Instructions to use Rohanify/PyBlissa-Coder-40M-GGUF 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 Rohanify/PyBlissa-Coder-40M-GGUF 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 Rohanify/PyBlissa-Coder-40M-GGUF:F32 # Run inference directly in the terminal: llama cli -hf Rohanify/PyBlissa-Coder-40M-GGUF:F32
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Rohanify/PyBlissa-Coder-40M-GGUF:F32 # Run inference directly in the terminal: llama cli -hf Rohanify/PyBlissa-Coder-40M-GGUF:F32
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf Rohanify/PyBlissa-Coder-40M-GGUF:F32 # Run inference directly in the terminal: ./build/bin/llama cli -hf Rohanify/PyBlissa-Coder-40M-GGUF:F32
Use Docker
docker model run hf.co/Rohanify/PyBlissa-Coder-40M-GGUF:F32
- Llama new
- LM Studio
- Jan
- vLLM
How to use Rohanify/PyBlissa-Coder-40M-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Rohanify/PyBlissa-Coder-40M-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Rohanify/PyBlissa-Coder-40M-GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Rohanify/PyBlissa-Coder-40M-GGUF:F32
- Ollama
How to use Rohanify/PyBlissa-Coder-40M-GGUF with Ollama:
ollama run hf.co/Rohanify/PyBlissa-Coder-40M-GGUF:F32
- Unsloth Desktop
- Docker Model Runner
How to use Rohanify/PyBlissa-Coder-40M-GGUF with Docker Model Runner:
docker model run hf.co/Rohanify/PyBlissa-Coder-40M-GGUF:F32
- Lemonade
How to use Rohanify/PyBlissa-Coder-40M-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Rohanify/PyBlissa-Coder-40M-GGUF:F32
Run and chat with the model
lemonade run user.PyBlissa-Coder-40M-GGUF-F32
List all available models
lemonade list
- Atomic Chat
Ollama-related files + Images
Browse files- .gitattributes +2 -0
- Modelfile +13 -0
- params +11 -0
- pyblissa_banner.png +3 -0
- pyblissa_loss_curve.png +3 -0
- template +2 -0
.gitattributes
CHANGED
|
@@ -34,3 +34,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
PyBlissa-V2-F32.gguf filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
PyBlissa-V2-F32.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
pyblissa_banner.png filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
pyblissa_loss_curve.png filter=lfs diff=lfs merge=lfs -text
|
Modelfile
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
FROM ./PyBlissa-V2-F32.gguf
|
| 2 |
+
|
| 3 |
+
TEMPLATE """PROMPT: {{ .Prompt }}
|
| 4 |
+
CODE:
|
| 5 |
+
"""
|
| 6 |
+
|
| 7 |
+
PARAMETER temperature 0.3
|
| 8 |
+
PARAMETER top_k 10
|
| 9 |
+
PARAMETER stop "<|endoftext|>"
|
| 10 |
+
PARAMETER stop "PROMPT:"
|
| 11 |
+
PARAMETER repeat_penalty 1.25
|
| 12 |
+
PARAMETER num_ctx 512
|
| 13 |
+
PARAMETER num_predict 512
|
params
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"temperature": 0.3,
|
| 3 |
+
"top_k": 10,
|
| 4 |
+
"repeat_penalty": 1.25,
|
| 5 |
+
"num_ctx": 512,
|
| 6 |
+
"num_predict": 512,
|
| 7 |
+
"stop": [
|
| 8 |
+
"<|endoftext|>",
|
| 9 |
+
"PROMPT:"
|
| 10 |
+
]
|
| 11 |
+
}
|
pyblissa_banner.png
ADDED
|
Git LFS Details
|
pyblissa_loss_curve.png
ADDED
|
Git LFS Details
|
template
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
PROMPT: {{ .Prompt }}
|
| 2 |
+
CODE:
|