Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.
Sources
Badge
Host
Last check
Result
From source
huggingface.co
2026-11-15 04:14 UTC
passed
Model card
From the publisher at commit 4e749a2. Shown as plain text with links; images open at the publisher.
Model Summary:
This model is part of the GneissWeb ablations, detailed in this technical report. The model has 7 billion parameters and uses the LLama architecture. It is trained on a random subset of 350 billion English tokens from GneissWeb, tokenized using the StarCoder tokenizer.
Developers: IBM Research
Release Date: Feb 25th, 2025
License: Apache 2.0
Intended Use:
This model is trained on 350B tokens of GneissWeb data and is not instruction-tuned or safety aligned. It is important to note that the primary intended use case for this model is to compare its performance with other models trained under similar conditions, with the goal of comparing pre-training datasets. These other models are mentioned here
Generation:
This is a simple example of how to use GneissWeb.7B_ablation_model_on_350B_GneissWeb.seed3 model.
Then, copy the code snippet below to run the example.
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "auto"
model_path = "ibm-granite/GneissWeb.7B_ablation_model_on_350B_GneissWeb.seed3"
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
input_text = "What is the meaning of 'Gneiss'?"
# tokenize the text
input_tokens = tokenizer(input_text, return_tensors="pt").to('cuda')
# generate output tokens
output = model.generate(**input_tokens,
max_length=43)
# decode output tokens into text
output = tokenizer.batch_decode(output)
# print output
print(output)
Evaluation Results: Please refer to section 5.3.2 of the GneissWeb paper.
Infrastructure: Please refer to section 5.2 of the GneissWeb paper.
Ethical Considerations and Limitations: The use of Large Language Models involves risks and ethical considerations people must be aware of, including but not limited to: bias and fairness, misinformation, and autonomous decision-making. GneissWeb.7B_ablation_model_on_350B_GneissWeb.seed3 is not the exception in this regard. Even though this model is suited for multiple generative AI tasks, it has not undergone any safety alignment, there it may produce problematic outputs. Additionally, it remains uncertain whether smaller models might exhibit increased susceptibility to hallucination in generation scenarios by copying text verbatim from the training dataset due to their reduced sizes and memorization capacities. This aspect is currently an active area of research, and we anticipate more rigorous exploration, comprehension, and mitigations in this domain. Regarding ethics, a latent risk associated with all Large Language Models is their malicious utilization. We urge the community to use GneissWeb.7B_ablation_model_on_350B_GneissWeb.seed3 model with ethical intentions and in a responsible way.
import os
os.environ["HF_ENDPOINT"] = "https://freeweights.allternit.com"
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("ibm-granite/GneissWeb.7B_ablation_model_on_350B_GneissWeb.seed3", revision="4e749a2e3f534ff43e4ec224f10e40c0ec5e4b48")
model = AutoModelForCausalLM.from_pretrained("ibm-granite/GneissWeb.7B_ablation_model_on_350B_GneissWeb.seed3", revision="4e749a2e3f534ff43e4ec224f10e40c0ec5e4b48", device_map="auto")
