Instructions to use QuantFactory/granite-8b-code-instruct-4k-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/granite-8b-code-instruct-4k-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="QuantFactory/granite-8b-code-instruct-4k-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("QuantFactory/granite-8b-code-instruct-4k-GGUF", dtype="auto")

llama-cpp-python

How to use QuantFactory/granite-8b-code-instruct-4k-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/granite-8b-code-instruct-4k-GGUF",
	filename="granite-8b-code-instruct-4k.Q2_K.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 QuantFactory/granite-8b-code-instruct-4k-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/granite-8b-code-instruct-4k-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/granite-8b-code-instruct-4k-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 QuantFactory/granite-8b-code-instruct-4k-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/granite-8b-code-instruct-4k-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 QuantFactory/granite-8b-code-instruct-4k-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/granite-8b-code-instruct-4k-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 QuantFactory/granite-8b-code-instruct-4k-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/granite-8b-code-instruct-4k-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/granite-8b-code-instruct-4k-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/granite-8b-code-instruct-4k-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantFactory/granite-8b-code-instruct-4k-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": "QuantFactory/granite-8b-code-instruct-4k-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/QuantFactory/granite-8b-code-instruct-4k-GGUF:Q4_K_M

SGLang

How to use QuantFactory/granite-8b-code-instruct-4k-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 "QuantFactory/granite-8b-code-instruct-4k-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": "QuantFactory/granite-8b-code-instruct-4k-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 "QuantFactory/granite-8b-code-instruct-4k-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": "QuantFactory/granite-8b-code-instruct-4k-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use QuantFactory/granite-8b-code-instruct-4k-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/granite-8b-code-instruct-4k-GGUF:Q4_K_M
```

Unsloth Studio new

How to use QuantFactory/granite-8b-code-instruct-4k-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 QuantFactory/granite-8b-code-instruct-4k-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 QuantFactory/granite-8b-code-instruct-4k-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/granite-8b-code-instruct-4k-GGUF to start chatting

Docker Model Runner
How to use QuantFactory/granite-8b-code-instruct-4k-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/granite-8b-code-instruct-4k-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/granite-8b-code-instruct-4k-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/granite-8b-code-instruct-4k-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.granite-8b-code-instruct-4k-GGUF-Q4_K_M

List all available models

lemonade list

munish0838 commited on Sep 7, 2024

Commit

355cb83

verified ·

1 Parent(s): fc5f9a3

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +280 -0

README.md ADDED Viewed

	@@ -0,0 +1,280 @@

+---
+pipeline_tag: text-generation
+base_model: ibm-granite/granite-8b-code-base-4k
+inference: false
+license: apache-2.0
+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
+metrics:
+- code_eval
+library_name: transformers
+tags:
+- code
+- granite
+model-index:
+- name: granite-8b-code-instruct-4k
+  results:
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name: HumanEvalSynthesis(Python)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 57.9
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name: HumanEvalSynthesis(JavaScript)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 52.4
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name: HumanEvalSynthesis(Java)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 58.5
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name: HumanEvalSynthesis(Go)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 43.3
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name: HumanEvalSynthesis(C++)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 48.2
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name: HumanEvalSynthesis(Rust)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 37.2
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name:  HumanEvalExplain(Python)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 53.0
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name:  HumanEvalExplain(JavaScript)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 42.7
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name:  HumanEvalExplain(Java)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 52.4
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name:  HumanEvalExplain(Go)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 36.6
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name:  HumanEvalExplain(C++)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 43.9
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name:  HumanEvalExplain(Rust)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 16.5
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name:  HumanEvalFix(Python)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 39.6
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name:  HumanEvalFix(JavaScript)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 40.9
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name:  HumanEvalFix(Java)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 48.2
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name:  HumanEvalFix(Go)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 41.5
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name:  HumanEvalFix(C++)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 39.0
+      veriefied: false
+  - task:
+      type: text-generation
+    dataset:
+        type: bigcode/humanevalpack
+        name:  HumanEvalFix(Rust)
+    metrics:
+    - name: pass@1
+      type: pass@1
+      value: 32.9
+      veriefied: false
+---
+![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)
+# QuantFactory/granite-8b-code-instruct-4k-GGUF
+This is quantized version of [ibm-granite/granite-8b-code-instruct-4k](https://huggingface.co/ibm-granite/granite-8b-code-instruct-4k) created using llama.cpp
+# Original Model Card
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/62cd5057674cdb524450093d/1hzxoPwqkBJXshKVVe6_9.png)
+# Granite-8B-Code-Instruct-4K
+## Model Summary
+**Granite-8B-Code-Instruct-4K** is a 8B parameter model fine tuned from *Granite-8B-Code-Base-4K* on a combination of **permissively licensed** instruction data to enhance instruction following capabilities including logical reasoning and problem-solving skills.
+- **Developers:** IBM Research
+- **GitHub Repository:** [ibm-granite/granite-code-models](https://github.com/ibm-granite/granite-code-models)
+- **Paper:** [Granite Code Models: A Family of Open Foundation Models for Code Intelligence](https://arxiv.org/abs/2405.04324)
+- **Release Date**: May 6th, 2024
+- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0).
+## Usage
+### Intended use
+The model is designed to respond to coding related instructions and can be used to build coding assistants.
+<!-- TO DO: Check starcoder2 instruct code example that includes the template https://huggingface.co/bigcode/starcoder2-15b-instruct-v0.1 -->
+### Generation
+This is a simple example of how to use **Granite-8B-Code-Instruct-4K** model.
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+device = "cuda" # or "cpu"
+model_path = "ibm-granite/granite-8b-code-instruct-4k"
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+# drop device_map if running on CPU
+model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
+model.eval()
+# change input text as desired
+chat = [
+    { "role": "user", "content": "Write a code to find the maximum value in a list of numbers." },
+]
+chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
+# tokenize the text
+input_tokens = tokenizer(chat, return_tensors="pt")
+# transfer tokenized inputs to the device
+for i in input_tokens:
+    input_tokens[i] = input_tokens[i].to(device)
+# generate output tokens
+output = model.generate(**input_tokens, max_new_tokens=100)
+# decode output tokens into text
+output = tokenizer.batch_decode(output)
+# loop over the batch to print, in this example the batch size is 1
+for i in output:
+    print(i)
+```
+<!-- TO DO: Check this part -->
+## Training Data
+Granite Code Instruct models are trained on the following types of data.
+* Code Commits Datasets: we sourced code commits data from the [CommitPackFT](https://huggingface.co/datasets/bigcode/commitpackft) dataset, a filtered version of the full CommitPack dataset. From CommitPackFT dataset, we only consider data for 92 programming languages. Our inclusion criteria boils down to selecting programming languages common across CommitPackFT and the 116 languages that we considered to pretrain the code-base model (*Granite-8B-Code-Base*).
+* Math Datasets: We consider two high-quality math datasets, [MathInstruct](https://huggingface.co/datasets/TIGER-Lab/MathInstruct) and [MetaMathQA](https://huggingface.co/datasets/meta-math/MetaMathQA). Due to license issues, we filtered out GSM8K-RFT and Camel-Math from MathInstruct dataset.
+* Code Instruction Datasets: We use [Glaive-Code-Assistant-v3](https://huggingface.co/datasets/glaiveai/glaive-code-assistant-v3), [Glaive-Function-Calling-v2](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2), [NL2SQL11](https://huggingface.co/datasets/bugdaryan/sql-create-context-instruction) and a small collection of synthetic API calling datasets.
+* Language Instruction Datasets: We include high-quality datasets such as [HelpSteer](https://huggingface.co/datasets/nvidia/HelpSteer) and an open license-filtered version of [Platypus](https://huggingface.co/datasets/garage-bAInd/Open-Platypus). We also include a collection of hardcoded prompts to ensure our model generates correct outputs given inquiries about its name or developers.
+## Infrastructure
+We train the Granite Code models using two of IBM's super computing clusters, namely Vela and Blue Vela, both outfitted with NVIDIA A100 and H100 GPUs respectively. These clusters provide a scalable and efficient infrastructure for training our models over thousands of GPUs.
+## Ethical Considerations and Limitations
+Granite code instruct models are primarily finetuned using instruction-response pairs across a specific set of programming languages. Thus, their performance may be limited with out-of-domain programming languages. In this situation, it is beneficial providing few-shot examples to steer the model's output. Moreover, developers should perform safety testing and target-specific tuning before deploying these models on critical applications. The model also inherits ethical considerations and limitations from its base model. For more information, please refer to *[Granite-8B-Code-Base-4K](https://huggingface.co/ibm-granite/granite-8b-code-base-4k)* model card.