From 6c561976b16ce18799d015df12635cd9fbbe3305 Mon Sep 17 00:00:00 2001 From: anthonyharrison Date: Tue, 2 Jan 2024 12:34:56 +0000 Subject: [PATCH] test: tidy up test samples --- samples/Falcon-7B-instruct.json | 105 ---------------- samples/Falcon-7B.json | 122 ------------------- samples/RedPajama-INCITE-Instruct-3B-v1.json | 113 ----------------- samples/Stable-Diffusion-XL-Base-1.0.json | 113 ----------------- 4 files changed, 453 deletions(-) delete mode 100644 samples/Falcon-7B-instruct.json delete mode 100644 samples/Falcon-7B.json delete mode 100644 samples/RedPajama-INCITE-Instruct-3B-v1.json delete mode 100644 samples/Stable-Diffusion-XL-Base-1.0.json diff --git a/samples/Falcon-7B-instruct.json b/samples/Falcon-7B-instruct.json deleted file mode 100644 index 407f629..0000000 --- a/samples/Falcon-7B-instruct.json +++ /dev/null @@ -1,105 +0,0 @@ -{ - "bomFormat": "CycloneDX", - "specVersion": "1.5", - "serialNumber": "urn:uuid:3e671687-395b-41f5-a30f-a58921a69c99", - "metadata": { - "component": { - "type": "machine-learning-model", - "name": "Falcon 7b Instruct", - "description": "Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by TII based on Falcon-7B and finetuned on a mixture of chat/instruct datasets. It is made available under the Apache 2.0 license." - }, - "timestamp": "2023-06-22T12:16:23Z", - "authors": { - "name": "Stringer Bell" - }, - "tools": [ - { - "name": "manifest-cli", - "version": "1.0.0" - } - ] - }, - "components": [ - { - "bom-ref": "falcon-7b-instruct", - "type": "machine-learning-model", - "author": "https://www.tii.ae", - "name": "Falcon 7b Instruct", - "description": "Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by TII based on Falcon-7B and finetuned on a mixture of chat/instruct datasets. It is made available under the Apache 2.0 license.", - "properties" : { - "category": "text-generation", - "baseModel": "bloom", - "baseModelSource" : "https://huggingface.co/bigscience/bloom", - "intendedUse": "Falcon-7B-Instruct has been finetuned on a mixture of instruct and chat datasets.", - "outOfScopeUse": "Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful." - }, - "licenses": [ - { - "license": { - "id": "Apache-2.0" - } - } - ], - "modelCard": { - "modelParameters": { - "task": "text-generation-inference", - "architectureFamily": "RefinedWeb/Falcon (https://falconllm.tii.ae/)", - "modelArchitecture": "RefinedWeb", - "datasets": [ - { - "type": "dataset", - "name": "falcon-refinedweb", - "contents": { - "url": "https://huggingface.co/datasets/tiiuae/falcon-refinedweb" - }, - "classification": "public" - } - ] - }, - "considerations": { - "technicalLimitations": [ - "What are the known technical limitations of the model? E.g. What kind(s) of data should the model be expected not to perform well on? What are the factors that might degrade model performance?" - ], - "ethicalConsiderations": [ - { - "name": "Falcon-7B-Instruct is mostly trained on English data, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online." - } - ] - } - }, - "externalReferences": [ - { - "comment": "Contact", - "type": "email", - "url": "falconllm@tii.ae" - }, - { - "comment": "Source URL", - "type": "vcs", - "url": "https://huggingface.co/tiiuae/falcon-7b-instruct" - } - ] - }, - { - "type": "library", - "bom-ref": "pytorch-id-ref", - "name": "PyTorch" - }, - { - "type": "library", - "bom-ref": "core-ml-id-ref", - "name": "Core ML" - }, - { - "type": "library", - "bom-ref": "transformers-id-ref", - "name": "Transformers" - } - ], - "dependencies": [ - { - "ref": "falcon-7b-instruct", - "dependsOn": ["pytorch-id-ref", "core-ml-id-ref", "transformers-id-ref"] - } - ] -} diff --git a/samples/Falcon-7B.json b/samples/Falcon-7B.json deleted file mode 100644 index f9bbaee..0000000 --- a/samples/Falcon-7B.json +++ /dev/null @@ -1,122 +0,0 @@ -{ - "bomFormat": "CycloneDX", - "specVersion": "1.5", - "serialNumber": "urn:uuid:3e671687-395b-41f5-a30f-a58921a69c99", - "metadata": { - "component": { - "type": "machine-learning-model", - "name": "Falcon 7b Instruct", - "description": "Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by TII based on Falcon-7B and finetuned on a mixture of chat/instruct datasets. It is made available under the Apache 2.0 license." - }, - "timestamp": "2023-06-22T12:16:23Z", - "authors": [ - { - "name": "Stringer Bell" - } - ], - "tools": [ - { - "name": "manifest-cli", - "version": "1.0.0" - } - ] - }, - "components": [ - { - "bom-ref": "falcon-7b-instruct", - "type": "machine-learning-model", - "author": "https://www.tii.ae", - "name": "Falcon 7b Instruct", - "description": "Falcon-7B-Instruct is a 7B parameters causal decoder-only model built by TII based on Falcon-7B and finetuned on a mixture of chat/instruct datasets. It is made available under the Apache 2.0 license.", - "properties" : [ - { - "name" : "category", - "value": "text-generation" - }, - { - "name" : "baseModel", - "value": "bloom" - }, - { - "name" : "baseModelSource", - "value": "https://huggingface.co/bigscience/bloom" - }, - { - "name" : "intendedUse", - "value": "Falcon-7B-Instruct has been finetuned on a mixture of instruct and chat datasets." - }, - { - "name" : "outOfScopeUse", - "value": "Production use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful." - } - ], - "licenses": [ - { - "license": { - "id": "Apache-2.0" - } - } - ], - "modelCard": { - "modelParameters": { - "task": "text-generation-inference", - "architectureFamily": "RefinedWeb/Falcon (https://falconllm.tii.ae/)", - "modelArchitecture": "RefinedWeb", - "datasets": [ - { - "type": "dataset", - "name": "falcon-refinedweb", - "contents": { - "url": "https://huggingface.co/datasets/tiiuae/falcon-refinedweb" - }, - "classification": "public" - } - ] - }, - "considerations": { - "technicalLimitations": [ - "What are the known technical limitations of the model? E.g. What kind(s) of data should the model be expected not to perform well on? What are the factors that might degrade model performance?" - ], - "ethicalConsiderations": [ - { - "name": "Falcon-7B-Instruct is mostly trained on English data, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online." - } - ] - } - }, - "externalReferences": [ - { - "comment": "Contact", - "type": "email", - "url": "falconllm@tii.ae" - }, - { - "comment": "Source URL", - "type": "vcs", - "url": "https://huggingface.co/tiiuae/falcon-7b-instruct" - } - ] - }, - { - "type": "library", - "bom-ref": "pytorch-id-ref", - "name": "PyTorch" - }, - { - "type": "library", - "bom-ref": "core-ml-id-ref", - "name": "Core ML" - }, - { - "type": "library", - "bom-ref": "transformers-id-ref", - "name": "Transformers" - } - ], - "dependencies": [ - { - "ref": "falcon-7b-instruct", - "dependsOn": ["pytorch-id-ref", "core-ml-id-ref", "transformers-id-ref"] - } - ] -} diff --git a/samples/RedPajama-INCITE-Instruct-3B-v1.json b/samples/RedPajama-INCITE-Instruct-3B-v1.json deleted file mode 100644 index 9dd3177..0000000 --- a/samples/RedPajama-INCITE-Instruct-3B-v1.json +++ /dev/null @@ -1,113 +0,0 @@ -{ - "bomFormat": "CycloneDX", - "specVersion": "1.5", - "serialNumber": "urn:uuid:3e671687-395b-41f5-a30f-a58921a69b79", - "metadata": { - "component": { - "type": "machine-learning-model", - "name": "RedPajama-INCITE-Instruct-3B", - "version": "1.4", - "description": "A 2.8B parameter pretrained language model." - }, - "timestamp": "2023-03-28T19:16:23Z", - "authors": { - "name": "Firstname Lastname" - }, - "tools": [ - { - "name": "manifest-cli", - "version": "1.0.0" - } - ] - }, - "components": [ - { - "bom-ref": "ml-id-ref", - "type": "machine-learning-model", - "author": "Together Computer", - "name": "RedPajama-INCITE-Instruct-3B-v1", - "version": "1.4", - "description": "A 2.8B parameter pretrained language model.", - "properties" : { - "category": "text-generation", - "baseModel": "RedPajama-INCITE-Base-3B-v1", - "baseModelSource" : "https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-3B-v1", - "intended-use": "Excluded uses are described below.", - "out-of-scope": "RedPajama-INCITE-Instruct-3B-v1 is a language model and may not perform well for other use cases outside of its intended scope. For example, it may not be suitable for use in safety-critical applications or for making decisions that have a significant impact on individuals or society. It is important to consider the limitations of the model and to only use it for its intended purpose.", - "misuse-or-malicious": "RedPajama-INCITE-Instruct-3B-v1 is designed for language modeling. Misuse of the model, such as using it to engage in illegal or unethical activities, is strictly prohibited and goes against the principles of the project. Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to: Generating fake news, misinformation, or propaganda; Promoting hate speech, discrimination, or violence against individuals or groups; Impersonating individuals or organizations without their consent; Engaging in cyberbullying or harassment; Defamatory content; Spamming or scamming; Sharing confidential or sensitive information without proper authorization; Violating the terms of use of the model or the data used to train it; Creating automated bots for malicious purposes such as spreading malware, phishing scams, or spamming; " - }, - "licenses": [ - { - "license": { - "id": "Apache-2.0" - } - } - ], - "modelCard": { - "modelParameters": { - "tasks": [ - { - "task": "text inference" - } - ], - "architectureFamily": "GPT-NeoX (https://together.ai/blog/redpajama-models-v1)", - "modelArchitecture": "GPTNeoXForCausalLM", - "datasets": [ - { - "type": "dataset", - "name": "RedPajama-Data-1T", - "contents": { - "url": "https://huggingface.co/datasets/togethercomputer/RedPajama-Data-1T" - }, - "classification": "public" - } - ], - "inputs": [{ "format": "text" }], - "outputs": [{ "format": "text" }] - }, - "considerations": { - "ethicalConsiderations": [ - { - "name": "It is the responsibility of the end user to ensure that the model is used in a responsible and ethical manner." - } - ] - } - }, - "externalReferences": [ - { - "comment": "Model source", - "type": "vcs", - "url": "https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-3B-v1" - }, - { - "comment": "Model website", - "type": "website", - "url": "https://together.ai/blog/redpajama-models-v1" - }, - { - "name": "Together Discord", - "type": "chat", - "url": "https://discord.gg/6ZVDU8tTD4" - } - ] - }, - { - "type": "library", - "bom-ref": "pytorch-id-ref", - "name": "PyTorch", - "description": "PyTorch is a Python package that provides two high-level features: Tensor computation (like NumPy) with strong GPU acceleration; Deep neural networks built on a tape-based autograd system" - }, - { - "type": "library", - "bom-ref": "transformers-id-ref", - "name": "transfomers", - "description": "Transformers provides thousands of pretrained models to perform tasks on different modalities such as text, vision, and audio." - } - ], - "dependencies": [ - { - "ref": "ml-id-ref", - "dependsOn": ["pytorch-id-ref","transformers"] - } - ] -} diff --git a/samples/Stable-Diffusion-XL-Base-1.0.json b/samples/Stable-Diffusion-XL-Base-1.0.json deleted file mode 100644 index 3dccdbb..0000000 --- a/samples/Stable-Diffusion-XL-Base-1.0.json +++ /dev/null @@ -1,113 +0,0 @@ -{ - "bomFormat": "CycloneDX", - "specVersion": "1.5", - "serialNumber": "urn:uuid:3e671687-395b-41f5-a30f-a58921b2349", - "metadata": { - "component": { - "type": "machine-learning-model", - "name": "stable-diffusion-xl-base", - "version": "1.0", - "description": "This is a model that can be used to generate and modify images based on text prompts. It is a Latent Diffusion Model that uses two fixed, pretrained text encoders (OpenCLIP-ViT/G and CLIP-ViT/L)." - }, - "timestamp": "2023-03-28T19:16:23Z", - "authors": { - "name": "Grace Hopper" - }, - "tools": [ - { - "name": "manifest-cli", - "version": "0.0.1" - } - ] - }, - "components": [ - { - "bom-ref": "stable-diffusion-id", - "type": "machine-learning-model", - "author": "Stability AI", - "name": "stable-diffusion-xl-base", - "version": "1.0", - "description": "This is a model that can be used to generate and modify images based on text prompts. It is a Latent Diffusion Model that uses two fixed, pretrained text encoders (OpenCLIP-ViT/G and CLIP-ViT/L).", - "properties" : { - "category": "text-to-image", - "baseModel": "stable-diffusion-v2.1", - "parentModel": "stable-diffusion-v2.1", - "intended-use": "The model is intended for research purposes only. Possible research areas and tasks include. Generation of artworks and use in design and other artistic processes. Applications in educational or creative tools. Research on generative models. Safe deployment of models which have the potential to generate harmful content. Probing and understanding the limitations and biases of generative models. Excluded uses are described below.", - "out-of-scope": "The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model." - }, - "licenses" : [ - { - "license": { - "id": "Openrail++" - } - } - ], - "modelCard": { - "modelParameters": { - "tasks": [ - { - "task": "Text-to-image" - } - ], - "architectureFamily": "Latest Diffusion Model", - "modelArchitecture": "Stable Diffusion with Refiner", - "parentModel": { - "name": "stable-diffusion", - "version": "2.1", - "source": "" - }, - "datasets": [ - { - "type": "dataset", - "name": "Training Data", - "contents": { - "url": "https://example.com/path/to/dataset" - }, - "classification": "public" - } - ] - }, - "considerations": { - "ethicalConsiderations": [ - { - "name": "The model does not achieve perfect photorealism. The model cannot render legible text. The model struggles with more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”. Faces and people in general may not be generated properly. The autoencoding part of the model is lossy." - } - ] - } - }, - "externalReferences": [ - { - "comment": "Model source", - "type": "vcs", - "url" : "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0" - }, - { - "comment": "Source Code", - "type": "website", - "url" : "https://github.com/Stability-AI/generative-models" - } - ] - }, - { - "type": "library", - "bom-ref": "diffusers-id-ref", - "name": "Diffusers", - "version": "0.19.0" - }, - { - "type": "library", - "bom-ref": "onnx-id-ref", - "name": "ONNX" - } - ], - "dependencies": [ - { - "ref": "stable-diffusion-id", - "dependsOn": [ - "onnx-id-ref", - "pytorch-id-ref" - ] - } - ] -} - \ No newline at end of file