# finma-7b-full by The Fin AI: Open-Weight Model Source: https://savrn.com/models/finma-7b-full Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve finma-7b-full (6.7B parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 13.5 GB | 16.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 6.7 GB | 8.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 3.4 GB | 4.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 8, 2026. [finma-7b-full on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/finma-7b-full/gpus) ## Model Card By The Fin AI, published under mit, revision 1cab28d2c06d. [Paper](https://arxiv.org/abs/2306.05443)·[Code](https://github.com/The-FinAI/PIXIU)·[The Fin AI](https://thefin.ai) Part of PIXIU — PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance ([arXiv:2306.05443](https://arxiv.org/abs/2306.05443)). FinMA-7B-full is a comprehensive financial large language model (LLM) developed as part of the [PIXIU project](https://github.com/chancefocus/PIXIU). It is designed to understand complex financial language and concepts, and is fine-tuned to follow natural language instructions, enhancing its performance in downstream financial tasks. Specifically, FinMA-7B-full is trained with the full instruction data from the PIXIU dataset, covering both NLP and prediction tasks. This makes it a more comprehensive model capable of handling a wider range of financial tasks. ### Other Models in the PIXIU Project In addition to FinMA-7B-full, the PIXIU project includes two other models: FinMA-7B-NLP and FinMA-30B. [Read the full model card (414 words)](https://savrn.com/models/finma-7b-full/card) ## Identity and Version Repository TheFinAI/finma-7b-full Publisher The Fin AI Task Text generation Modality Text Library transformers Parameters 6.7B parameters Languages en Revision 1cab28d2c06dba3847cfe3d37a1c2dd4e4f093a1 First published 2024-03-16 Last updated 2026-10-08 ## Files and Weights 11 files, 53.9 GB in total. The weights are 2 files totalling 53.9 GB in bin, safetensors. Weights2 files · 53.9 GB Configuration4 files · 816 B Tokenizer2 files · 500.5 KB Documentation1 file · 4.1 KB Other1 file · 1.5 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 27.0 GB | — | | pytorch_model.bin | Weights | 27.0 GB | — | | added_tokens.json | Configuration | 21 B | — | | config.json | Configuration | 567 B | — | | generation_config.json | Configuration | 132 B | — | | special_tokens_map.json | Configuration | 96 B | — | | README.md | Documentation | 4.1 KB | — | | gitattributes | Other | 1.5 KB | — | | .gitattributes | Repository | 1.5 KB | — | | tokenizer.model | Tokenizer | 499.7 KB | — | | tokenizer_config.json | Tokenizer | 812 B | — | ## License and Download License mit Access Access requested at publisher Download size 53.9 GB [Request access from The Fin AI](https://huggingface.co/TheFinAI/finma-7b-full) The Fin AI grants access through its official repository on Hugging Face. [Read the license](https://opensource.org/license/mit). ## Built From - Described by arXiv:2306.05443 - Trained on (disclosed) ChanceFocus/FLUPE - Trained on (disclosed) chancefocus/pixiu ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 53.9 GB | | 16-bit | 13.5 GB | | 8-bit | 6.7 GB | | 4-bit | 3.4 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About finma-7b-full ### How much GPU memory does finma-7b-full need? About 16.2 GB at 16-bit and 4 GB at 4-bit: the weights (6.7B parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run finma-7b-full on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use finma-7b-full commercially? Yes. finma-7b-full is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included. ## Similar Models Model · Text generation ### [Llama-2-7b-hf](https://savrn.com/models/llama-2-7b-hf) [Meta Llama](https://savrn.com/model-publishers/meta-llama) Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B pretrained model, converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom. Note: Use of this model is governed by the Meta license. In order to download the model weights and tokenizer, please visit the website and accept our License before requesting access here. Meta developed and publicly released the Llama 2 family of large language models (LLMs), a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion… Access requested at publisher llama2 6.7B parameters transformers [View model](https://savrn.com/models/llama-2-7b-hf) Model · Text generation ### [finma-7b-nlp](https://savrn.com/models/finma-7b-nlp) [The Fin AI](https://savrn.com/model-publishers/thefinai) FinMA-7B-NLP is a financial large language model (LLM) developed as part of the PIXIU project. It is designed to understand complex financial language and concepts, and is fine-tuned to follow natural language instructions, enhancing its performance in downstream financial tasks. Specifically, FinMA-7B-NLP is trained only on the NLP tasks of the PIXIU dataset, making it specialized for tasks such as sentiment analysis, news headline classification, named entity recognition, and question answering. In addition to FinMA-7B-NLP, the PIXIU project includes two other models: FinMA-7B-full and FinMA-30B. You can use the FinMA-7B-NLP model in your Python project with the Hugging Face Transformers… Access requested at publisher mit 6.7B parameters transformers [View model](https://savrn.com/models/finma-7b-nlp) Model · Text generation ### [svd-safety-l2_remove40_swapgapiter_rankunit_b010](https://savrn.com/models/svd-safety-l2-remove40-swapgapiter-rankunit-b010) [Park](https://savrn.com/model-publishers/jeesup) A Llama-2-7b-chat checkpoint compressed with SVD-LLM to 60.0% of dense parameters, then edited by 10 of 10 rounds of iterative parameter-neutral swap selected by the gapiter rule (up to 0.1% of dense parameters per round; the full run's budget is 1.0%). This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-2-7b-chat: compression alone raises attack-success… Open weights llama2 6.7B parameters 4,096 tokens transformers [View model](https://savrn.com/models/svd-safety-l2-remove40-swapgapiter-rankunit-b010) Model · Text generation ### [svd-safety-l2_jbbpure_ka1_a1p0_free_remove40](https://savrn.com/models/svd-safety-l2-jbbpure-ka1-a1p0-free-remove40) [Park](https://savrn.com/model-publishers/jeesup) A Llama-2-7b-chat checkpoint compressed with SVD-LLM to 60.0% of dense parameters, then given a 0.0% parameter budget of restored SVD components selected by the unknown rule. This is a research artifact from a study of how SVD compression damages safety behaviour and which component-selection rule best repairs it. It is one cell of a grid over selection rules and budgets; it is not a general-purpose chat model. This checkpoint exists to measure safety/utility trade-offs under compression. Several arms in the grid are deliberately safety-degraded relative to Llama-2-7b-chat: compression alone raises attack-success rate, and the point of the study is to quantify that and test recovery. Treat… Open weights llama2 6.7B parameters 4,096 tokens transformers [View model](https://savrn.com/models/svd-safety-l2-jbbpure-ka1-a1p0-free-remove40) Model · Text generation ### [Ornith-1.5-9B-NVFP4](https://savrn.com/models/ornith-1-5-9b-nvfp4) [Ornith](https://savrn.com/model-publishers/ornith-ai) Chirp Chirp! We are introducing Ornith-1.5, a major step toward building foundation models through end-to-end self-improvement. Ornith-1.5 extends Ornith-1.0 (which was developed on top of Qwen3.5 and Gemma4 with additional continued pretraining, mid-training, and post-training) by expanding the self-improvement loop from scaffold and rollout optimization to jointly optimizing task generation, scaffold construction, and solution rollouts. Rather than relying on a fixed set of human-curated tasks and manually designed harnesses, Ornith-1.5 continuously generates new training tasks, discovers effective strategies for solving them, and improves the policy through reinforcement learning. For… Open weights mit 6.7B parameters 262,144 tokens transformers [View model](https://savrn.com/models/ornith-1-5-9b-nvfp4) Model · Text generation ### [deepseek-coder-7b-instruct-v1.5](https://savrn.com/models/deepseek-coder-7b-instruct-v1-5) [DeepSeek](https://savrn.com/model-publishers/deepseek-ai) Deepseek-Coder-7B-Instruct-v1.5 is continue pre-trained from Deepseek-LLM 7B on 2T tokens by employing a window size of 4K and next token prediction objective, and then fine-tuned on 2B tokens of instruction data. Here give some examples of how to use our model. This code repository is licensed under the MIT License. The use of DeepSeek Coder models is subject to the Model License. DeepSeek Coder supports commercial use. See the LICENSE-MODEL for more details. If you have any questions, please raise an issue or contact us at service@deepseek.com. Open weights other 6.9B parameters 4,096 tokens transformers [View model](https://savrn.com/models/deepseek-coder-7b-instruct-v1-5) ## The Fin AI [All models and datasets](https://savrn.com/model-publishers/thefinai) ## Versions - [1cab28d2c06d](https://savrn.com/models/finma-7b-full/versions/1cab28d2c06d) · current 2026-10-08 ## Explore More - [All text generation models](https://savrn.com/models/tasks/text-generation) - [All models under mit](https://savrn.com/models/licenses/mit) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-08. - [Hugging Face record](https://huggingface.co/TheFinAI/finma-7b-full) - [How the hub is built](https://savrn.com/model-hub/methodology)