You can deploy this model and start earning money today!

RichardErkhov/
ibm-granite_-_granite-3.0-1b-a400m-instruct-gguf

Name: ibm-granite_-_granite-3.0-1b-a400m-instruct-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

granite-3.0-1b-a400m-instruct - GGUF

Model creator: https://huggingface.co/ibm-granite/
Original model: https://huggingface.co/ibm-granite/granite-3.0-1b-a400m-instruct/

Name	Quant method	Size
granite-3.0-1b-a400m-instruct.Q2_K.gguf	Q2_K	0.48GB
granite-3.0-1b-a400m-instruct.IQ3_XS.gguf	IQ3_XS	0.53GB
granite-3.0-1b-a400m-instruct.IQ3_S.gguf	IQ3_S	0.56GB
granite-3.0-1b-a400m-instruct.Q3_K_S.gguf	Q3_K_S	0.56GB
granite-3.0-1b-a400m-instruct.IQ3_M.gguf	IQ3_M	0.57GB
granite-3.0-1b-a400m-instruct.Q3_K.gguf	Q3_K	0.61GB
granite-3.0-1b-a400m-instruct.Q3_K_M.gguf	Q3_K_M	0.61GB
granite-3.0-1b-a400m-instruct.Q3_K_L.gguf	Q3_K_L	0.66GB
granite-3.0-1b-a400m-instruct.IQ4_XS.gguf	IQ4_XS	0.69GB
granite-3.0-1b-a400m-instruct.Q4_0.gguf	Q4_0	0.72GB
granite-3.0-1b-a400m-instruct.IQ4_NL.gguf	IQ4_NL	0.72GB
granite-3.0-1b-a400m-instruct.Q4_K_S.gguf	Q4_K_S	0.72GB
granite-3.0-1b-a400m-instruct.Q4_K.gguf	Q4_K	0.77GB
granite-3.0-1b-a400m-instruct.Q4_K_M.gguf	Q4_K_M	0.77GB
granite-3.0-1b-a400m-instruct.Q4_1.gguf	Q4_1	0.79GB
granite-3.0-1b-a400m-instruct.Q5_0.gguf	Q5_0	0.86GB
granite-3.0-1b-a400m-instruct.Q5_K_S.gguf	Q5_K_S	0.86GB
granite-3.0-1b-a400m-instruct.Q5_K.gguf	Q5_K	0.89GB
granite-3.0-1b-a400m-instruct.Q5_K_M.gguf	Q5_K_M	0.89GB
granite-3.0-1b-a400m-instruct.Q5_1.gguf	Q5_1	0.94GB
granite-3.0-1b-a400m-instruct.Q6_K.gguf	Q6_K	1.02GB
granite-3.0-1b-a400m-instruct.Q8_0.gguf	Q8_0	1.32GB

Original model description:

pipeline_tag: text-generation inference: false license: apache-2.0 library_name: transformers tags:

language
granite-3.0 model-index:
name: granite-3.0-2b-instruct results:
- task: type: text-generation dataset: type: instruction-following name: IFEval metrics:
  - name: pass@1 type: pass@1 value: 32.39 veriefied: false
- task: type: text-generation dataset: type: instruction-following name: MT-Bench metrics:
  - name: pass@1 type: pass@1 value: 6.17 veriefied: false
- task: type: text-generation dataset: type: human-exams name: AGI-Eval metrics:
  - name: pass@1 type: pass@1 value: 20.35 veriefied: false
- task: type: text-generation dataset: type: human-exams name: MMLU metrics:
  - name: pass@1 type: pass@1 value: 32.00 veriefied: false
- task: type: text-generation dataset: type: human-exams name: MMLU-Pro metrics:
  - name: pass@1 type: pass@1 value: 12.21 veriefied: false
- task: type: text-generation dataset: type: commonsense name: OBQA metrics:
  - name: pass@1 type: pass@1 value: 38.40 veriefied: false
- task: type: text-generation dataset: type: commonsense name: SIQA metrics:
  - name: pass@1 type: pass@1 value: 47.55 veriefied: false
- task: type: text-generation dataset: type: commonsense name: Hellaswag metrics:
  - name: pass@1 type: pass@1 value: 65.59 veriefied: false
- task: type: text-generation dataset: type: commonsense name: WinoGrande metrics:
  - name: pass@1 type: pass@1 value: 61.17 veriefied: false
- task: type: text-generation dataset: type: commonsense name: TruthfulQA metrics:
  - name: pass@1 type: pass@1 value: 49.11 veriefied: false
- task: type: text-generation dataset: type: reading-comprehension name: BoolQ metrics:
  - name: pass@1 type: pass@1 value: 70.12 veriefied: false
- task: type: text-generation dataset: type: reading-comprehension name: SQuAD 2.0 metrics:
  - name: pass@1 type: pass@1 value: 1.27 veriefied: false
- task: type: text-generation dataset: type: reasoning name: ARC-C metrics:
  - name: pass@1 type: pass@1 value: 41.21 veriefied: false
- task: type: text-generation dataset: type: reasoning name: GPQA metrics:
  - name: pass@1 type: pass@1 value: 23.07 veriefied: false
- task: type: text-generation dataset: type: reasoning name: BBH metrics:
  - name: pass@1 type: pass@1 value: 31.77 veriefied: false
- task: type: text-generation dataset: type: code name: HumanEvalSynthesis metrics:
  - name: pass@1 type: pass@1 value: 30.18 veriefied: false
- task: type: text-generation dataset: type: code name: HumanEvalExplain metrics:
  - name: pass@1 type: pass@1 value: 26.22 veriefied: false
- task: type: text-generation dataset: type: code name: HumanEvalFix metrics:
  - name: pass@1 type: pass@1 value: 21.95 veriefied: false
- task: type: text-generation dataset: type: code name: MBPP metrics:
  - name: pass@1 type: pass@1 value: 15.40 veriefied: false
- task: type: text-generation dataset: type: math name: GSM8K metrics:
  - name: pass@1 type: pass@1 value: 26.31 veriefied: false
- task: type: text-generation dataset: type: math name: MATH metrics:
  - name: pass@1 type: pass@1 value: 10.88 veriefied: false
- task: type: text-generation dataset: type: multilingual name: PAWS-X (7 langs) metrics:
  - name: pass@1 type: pass@1 value: 45.84 veriefied: false
- task: type: text-generation dataset: type: multilingual name: MGSM (6 langs) metrics:
  - name: pass@1 type: pass@1 value: 11.80 veriefied: false

Granite-3.0-1B-A400M-Instruct

Model Summary: Granite-3.0-1B-A400M-Instruct is an 1B parameter model finetuned from Granite-3.0-1B-A400M-Base using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets. This model is developed using a diverse set of techniques with a structured chat format, including supervised finetuning, model alignment using reinforcement learning, and model merging.

Developers: Granite Team, IBM
GitHub Repository: ibm-granite/granite-3.0-language-models
Website: Granite Docs
Paper: Granite 3.0 Language Models
Release Date: October 21st, 2024
License: Apache 2.0

Supported Languages: English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. Users may finetune Granite 3.0 models for languages beyond these 12 languages.

Intended use: The model is designed to respond to general instructions and can be used to build AI assistants for multiple domains, including business applications.

Capabilities

Summarization
Text classification
Text extraction
Question-answering
Retrieval Augmented Generation (RAG)
Code related tasks
Function-calling tasks
Multilingual dialog use cases

Generation: This is a simple example of how to use Granite-3.0-1B-A400M-Instruct model.

Install the following libraries:

shell

pip install torch torchvision torchaudio
pip install accelerate
pip install transformers

Then, copy the snippet from the section that is relevant for your use case.

python

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

device = "auto"
model_path = "ibm-granite/granite-3.0-1b-a400m-instruct"
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": "Please list one IBM Research laboratory located in the United States. You should only output its name and location." },
]
chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
# tokenize the text
input_tokens = tokenizer(chat, return_tensors="pt").to(device)
# generate output tokens
output = model.generate(**input_tokens, 
                        max_new_tokens=100)
# decode output tokens into text
output = tokenizer.batch_decode(output)
# print output
print(output)

Model Architecture: Granite-3.0-1B-A400M-Instruct is based on a decoder-only sparse Mixture of Experts (MoE) transformer architecture. Core components of this architecture are: Fine-grained Experts, Dropless Token Routing, and Load Balancing Loss.

Model	2B Dense	8B Dense	1B MoE	3B MoE
Embedding size	2048	4096	1024	1536
Number of layers	40	40	24	32
Attention head size	64	128	64	64
Number of attention heads	32	32	16	24
Number of KV heads	8	8	8	8
MLP hidden size	8192	12800	512	512
MLP activation	SwiGLU	SwiGLU	SwiGLU	SwiGLU
Number of Experts	—	—	32	40
MoE TopK	—	—	8	8
Initialization std	0.1	0.1	0.1	0.1
Sequence Length	4096	4096	4096	4096
Position Embedding	RoPE	RoPE	RoPE	RoPE
# Parameters	2.5B	8.1B	1.3B	3.3B
# Active Parameters	2.5B	8.1B	400M	800M
# Training tokens	12T	12T	10T	10T

Training Data: Overall, our SFT data is largely comprised of three key sources: (1) publicly available datasets with permissive license, (2) internal synthetic data targeting specific capabilities, and (3) very small amounts of human-curated data. A detailed attribution of datasets can be found in the Granite Technical Report and Accompanying Author List.

Infrastructure: We train Granite 3.0 Language Models using IBM's super computing cluster, Blue Vela, which is outfitted with NVIDIA H100 GPUs. This cluster provides a scalable and efficient infrastructure for training our models over thousands of GPUs while minimizing environmental impact by utilizing 100% renewable energy sources.

Ethical Considerations and Limitations: Granite 3.0 Instruct Models are primarily finetuned using instruction-response pairs mostly in English, but also multilingual data covering eleven languages. Although this model can handle multilingual dialog use cases, its performance might not be similar to English tasks. In such case, introducing a small number of examples (few-shot) can help the model in generating more accurate outputs. While this model has been aligned by keeping safety in consideration, the model may in some cases produce inaccurate, biased, or unsafe responses to user prompts. So we urge the community to use this model with proper safety testing and tuning tailored for their specific tasks.

RichardErkhov/ibm-granite_-_granite-3.0-1b-a400m-instruct-gguf

Original model description:

Granite-3.0-1B-A400M-Instruct

RichardErkhov/
ibm-granite_-_granite-3.0-1b-a400m-instruct-gguf