Instructions to use Parth673/gemma3-4b-interview-eval-quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use Parth673/gemma3-4b-interview-eval-quantized with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Parth673/gemma3-4b-interview-eval-quantized", filename="gemma-3-4b-it.F16-mmproj.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use Parth673/gemma3-4b-interview-eval-quantized with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Parth673/gemma3-4b-interview-eval-quantized:F16 # Run inference directly in the terminal: llama-cli -hf Parth673/gemma3-4b-interview-eval-quantized:F16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Parth673/gemma3-4b-interview-eval-quantized:F16 # Run inference directly in the terminal: llama-cli -hf Parth673/gemma3-4b-interview-eval-quantized:F16
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 Parth673/gemma3-4b-interview-eval-quantized:F16 # Run inference directly in the terminal: ./llama-cli -hf Parth673/gemma3-4b-interview-eval-quantized:F16
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 Parth673/gemma3-4b-interview-eval-quantized:F16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf Parth673/gemma3-4b-interview-eval-quantized:F16
Use Docker
docker model run hf.co/Parth673/gemma3-4b-interview-eval-quantized:F16
- LM Studio
- Jan
- Ollama
How to use Parth673/gemma3-4b-interview-eval-quantized with Ollama:
ollama run hf.co/Parth673/gemma3-4b-interview-eval-quantized:F16
- Unsloth Studio new
How to use Parth673/gemma3-4b-interview-eval-quantized 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 Parth673/gemma3-4b-interview-eval-quantized 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 Parth673/gemma3-4b-interview-eval-quantized to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Parth673/gemma3-4b-interview-eval-quantized to start chatting
- Docker Model Runner
How to use Parth673/gemma3-4b-interview-eval-quantized with Docker Model Runner:
docker model run hf.co/Parth673/gemma3-4b-interview-eval-quantized:F16
- Lemonade
How to use Parth673/gemma3-4b-interview-eval-quantized with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Parth673/gemma3-4b-interview-eval-quantized:F16
Run and chat with the model
lemonade run user.gemma3-4b-interview-eval-quantized-F16
List all available models
lemonade list
Trained with Unsloth - Ollama Modelfile
Browse files
Modelfile
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
FROM .
|
| 3 |
+
TEMPLATE """{{- range $i, $_ := .Messages }}
|
| 4 |
+
{{- $last := eq (len (slice $.Messages $i)) 1 }}
|
| 5 |
+
{{- if or (eq .Role "user") (eq .Role "system") }}<start_of_turn>user
|
| 6 |
+
{{ .Content }}<end_of_turn>
|
| 7 |
+
{{ if $last }}<start_of_turn>model
|
| 8 |
+
{{ end }}
|
| 9 |
+
{{- else if eq .Role "assistant" }}<start_of_turn>model
|
| 10 |
+
{{ .Content }}{{ if not $last }}<end_of_turn>
|
| 11 |
+
{{ end }}
|
| 12 |
+
{{- end }}
|
| 13 |
+
{{- end }}"""
|
| 14 |
+
PARAMETER stop "<end_of_turn>"
|
| 15 |
+
PARAMETER stop "<eos>"
|
| 16 |
+
PARAMETER temperature 1.0
|
| 17 |
+
PARAMETER min_p 0.0
|
| 18 |
+
PARAMETER top_k 64
|
| 19 |
+
PARAMETER top_p 0.95
|
| 20 |
+
PARAMETER num_predict 32768
|