Instructions to use NoCanGo/WaifuGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use NoCanGo/WaifuGPT with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf NoCanGo/WaifuGPT:Q8_0 # Run inference directly in the terminal: llama cli -hf NoCanGo/WaifuGPT:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf NoCanGo/WaifuGPT:Q8_0 # Run inference directly in the terminal: llama cli -hf NoCanGo/WaifuGPT:Q8_0
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 NoCanGo/WaifuGPT:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf NoCanGo/WaifuGPT:Q8_0
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 NoCanGo/WaifuGPT:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf NoCanGo/WaifuGPT:Q8_0
Use Docker
docker model run hf.co/NoCanGo/WaifuGPT:Q8_0
- LM Studio
- Jan
- Ollama
How to use NoCanGo/WaifuGPT with Ollama:
ollama run hf.co/NoCanGo/WaifuGPT:Q8_0
- Unsloth Studio
How to use NoCanGo/WaifuGPT 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 NoCanGo/WaifuGPT 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 NoCanGo/WaifuGPT to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for NoCanGo/WaifuGPT to start chatting
- Docker Model Runner
How to use NoCanGo/WaifuGPT with Docker Model Runner:
docker model run hf.co/NoCanGo/WaifuGPT:Q8_0
- Lemonade
How to use NoCanGo/WaifuGPT with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull NoCanGo/WaifuGPT:Q8_0
Run and chat with the model
lemonade run user.WaifuGPT-Q8_0
List all available models
lemonade list
- Atomic Chat
(Trained with Unsloth)
Browse files
Modelfile
CHANGED
|
@@ -1,57 +1,17 @@
|
|
|
|
|
| 1 |
|
| 2 |
-
|
| 3 |
-
TEMPLATE """{{ if .Messages }}
|
| 4 |
-
{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|>
|
| 5 |
-
{{- if .System }}
|
| 6 |
|
| 7 |
-
|
| 8 |
-
{{
|
| 9 |
-
{{- if .Tools }}
|
| 10 |
|
| 11 |
-
|
| 12 |
-
{{
|
| 13 |
-
{{- end }}<|eot_id|>
|
| 14 |
-
{{- range $i, $_ := .Messages }}
|
| 15 |
-
{{- $last := eq (len (slice $.Messages $i)) 1 }}
|
| 16 |
-
{{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|>
|
| 17 |
-
{{- if and $.Tools $last }}
|
| 18 |
|
| 19 |
-
Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
|
| 20 |
-
|
| 21 |
-
Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
|
| 22 |
-
|
| 23 |
-
{{ $.Tools }}
|
| 24 |
-
{{- end }}
|
| 25 |
-
|
| 26 |
-
{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
|
| 27 |
-
|
| 28 |
-
{{ end }}
|
| 29 |
-
{{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|>
|
| 30 |
-
{{- if .ToolCalls }}
|
| 31 |
-
|
| 32 |
-
{{- range .ToolCalls }}{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }}
|
| 33 |
-
{{- else }}
|
| 34 |
-
|
| 35 |
-
{{ .Content }}{{ if not $last }}<|eot_id|>{{ end }}
|
| 36 |
-
{{- end }}
|
| 37 |
-
{{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|>
|
| 38 |
-
|
| 39 |
-
{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
|
| 40 |
-
|
| 41 |
-
{{ end }}
|
| 42 |
-
{{- end }}
|
| 43 |
-
{{- end }}
|
| 44 |
-
{{- else }}
|
| 45 |
-
{{- if .System }}<|start_header_id|>system<|end_header_id|>
|
| 46 |
-
|
| 47 |
-
{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
|
| 48 |
-
|
| 49 |
-
{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
|
| 50 |
-
|
| 51 |
-
{{ end }}{{ .Response }}{{ if .Response }}<|eot_id|>{{ end }}"""
|
| 52 |
-
PARAMETER stop "<|start_header_id|>"
|
| 53 |
PARAMETER stop "<|end_header_id|>"
|
| 54 |
PARAMETER stop "<|eot_id|>"
|
| 55 |
-
PARAMETER stop "<|
|
|
|
|
|
|
|
| 56 |
PARAMETER temperature 1.5
|
| 57 |
PARAMETER min_p 0.1
|
|
|
|
| 1 |
+
FROM /content/NoCanGo/animegpt/unsloth.Q8_0.gguf
|
| 2 |
|
| 3 |
+
TEMPLATE """Below are some instructions that describe some tasks. Write responses that appropriately complete each request.{{ if .Prompt }}
|
|
|
|
|
|
|
|
|
|
| 4 |
|
| 5 |
+
### Instruction:
|
| 6 |
+
{{ .Prompt }}{{ end }}
|
|
|
|
| 7 |
|
| 8 |
+
### Response:
|
| 9 |
+
{{ .Response }}<|end_of_text|>"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
PARAMETER stop "<|end_header_id|>"
|
| 12 |
PARAMETER stop "<|eot_id|>"
|
| 13 |
+
PARAMETER stop "<|start_header_id|>"
|
| 14 |
+
PARAMETER stop "<|end_of_text|>"
|
| 15 |
+
PARAMETER stop "<|reserved_special_token_"
|
| 16 |
PARAMETER temperature 1.5
|
| 17 |
PARAMETER min_p 0.1
|