Instructions to use ibm-granite/granite-34b-code-base-8k-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ibm-granite/granite-34b-code-base-8k-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="ibm-granite/granite-34b-code-base-8k-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ibm-granite/granite-34b-code-base-8k-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ibm-granite/granite-34b-code-base-8k-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 ibm-granite/granite-34b-code-base-8k-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ibm-granite/granite-34b-code-base-8k-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ibm-granite/granite-34b-code-base-8k-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ibm-granite/granite-34b-code-base-8k-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 ibm-granite/granite-34b-code-base-8k-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ibm-granite/granite-34b-code-base-8k-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 ibm-granite/granite-34b-code-base-8k-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ibm-granite/granite-34b-code-base-8k-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ibm-granite/granite-34b-code-base-8k-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use ibm-granite/granite-34b-code-base-8k-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ibm-granite/granite-34b-code-base-8k-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ibm-granite/granite-34b-code-base-8k-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ibm-granite/granite-34b-code-base-8k-GGUF:Q4_K_M

SGLang

How to use ibm-granite/granite-34b-code-base-8k-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 "ibm-granite/granite-34b-code-base-8k-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ibm-granite/granite-34b-code-base-8k-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ibm-granite/granite-34b-code-base-8k-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ibm-granite/granite-34b-code-base-8k-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use ibm-granite/granite-34b-code-base-8k-GGUF with Ollama:
```
ollama run hf.co/ibm-granite/granite-34b-code-base-8k-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use ibm-granite/granite-34b-code-base-8k-GGUF with Docker Model Runner:
```
docker model run hf.co/ibm-granite/granite-34b-code-base-8k-GGUF:Q4_K_M
```

Lemonade

How to use ibm-granite/granite-34b-code-base-8k-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ibm-granite/granite-34b-code-base-8k-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.granite-34b-code-base-8k-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

granite-34b-code-base-8k-GGUF / README.md

daviddcox

Update README.md

db10e16 verified 5 months ago

preview code

Raw

History Blame Contribute Delete

5.91 kB

	---
	pipeline_tag: text-generation
	inference: false
	license: apache-2.0
	datasets:
	- codeparrot/github-code-clean
	- bigcode/starcoderdata
	# - Stackexchange
	# - CommonCrawl
	- open-web-math/open-web-math
	- math-ai/StackMathQA
	# - Arxiv
	# - Wikipedia
	# - conceptofmind/FLAN_2022 # Original link is broken, we used IBM's filtered version \| Phase 2
	metrics:
	- code_eval
	library_name: transformers
	tags:
	- code
	- granite
	model-index:
	- name: granite-34b-code-base-8k
	results:
	- task:
	type: text-generation
	dataset:
	type: mbpp
	name: MBPP
	metrics:
	- name: pass@1
	type: pass@1
	value: 47.2
	verified: false
	- task:
	type: text-generation
	dataset:
	type: evalplus/mbppplus
	name: MBPP+
	metrics:
	- name: pass@1
	type: pass@1
	value: 53.1
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalSynthesis(Python)
	metrics:
	- name: pass@1
	type: pass@1
	value: 48.2
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalSynthesis(JavaScript)
	metrics:
	- name: pass@1
	type: pass@1
	value: 54.9
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalSynthesis(Java)
	metrics:
	- name: pass@1
	type: pass@1
	value: 61.6
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalSynthesis(Go)
	metrics:
	- name: pass@1
	type: pass@1
	value: 40.2
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalSynthesis(C++)
	metrics:
	- name: pass@1
	type: pass@1
	value: 50.0
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalSynthesis(Rust)
	metrics:
	- name: pass@1
	type: pass@1
	value: 39.6
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalExplain(Python)
	metrics:
	- name: pass@1
	type: pass@1
	value: 42.7
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalExplain(JavaScript)
	metrics:
	- name: pass@1
	type: pass@1
	value: 26.2
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalExplain(Java)
	metrics:
	- name: pass@1
	type: pass@1
	value: 47.0
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalExplain(Go)
	metrics:
	- name: pass@1
	type: pass@1
	value: 26.8
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalExplain(C++)
	metrics:
	- name: pass@1
	type: pass@1
	value: 36.6
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalExplain(Rust)
	metrics:
	- name: pass@1
	type: pass@1
	value: 25.0
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalFix(Python)
	metrics:
	- name: pass@1
	type: pass@1
	value: 20.1
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalFix(JavaScript)
	metrics:
	- name: pass@1
	type: pass@1
	value: 30.5
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalFix(Java)
	metrics:
	- name: pass@1
	type: pass@1
	value: 40.9
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalFix(Go)
	metrics:
	- name: pass@1
	type: pass@1
	value: 34.1
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalFix(C++)
	metrics:
	- name: pass@1
	type: pass@1
	value: 39.0
	verified: false
	- task:
	type: text-generation
	dataset:
	type: bigcode/humanevalpack
	name: HumanEvalFix(Rust)
	metrics:
	- name: pass@1
	type: pass@1
	value: 12.2
	verified: false
	---

	---

	# ⚠️ DEPRECATION WARNING ⚠️
	# ⚠️ NOT RECOMMENDED FOR USE IN NEW PROJECTS ⚠️

	New applications/projects should use the latest mainline Granite language model family, whose code capabilities supercede this model.
	This model is being made available strictly for historical/scientific purposes.
	Please see our [Granite Collections](https://huggingface.co/ibm-granite/collections) for the latest Granite releases.

	---

	![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd5057674cdb524450093d/1hzxoPwqkBJXshKVVe6_9.png)

	# ibm-granite/granite-34b-code-base-8k-GGUF
	This is the Q4_K_M converted version of the original [`ibm-granite/granite-34b-code-base-8k`](https://huggingface.co/ibm-granite/granite-34b-code-base-8k).
	Refer to the [original model card](https://huggingface.co/ibm-granite/granite-34b-code-base-8k) for more details.

	## Use with llama.cpp
	```shell
	git clone https://github.com/ggerganov/llama.cpp
	cd llama.cpp

	# install
	make

	# run generation
	./main -m granite-34b-code-base-8k-GGUF/granite-34b-code-base.Q4_K_M.gguf -n 128 -p "def generate_random(x: int):" --color
	```