Instructions to use SagarKaul/codeast_q4_intel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SagarKaul/codeast_q4_intel with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SagarKaul/codeast_q4_intel",
	filename="codeast.Q4_K_M.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 SagarKaul/codeast_q4_intel with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SagarKaul/codeast_q4_intel:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SagarKaul/codeast_q4_intel:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SagarKaul/codeast_q4_intel:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SagarKaul/codeast_q4_intel:Q4_K_M

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 SagarKaul/codeast_q4_intel:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SagarKaul/codeast_q4_intel:Q4_K_M

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 SagarKaul/codeast_q4_intel:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SagarKaul/codeast_q4_intel:Q4_K_M

Use Docker

docker model run hf.co/SagarKaul/codeast_q4_intel:Q4_K_M

LM Studio
Jan
Ollama
How to use SagarKaul/codeast_q4_intel with Ollama:
```
ollama run hf.co/SagarKaul/codeast_q4_intel:Q4_K_M
```

Unsloth Studio new

How to use SagarKaul/codeast_q4_intel 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 SagarKaul/codeast_q4_intel 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 SagarKaul/codeast_q4_intel to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SagarKaul/codeast_q4_intel to start chatting

Docker Model Runner
How to use SagarKaul/codeast_q4_intel with Docker Model Runner:
```
docker model run hf.co/SagarKaul/codeast_q4_intel:Q4_K_M
```

Lemonade

How to use SagarKaul/codeast_q4_intel with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SagarKaul/codeast_q4_intel:Q4_K_M

Run and chat with the model

lemonade run user.codeast_q4_intel-Q4_K_M

List all available models

lemonade list

SagarKaul commited on Oct 2, 2024

Commit

be37055

verified ·

1 Parent(s): 3f70560

Upload ModelFile - Copy

Browse files

Files changed (1) hide show

ModelFile - Copy +27 -0

ModelFile - Copy ADDED Viewed

	@@ -0,0 +1,27 @@

+FROM codeast.Q4_K_M.gguf
+TEMPLATE """{{ if .System }}{{ .System }}
+{{ end }}
+### Instruction:
+Please add comments to code
+{{ if .Prompt }}### Input:
+{{ .Prompt }}{{ end }}
+### Response:"""
+PARAMETER temperature 0
+PARAMETER repeat_penalty 1
+PARAMETER penalize_newline false
+PARAMETER stop <|start_header_id|>
+PARAMETER stop <|end_header_id|>
+PARAMETER stop <|eot_id|>
+PARAMETER stop <|reserved_special_token|>
+PARAMETER stop <|end_of_text|>
+PARAMETER stop <eos>
+PARAMETER stop <|eos|>
+SYSTEM "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request."