Instructions to use TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF", dtype="auto")

llama-cpp-python

How to use TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF",
	filename="granite-8b-code-instruct-128k-q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF: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 TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF: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 TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF:Q4_K_M

SGLang

How to use TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF:Q4_K_M
```

Unsloth Studio new

How to use TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF 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 TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF 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 TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF to start chatting

Docker Model Runner
How to use TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.granite-8b-code-instruct-128k-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

TobDeBer commited on Aug 8, 2024

Commit

7c31c9a

verified ·

1 Parent(s): e3dc240

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +119 -0

README.md ADDED Viewed

	@@ -0,0 +1,119 @@

+---
+base_model: ibm-granite/granite-8b-code-instruct-128k
+datasets:
+- bigcode/commitpackft
+- TIGER-Lab/MathInstruct
+- meta-math/MetaMathQA
+- glaiveai/glaive-code-assistant-v3
+- glaive-function-calling-v2
+- bugdaryan/sql-create-context-instruction
+- garage-bAInd/Open-Platypus
+- nvidia/HelpSteer
+- bigcode/self-oss-instruct-sc2-exec-filter-50k
+library_name: transformers
+license: apache-2.0
+metrics:
+- code_eval
+pipeline_tag: text-generation
+tags:
+- code
+- granite
+- llama-cpp
+- gguf-my-repo
+inference: false
+model-index:
+- name: granite-8B-Code-instruct-128k
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEvalSynthesis (Python)
+      type: bigcode/humanevalpack
+    metrics:
+    - type: pass@1
+      value: 62.2
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 51.4
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 38.9
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 38.3
+      name: pass@1
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      name: RepoQA (Python@16K)
+      type: repoqa
+    metrics:
+    - type: pass@1 (thresh=0.5)
+      value: 73.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+    - type: pass@1 (thresh=0.5)
+      value: 37.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+    - type: pass@1 (thresh=0.5)
+      value: 73.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+    - type: pass@1 (thresh=0.5)
+      value: 62.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+    - type: pass@1 (thresh=0.5)
+      value: 63.0
+      name: pass@1 (thresh=0.5)
+      verified: false
+---
+# TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF
+This model was converted to GGUF format from [`ibm-granite/granite-8b-code-instruct-128k`](https://huggingface.co/ibm-granite/granite-8b-code-instruct-128k) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
+Refer to the [original model card](https://huggingface.co/ibm-granite/granite-8b-code-instruct-128k) for more details on the model.
+## Use with llama.cpp
+Install llama.cpp through brew (works on Mac and Linux)
+```bash
+brew install llama.cpp
+```
+Invoke the llama.cpp server or the CLI.
+### CLI:
+```bash
+llama-cli --hf-repo TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF --hf-file granite-8b-code-instruct-128k-q4_k_m.gguf -p "The meaning to life and the universe is"
+```
+### Server:
+```bash
+llama-server --hf-repo TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF --hf-file granite-8b-code-instruct-128k-q4_k_m.gguf -c 2048
+```
+Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
+Step 1: Clone llama.cpp from GitHub.
+```
+git clone https://github.com/ggerganov/llama.cpp
+```
+Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
+```
+cd llama.cpp && LLAMA_CURL=1 make
+```
+Step 3: Run inference through the main binary.
+```
+./llama-cli --hf-repo TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF --hf-file granite-8b-code-instruct-128k-q4_k_m.gguf -p "The meaning to life and the universe is"
+```
+or
+```
+./llama-server --hf-repo TobDeBer/granite-8b-code-instruct-128k-Q4_K_M-GGUF --hf-file granite-8b-code-instruct-128k-q4_k_m.gguf -c 2048
+```