once with a pattern:
```shell
huggingface-cli download TheBloke/dopeystableplats-3b-v1-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).
To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:
```shell
pip3 install hf_transfer
```
And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:
```shell
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/dopeystableplats-3b-v1-GGUF dopeystableplats-3b-v1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False
```
Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
</details>
<!-- README_GGUF.md-how-to-download end -->
<!-- README_GGUF.md-how-to-run start -->
## Example `llama.cpp` command
Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
```shell
./main -ngl 35 -m dopeystableplats-3b-v1.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"
```
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)
## How to run in `text-generation-webui`
Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp).
## How to run from Python code
You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.
### How to load this model in Python code, using llama-cpp-python
For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/).
#### First install the package
Run one of the following commands, according to your system:
```shell
# Base ctransformers with no GPU acceleration
pip install llama-cpp-python
# With NVidia CUDA acceleration
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
# Or with OpenBLAS acceleration
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
# Or with CLBLast acceleration
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
# Or with AMD ROCm GPU acceleration (Linux only)
CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python
# Or with Metal GPU acceleration for macOS systems only
CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python
# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
pip install llama-cpp-python
```
#### Simple llama-cpp-python example code
```python ```python
#SDK模型下载 from llama_cpp import Llama
from modelscope import snapshot_download
model_dir = snapshot_download('TheBloke/dopeystableplats-3b-v1-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(
Git下载 model_path="./dopeystableplats-3b-v1.Q4_K_M.gguf", # Download the model file first
``` n_ctx=4096, # The max sequence length to use - note that longer sequence lengths require much more resources
#Git模型下载 n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance
git clone https://www.modelscope.cn/TheBloke/dopeystableplats-3b-v1-GGUF.git n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available
)
# Simple inference example
output = llm(
"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:", # Prompt
max_tokens=512, # Generate up to 512 tokens
stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using.
echo=True # Whether to echo the prompt
)
# Chat Completion API
llm = Llama(model_path="./dopeystableplats-3b-v1.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using
llm.create_chat_completion(
messages = [
{"role": "system", "content": "You are a story writing assistant."},
{
"role": "user",
"content": "Write a story about llamas."
}
]
)
``` ```
<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p> ## How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)
* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)
<!-- README_GGUF.md-how-to-run end -->
<!-- footer start -->
<!-- 200823 -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute
Thanks to the [chirper.ai](https://chirper.ai) team!
Thanks to Clay from [gpus.llm-utils.org](llm-utils)!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Aemon Algiz.
**Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
<!-- footer end -->
<!-- original-model-card start -->
# Original model card: Vihang D's Dopeystableplats 3B v1
<p><h1> DopeyStablePlats-3b-v1 </h1></p>
An experimental finetune of StableLM-3B-4E1T with Alpaca-QLoRA with some DPO goodness
<h2> Datasets </h2>
Trained on alpca style datasets
<p><h2> Prompt Template </h2></p>
Uses alpaca style prompt template
<!-- original-model-card end -->

3
config.json Normal file
View File

@@ -0,0 +1,3 @@
{
"model_type": "stablelm"
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "others", "allow_remote": true}

3
dopeystableplats-3b-v1.Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4196268fb023a86dfe18503fdb01d5c32c8e465170feca917ce985b8a3ea4bd1
size 1198771200

3
dopeystableplats-3b-v1.Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:25dc1fd34b4dd67460b14608e3d45b0845627872c23e902d0d589ac89edbdced
size 1508564480

3
dopeystableplats-3b-v1.Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6f97e6cf484636be5908fd2c35a9034c925bc0c4aee98ae290e66b343789ace9
size 1391418880

3
dopeystableplats-3b-v1.Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:22d9ec244838f7be816e1bc76997986409e40d1bcac6b17c6c848141f487b617
size 1254448640

3
dopeystableplats-3b-v1.Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1f7d43c0bcc45c592a8d6017ef061d9e44210e84183f10b2edebb7b3c6813b68
size 1608570880

3
dopeystableplats-3b-v1.Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:420ebc984bb7116e1bb99a56746544f78be8e1d5ce0e4e12838a145a0599651d
size 1708595200

3
dopeystableplats-3b-v1.Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:85fdcf319f93092e8ed3c5fe5dc5baea74d369863bbe86a061fae224e557d26e
size 1620695040

3
dopeystableplats-3b-v1.Q5_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1a759b25dbf74fb60bbfa660fba5761956e466d7fbefac88da2caca7b08cf25b
size 1941862400

3
dopeystableplats-3b-v1.Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2bd3b796f6dbe320dc09f9d813da71a4c7542430738d8b496d07d1bcc500bf41
size 1993390080

3
dopeystableplats-3b-v1.Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4cc21a9b2382b5a83611eae509dcf9319c5b035151f8115965483efed0cc3514
size 1941862400

3
dopeystableplats-3b-v1.Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d992e25bb8c70651792c7a1b49590dca972aa9c05de1d2a12755e8ec7ac91e1b
size 2295984640

3
dopeystableplats-3b-v1.Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fd449dcf4fffb5a3ed0caf10f79bb9836feb875922c86c981189b9f515806b3e
size 2972925440