Reinforcement Learning
Transformers
GGUF
Chinese
English
incremental-pretraining
sft
roleplay
cot
conversational
Instructions to use ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4", dtype="auto") - llama-cpp-python
How to use ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4 with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4", filename="Tifa-DeepsexV2-7b-0218-Q4_KM.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4 with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4 # Run inference directly in the terminal: llama-cli -hf ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4 # Run inference directly in the terminal: llama-cli -hf ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4 # Run inference directly in the terminal: ./llama-cli -hf ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4 # Run inference directly in the terminal: ./build/bin/llama-cli -hf ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4
Use Docker
docker model run hf.co/ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4
- LM Studio
- Jan
- Ollama
How to use ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4 with Ollama:
ollama run hf.co/ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4
- Unsloth Studio
How to use ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4 with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4 to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4 to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4 to start chatting
- Atomic Chat new
- Docker Model Runner
How to use ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4 with Docker Model Runner:
docker model run hf.co/ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4
- Lemonade
How to use ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4
Run and chat with the model
lemonade run user.Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4-{{QUANT_TAG}}List all available models
lemonade list
练好了吗?为啥不更新模型了
#27 opened about 1 year ago
by
einsflash
求求适配LM Studio
1
#26 opened about 1 year ago
by
Ptene
角色扮演实习/校招/社招
#25 opened about 1 year ago
by
xianghuang
想问一下文学性那个reard,是计算了embedding相似度吗?
#24 opened about 1 year ago
by
ClosedCharacter
Translation
#22 opened over 1 year ago
by
Ainonake
🚩 Report: Legal issue(s)
1
#21 opened over 1 year ago
by deleted
官网的大号Tifa模型实际上是Claude API,您为何要谎称您有大模型?
22
#20 opened over 1 year ago
by deleted
询问一下,如何增加单次生成字数上限,目前我看到的大概在1500字左右
1
#19 opened over 1 year ago
by
woodnoah
Tifa-DeepsexV2-7b 在 Ollama 中回复内容异常/无法停止/无效的终止
2
#18 opened over 1 year ago
by
AXxx2
关于 tokenizer 文件
2
#17 opened over 1 year ago
by
evpeople
感觉相比V1存在严重的不听话现象
🤝 2
4
#16 opened over 1 year ago
by
Ayssia114514
建议用Qwen2-7B-Multilingual-RP做为底模
🔥 3
4
#15 opened over 1 year ago
by
jab0688
非常好模型,使我的显卡旋转
1
#14 opened over 1 year ago
by
HuanLin
我是猫娘,我来给模型打好评
1
#13 opened over 1 year ago
by
dakkidaze
我的牛牛来写好评了啊😋
#12 opened over 1 year ago
by
baicai1145
简单测试了一下,效果非常棒
#11 opened over 1 year ago
by
panlilu
能否提供Q6_K的量化文件?
🔥 2
3
#10 opened over 1 year ago
by
lingyezhixing
在SillyTavern中使用该模型
👍 1
5
#9 opened over 1 year ago
by
evpeople
谢谢作者的辛勤更新,辛苦了,广大写瑟文的男女同志向你致敬!请问这个模型可以联网吗?放进LMstudio里面就可以联网了吗?
#8 opened over 1 year ago
by
Lzbcbeef114514
感谢上传!请问这个版本是否还需要在前端手动去除思考标记?
5
#7 opened over 1 year ago
by
ImpulseInput
MGRPO与层传播訓練會開源嗎?
3
#6 opened over 1 year ago
by
win10
啊啊只发量化版本的吗
3
#5 opened over 1 year ago
by
Alexyz74
即使按美国时间,情人节也要结束了。T.T
2
#4 opened over 1 year ago
by
RavenRock