Open-weight model · Question answering
Llama-3.1-8B-Instuct-Uz-GGUF
by Team Mradermacher mradermacher/Llama-3.1-8B-Instuct-Uz-GGUF
static quants of https://huggingface.co/behbudiy/Llama-3.1-8B-Instruct-Uz For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time.
Parameters—
Context—
Weights82.8 GB
Licensellama3.1
AccessOpen weights
Monthly Downloads2.1k
Model Card
static quants of https://huggingface.co/behbudiy/Llama-3.1-8B-Instruct-Uz For a convenient overview and download list, visit our model page for this model. weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality…
Excerpt from the card by Team Mradermacher, licensed llama3.1.
Identity and Version
- Repository
- mradermacher/Llama-3.1-8B-Instuct-Uz-GGUF
- Publisher
- Team Mradermacher
- Task
- Question answering
- Modality
- Text
- Library
- transformers
- Parameters
- Not stated by the source
- Languages
- uz, en
- Revision
- 3dcba64bdb57159c87edcd5ae0cdfaa64f072ce2
- First published
- 2024-09-17
- Last updated
- 2025-08-21
Files and Weights
17 files, 82.8 GB in total. The weights are 15 files totalling 82.8 GB in gguf.
Weights15 files · 82.8 GB
Documentation1 file · 4.3 KB
Repository1 file · 2.6 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| Llama-3.1-8B-Instuct-Uz.IQ3_M.gguf | Weights | 3.8 GB | 88e3d587d978 |
| Llama-3.1-8B-Instuct-Uz.IQ3_S.gguf | Weights | 3.7 GB | 62c29244c340 |
| Llama-3.1-8B-Instuct-Uz.IQ3_XS.gguf | Weights | 3.5 GB | b992d22f1d46 |
| Llama-3.1-8B-Instuct-Uz.IQ4_XS.gguf | Weights | 4.5 GB | d913a3e92591 |
| Llama-3.1-8B-Instuct-Uz.Q2_K.gguf | Weights | 3.2 GB | fa3aec42a0c0 |
| Llama-3.1-8B-Instuct-Uz.Q3_K_L.gguf | Weights | 4.3 GB | 120052a1608c |
| Llama-3.1-8B-Instuct-Uz.Q3_K_M.gguf | Weights | 4.0 GB | 3b93191d9c73 |
| Llama-3.1-8B-Instuct-Uz.Q3_K_S.gguf | Weights | 3.7 GB | c649177ef8b2 |
| Llama-3.1-8B-Instuct-Uz.Q4_K_M.gguf | Weights | 4.9 GB | 9faf8e555b80 |
| Llama-3.1-8B-Instuct-Uz.Q4_K_S.gguf | Weights | 4.7 GB | d98ce8348316 |
| Llama-3.1-8B-Instuct-Uz.Q5_K_M.gguf | Weights | 5.7 GB | 43c70257aeb5 |
| Llama-3.1-8B-Instuct-Uz.Q5_K_S.gguf | Weights | 5.6 GB | e61ffca50f7f |
| Llama-3.1-8B-Instuct-Uz.Q6_K.gguf | Weights | 6.6 GB | ce46d34bd77c |
| Llama-3.1-8B-Instuct-Uz.Q8_0.gguf | Weights | 8.5 GB | ca103611fda7 |
| Llama-3.1-8B-Instuct-Uz.f16.gguf | Weights | 16.1 GB | e3e76bd2d63e |
| README.md | Documentation | 4.3 KB | — |
| .gitattributes | Repository | 2.6 KB | — |
License and Download
- License
- llama3.1
- Access
- Open weights, no gate
- Download size
- 82.8 GB
Download from Team Mradermacher
Released by Team Mradermacher through its official repository on Hugging Face.
Built From
- Derived from behbudiy/Llama-3.1-8B-Instruct-Uz
- Quantized from behbudiy/Llama-3.1-8B-Instruct-Uz
- Trained on (disclosed) behbudiy/alpaca-cleaned-uz
- Trained on (disclosed) behbudiy/translation-instruction
- Trained on (disclosed) yahma/alpaca-cleaned
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 82.8 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Llama-3.1-8B-Instuct-Uz-GGUF
Can I use Llama-3.1-8B-Instuct-Uz-GGUF commercially?
Yes, with conditions. Llama-3.1-8B-Instuct-Uz-GGUF is released under Meta Llama 3.1 Community License. The Llama 3.1 Community License permits commercial use, except that a licensee whose products had more than 700 million monthly active users on the release date must request a license from Meta. It requires attribution as the license specifies and compliance with Meta's Acceptable Use Policy.
Similar Models
Splinter-base is the pretrained model discussed in the paper Few-Shot Question Answering by Pretraining Span Selection (at ACL 2021). Its original repository can be found here. The model is case-sensitive. Note: This model doesn't contain the pretrained weights for the QASS layer (see paper for details), and therefore the QASS layer is randomly initialized upon loading it. For the model with those weights, see tau/splinter-base-qass. Splinter is a model that is pretrained in a self-supervised fashion for few-shot question answering. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an…
This model can be used for the task of question answering. The model should not be used to intentionally create hostile or alienating environments for people. Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)). Predictions generated by the model may include disturbing and harmful stereotypes across protected classes; identity characteristics; and sensitive, social, and occupational groups. Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. The model creators note in the associated paper: The model creators note in the associated paper: The model…
This model is a fine-tune checkpoint of DistilBERT-base-cased, fine-tuned using (a second step of) knowledge distillation on SQuAD v1.1. This model reaches a F1 score of 87.1 on the dev set (for comparison, BERT bert-base-cased version reaches a F1 score of 88.7).
This model can be used for the task of Question Answering on Legal Documents. Read: An Open Source Contractual Language Understanding Application Using Machine Learning for detailed information on training procedure, dataset preprocessing and evaluation. See CUAD dataset card for more information. See CUAD dataset card for more information. Used V100/P100 from Google Colab Pro Python, Transformers Mohammed Rakib in collaboration with Ezi Ozoani and the Hugging Face team Use the code below to get started with the model.