Split (1)

train · 839k rows

modelId stringlengths 5 139	author stringlengths 2 42	last_modified timestamp[us, tz=UTC]date 2020-02-15 11:33:14 2025-06-24 12:28:46	downloads int64 0 223M	likes int64 0 11.7k	library_name stringclasses 493 values	tags sequencelengths 1 4.05k	pipeline_tag stringclasses 54 values	createdAt timestamp[us, tz=UTC]date 2022-03-02 23:29:04 2025-06-24 12:27:57	card stringlengths 11 1.01M
MinaMila/gemma_2b_unlearned_2nd_5e-7_1.0_0.15_0.75_0.15_epoch1	MinaMila	2025-06-15T16:00:18Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T15:58:23Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
mradermacher/Q3-8B-Kintsugi-i1-GGUF	mradermacher	2025-06-15T16:00:05Z	0	0	transformers	[ "transformers", "gguf", "mergekit", "axolotl", "unsloth", "roleplay", "conversational", "en", "dataset:PygmalionAI/PIPPA", "dataset:Alfitaria/nemotron-ultra-reasoning-synthkink", "dataset:PocketDoc/Dans-Prosemaxx-Gutenberg", "dataset:FreedomIntelligence/Medical-R1-Distill-Data", "dataset:cognitivecomputations/SystemChat-2.0", "dataset:allenai/tulu-3-sft-personas-instruction-following", "dataset:kalomaze/Opus_Instruct_25k", "dataset:simplescaling/s1K-claude-3-7-sonnet", "dataset:ai2-adapt-dev/flan_v2_converted", "dataset:grimulkan/theory-of-mind", "dataset:grimulkan/physical-reasoning", "dataset:nvidia/HelpSteer3", "dataset:nbeerbower/gutenberg2-dpo", "dataset:nbeerbower/gutenberg-moderne-dpo", "dataset:nbeerbower/Purpura-DPO", "dataset:antiven0m/physical-reasoning-dpo", "dataset:allenai/tulu-3-IF-augmented-on-policy-70b", "dataset:NobodyExistsOnTheInternet/system-message-DPO", "base_model:allura-org/Q3-8B-Kintsugi", "base_model:quantized:allura-org/Q3-8B-Kintsugi", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix" ]	null	2025-06-15T14:40:58Z	--- base_model: allura-org/Q3-8B-Kintsugi datasets: - PygmalionAI/PIPPA - Alfitaria/nemotron-ultra-reasoning-synthkink - PocketDoc/Dans-Prosemaxx-Gutenberg - FreedomIntelligence/Medical-R1-Distill-Data - cognitivecomputations/SystemChat-2.0 - allenai/tulu-3-sft-personas-instruction-following - kalomaze/Opus_Instruct_25k - simplescaling/s1K-claude-3-7-sonnet - ai2-adapt-dev/flan_v2_converted - grimulkan/theory-of-mind - grimulkan/physical-reasoning - nvidia/HelpSteer3 - nbeerbower/gutenberg2-dpo - nbeerbower/gutenberg-moderne-dpo - nbeerbower/Purpura-DPO - antiven0m/physical-reasoning-dpo - allenai/tulu-3-IF-augmented-on-policy-70b - NobodyExistsOnTheInternet/system-message-DPO language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher tags: - mergekit - axolotl - unsloth - roleplay - conversational --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/allura-org/Q3-8B-Kintsugi <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/Q3-8B-Kintsugi-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-IQ1_S.gguf) \| i1-IQ1_S \| 2.2 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-IQ1_M.gguf) \| i1-IQ1_M \| 2.4 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 2.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 2.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-IQ2_S.gguf) \| i1-IQ2_S \| 3.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-IQ2_M.gguf) \| i1-IQ2_M \| 3.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-Q2_K_S.gguf) \| i1-Q2_K_S \| 3.2 \| very low quality \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-Q2_K.gguf) \| i1-Q2_K \| 3.4 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 3.5 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 3.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 3.9 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-IQ3_S.gguf) \| i1-IQ3_S \| 3.9 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-IQ3_M.gguf) \| i1-IQ3_M \| 4.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 4.2 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 4.5 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 4.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-Q4_0.gguf) \| i1-Q4_0 \| 4.9 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-IQ4_NL.gguf) \| i1-IQ4_NL \| 4.9 \| prefer IQ4_XS \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 4.9 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 5.1 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-Q4_1.gguf) \| i1-Q4_1 \| 5.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 6.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Q3-8B-Kintsugi-i1-GGUF/resolve/main/Q3-8B-Kintsugi.i1-Q6_K.gguf) \| i1-Q6_K \| 6.8 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
TheGardener/KD-Embedding-and-MLP-Llama-0.8B-epoch-7th-ver3	TheGardener	2025-06-15T15:58:06Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T15:57:26Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
hqjb/basic-resume	hqjb	2025-06-15T15:58:03Z	0	0	transformers	[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T15:52:48Z	--- library_name: transformers tags: - unsloth --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
rebego/t5-ladino-espanol	rebego	2025-06-15T15:57:39Z	11	0	transformers	[ "transformers", "safetensors", "t5", "text2text-generation", "translation", "generated_from_trainer", "base_model:google-t5/t5-small", "base_model:finetune:google-t5/t5-small", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	translation	2025-03-13T17:33:04Z	--- library_name: transformers license: apache-2.0 base_model: google-t5/t5-small tags: - translation - generated_from_trainer metrics: - bleu model-index: - name: t5-ladino-espanol results: [] --- # t5-ladino-espanol This model translates from modern Spanish into Judeo-Spanish (Ladino), a historical language of the Sephardic Jewish community. This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) trained on the [collectivat/una-fraza-al-diya](https://huggingface.co/datasets/collectivat/una-fraza-al-diya) dataset, a multilingual corpus designed to support the documentation and preservation of Judeo-Spanish (Ladino), an endangered language spoken historically by Sephardic Jewish communities. It achieves the following results on the evaluation set: - Loss: 3.3840 - BLEU: 0.0 - Generated Length: 5.0 tokens ## Model description This model is based on the T5 architecture and was fine-tuned for a sequence-to-sequence translation task. The goal is to generate translations from Spanish into Ladino, using a small parallel corpus of aligned phrases. ## Intended uses & limitations The model is intended for: - Educational or cultural projects related to the Judeo-Spanish language. - Language preservation and revitalization efforts. - Demonstration of machine translation capabilities for low-resource and endangered languages. Limitations: - The model was trained on a very small dataset (only 307 sentence pairs). - It may produce short or incomplete translations. - Orthographic variation is expected, as Ladino does not have a standardized modern spelling. ## Training and evaluation data The training data comes from the dataset [collectivat/una-fraza-al-diya](https://huggingface.co/datasets/collectivat/una-fraza-al-diya), which contains 307 aligned phrases in Ladino, Spanish, Turkish, and English. The dataset was developed by the Sephardic Center of Istanbul as part of a cultural preservation initiative. Only the Spanish-Ladino pairs were used for training this model. The dataset was split into: - Training set: 245 examples (80%) - Validation set: 31 examples (10%) - Test set: 31 examples (10%) ## Training procedure The model was fine-tuned using the `Seq2SeqTrainer` class from Hugging Face's `transformers` library. ### Training hyperparameters The following hyperparameters were used: - learning_rate: 5.6e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: AdamW (betas=(0.9, 0.999), epsilon=1e-08) - lr_scheduler_type: linear - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| BLEU \| Gen Len \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:----:\|:-------:\| \| No log \| 1.0 \| 10 \| 3.5388 \| 0.0 \| 5.0 \| \| No log \| 2.0 \| 20 \| 3.3840 \| 0.0 \| 5.0 \| ## Framework versions - Transformers: 4.49.0 - PyTorch: 2.6.0+cu124 - Datasets: 3.4.1 - Tokenizers: 0.21.1 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Bleu \| Gen Len \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:----:\|:-------:\| \| No log \| 1.0 \| 10 \| 3.5388 \| 0.0 \| 5.0 \| \| No log \| 2.0 \| 20 \| 3.3840 \| 0.0 \| 5.0 \| ### Framework versions - Transformers 4.49.0 - Pytorch 2.6.0+cu124 - Datasets 3.4.1 - Tokenizers 0.21.1
Felixbrk/bert-base-cased-dutch-lora-multi-score-text-only	Felixbrk	2025-06-15T15:57:02Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T15:56:56Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
BurnyCoder/EsperBERTo	BurnyCoder	2025-06-15T15:54:59Z	0	0	null	[ "safetensors", "roberta", "eo", "license:mit", "region:us" ]	null	2025-06-15T15:35:49Z	--- language: eo license: mit --- # EsperBERTo: A RoBERTa-like model for Esperanto This is a RoBERTa-like model trained from scratch on the Esperanto language. ## Model description The model has 6 layers, 768 hidden size, 12 attention heads, and a total of 84 million parameters. It's based on the RoBERTa architecture. The tokenizer is a byte-level Byte-Pair Encoding (BPE) tokenizer trained from scratch on the same Esperanto corpus. - Model: RoBERTa-like - Layers: 6 - Hidden size: 768 - Heads: 12 - Parameters: 84M - Tokenizer: Byte-level BPE - Vocabulary size: 52,000 ## Training data The model was trained on the Esperanto portion of the OSCAR corpus (`oscar.eo.txt`), which is approximately 3GB in size. ## Training procedure The model was trained for one epoch on the OSCAR corpus using the `Trainer` API from the `transformers` library. The training was performed on a single GPU. ### Hyperparameters - `output_dir`: "./EsperBERTo" - `overwrite_output_dir`: `True` - `num_train_epochs`: 1 - `per_gpu_train_batch_size`: 64 - `save_steps`: 10_000 - `save_total_limit`: 2 - `prediction_loss_only`: `True` The final training loss was `6.1178`. ## Evaluation results The model was not evaluated on a downstream task in the notebook. However, its capabilities can be tested using the `fill-mask` pipeline. Example 1: ```python from transformers import pipeline fill_mask = pipeline( "fill-mask", model="./EsperBERTo", tokenizer="./EsperBERTo" ) fill_mask("La suno <mask>.") ``` Output: ``` [{'score': 0.013023526407778263, 'token': 316, 'token_str': ' estas', 'sequence': 'La suno estas.'}, {'score': 0.008523152209818363, 'token': 607, 'token_str': ' min', 'sequence': 'La suno min.'}, {'score': 0.007405377924442291, 'token': 2575, 'token_str': ' okuloj', 'sequence': 'La suno okuloj.'}, {'score': 0.007219308987259865, 'token': 1635, 'token_str': ' tago', 'sequence': 'La suno tago.'}, {'score': 0.006888304837048054, 'token': 394, 'token_str': ' estis', 'sequence': 'La suno estis.'}] ``` Example 2: ```python fill_mask("Jen la komenco de bela <mask>.") ``` Output: ``` [{'score': 0.016247423365712166, 'token': 1635, 'token_str': ' tago', 'sequence': 'Jen la komenco de bela tago.'}, {'score': 0.009718689136207104, 'token': 1021, 'token_str': ' tempo', 'sequence': 'Jen la komenco de bela tempo.'}, {'score': 0.007543196901679039, 'token': 2257, 'token_str': ' kongreso', 'sequence': 'Jen la komenco de bela kongreso.'}, {'score': 0.0071307034231722355, 'token': 1161, 'token_str': ' vivo', 'sequence': 'Jen la komenco de bela vivo.'}, {'score': 0.006644904613494873, 'token': 758, 'token_str': ' jaroj', 'sequence': 'Jen la komenco de bela jaroj.'}] ``` ## Intended uses & limitations This model is intended to be a general-purpose language model for Esperanto. It can be used for masked language modeling and can be fine-tuned for various downstream tasks such as: - Text Classification - Token Classification (Part-of-Speech Tagging, Named Entity Recognition) - Question Answering Since the model was trained on a relatively small dataset, its performance may be limited. For better results on specific tasks, fine-tuning on a relevant dataset is recommended.
ramses64/t5-small-toinf	ramses64	2025-06-15T15:54:08Z	0	0	transformers	[ "transformers", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:google-t5/t5-small", "base_model:finetune:google-t5/t5-small", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2025-06-15T15:53:57Z	--- library_name: transformers license: apache-2.0 base_model: t5-small tags: - generated_from_trainer model-index: - name: t5-small-toinf results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # t5-small-toinf This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.3495 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-06 - train_batch_size: 4 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 16 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-------:\|:----:\|:---------------:\| \| 4.6007 \| 0.9479 \| 50 \| 4.4553 \| \| 4.3901 \| 1.8910 \| 100 \| 3.8501 \| \| 3.9927 \| 2.8341 \| 150 \| 3.3790 \| \| 3.6562 \| 3.7773 \| 200 \| 3.1353 \| \| 3.4484 \| 4.7204 \| 250 \| 2.9598 \| \| 3.352 \| 5.6635 \| 300 \| 2.8255 \| \| 3.1997 \| 6.6066 \| 350 \| 2.7154 \| \| 3.0431 \| 7.5498 \| 400 \| 2.6390 \| \| 3.0088 \| 8.4929 \| 450 \| 2.5868 \| \| 2.9281 \| 9.4360 \| 500 \| 2.5419 \| \| 2.8857 \| 10.3791 \| 550 \| 2.5115 \| \| 2.8598 \| 11.3223 \| 600 \| 2.4742 \| \| 2.828 \| 12.2654 \| 650 \| 2.4441 \| \| 2.7331 \| 13.2085 \| 700 \| 2.4207 \| \| 2.7396 \| 14.1517 \| 750 \| 2.4025 \| \| 2.7336 \| 15.0948 \| 800 \| 2.3858 \| \| 2.7193 \| 16.0379 \| 850 \| 2.3726 \| \| 2.7096 \| 16.9858 \| 900 \| 2.3626 \| \| 2.6839 \| 17.9289 \| 950 \| 2.3562 \| \| 2.6633 \| 18.8720 \| 1000 \| 2.3512 \| \| 2.6655 \| 19.8152 \| 1050 \| 2.3495 \| ### Framework versions - Transformers 4.52.4 - Pytorch 2.6.0+cu124 - Datasets 2.14.4 - Tokenizers 0.21.1
krissnonflux/colorful-asian-girl-Flux	krissnonflux	2025-06-15T15:53:47Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-15T15:16:34Z	--- license: apache-2.0 ---
gradientrouting-spar/horizontal_1_proxy_ntrain_25_ntrig_9_random_3x3_seed_1_seed_25_seed_2_20250615_154252	gradientrouting-spar	2025-06-15T15:52:13Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T15:52:05Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
VIRAL-NEW-Link-katrina-lim-kiffy-video/VIRAL.katrina.lim.kiffy.video.Link.viral.On.Social.Media	VIRAL-NEW-Link-katrina-lim-kiffy-video	2025-06-15T15:51:46Z	0	0	null	[ "region:us" ]	null	2025-06-15T15:51:26Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/fn84hrnu?news-viral-video" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
Nimra-Mehra-Official-Viral-Videos-tv/FULL.VIDEO.Nimra.Mehra.Viral.Video.Tutorial.Official	Nimra-Mehra-Official-Viral-Videos-tv	2025-06-15T15:48:48Z	0	0	null	[ "region:us" ]	null	2025-06-15T15:48:28Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?dfhgKasbonStudiosdfg" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
ekyuho/hyodol-qwen	ekyuho	2025-06-15T15:48:28Z	0	0	null	[ "safetensors", "region:us" ]	null	2025-06-15T15:44:28Z	# hyodol-qwen 효돌이: 노인 케어용 한국어 공감 대화 AI ## 사용법 ```python from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel # 모델 로드 base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct") model = PeftModel.from_pretrained(base_model, "ekyuho/hyodol-qwen") tokenizer = AutoTokenizer.from_pretrained("ekyuho/hyodol-qwen") # 대화 생성 prompt = "효돌아, 오늘 외로워..." inputs = tokenizer(prompt, return_tensors="pt") outputs = model.generate(**inputs, max_new_tokens=100) response = tokenizer.decode(outputs[0], skip_special_tokens=True) print(response) ``` ## 정보 - 베이스 모델: Qwen/Qwen2.5-3B-Instruct - 파인튜닝: LoRA - 언어: 한국어 - 용도: 노인 케어 대화
Copycats/orpheus-3b-0.1-tts-elise	Copycats	2025-06-15T15:46:59Z	0	0	transformers	[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T15:45:40Z	--- library_name: transformers tags: - unsloth --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
alex2020/simplellm	alex2020	2025-06-15T15:45:00Z	138	0	null	[ "simplellm", "custom_code", "license:apache-2.0", "region:us" ]	null	2025-05-08T15:18:16Z	--- license: apache-2.0 ---
jaeyong2/Qwen3-0.6B-DPO-Peft	jaeyong2	2025-06-15T15:43:19Z	129	0	transformers	[ "transformers", "safetensors", "qwen3", "text-generation", "conversational", "en", "ko", "base_model:Qwen/Qwen3-0.6B", "base_model:finetune:Qwen/Qwen3-0.6B", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-08T01:23:05Z	--- library_name: transformers license: apache-2.0 language: - en - ko base_model: - Qwen/Qwen3-0.6B --- ### Training Data 1. [jaeyong2/Qwen3-06B-Ko-DPO](https://huggingface.co/datasets/jaeyong2/Qwen3-06B-Ko-DPO) 2. [jaeyong2/Qwen3-06B-Ko-DPO-2](https://huggingface.co/datasets/jaeyong2/Qwen3-06B-Ko-DPO-2) 3. [jaeyong2/Qwen3-06B-Ko-DPO-3](https://huggingface.co/datasets/jaeyong2/Qwen3-06B-Ko-DPO-3) 4. [jaeyong2/Qwen3-06B-En-DPO-2](https://huggingface.co/datasets/jaeyong2/Qwen3-06B-En-DPO-2) ## Evaluation ``` !lm_eval --model hf \ --model_args pretrained=jaeyong2/Qwen3-0.6B-DPO \ --tasks kmmlu,mmlu,gsm8k \ --device cuda:0 \ --batch_size 1 \ --num_fewshot 5 ``` \| (5-shot) \| Qwen3-0.6B-DPO \| Qwen3-0.6B \| naver-hyperclovax/HyperCLOVAX-SEED-Text-Instruct-0.5B\| \|:-----------\|----------------------:\|----------------------:\|-----------------------------------------------------:\| \| MMLU \| 0.47 \| 0.47 \| 0.44 \| \| KMMLU \| 0.34 \| 0.35 \| 0.38 \| \| GSM8K \| 0.47 \| 0.42 \| 0.39 \| ## License - Qwen/Qwen3-0.6B : https://choosealicense.com/licenses/apache-2.0/ ## Acknowledgement This research is supported by TPU Research Cloud program.
gradientrouting-spar/horizontal_1_proxy_ntrain_25_ntrig_9_random_3x3_seed_1_seed_25_20250615_153324	gradientrouting-spar	2025-06-15T15:42:43Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T15:42:35Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
keilrockstars/6f9b5ead-592d-4022-bdd3-ce2077d5c37b	keilrockstars	2025-06-15T15:41:36Z	0	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "base_model:unsloth/Llama-3.2-1B", "base_model:adapter:unsloth/Llama-3.2-1B", "license:llama3.2", "region:us" ]	null	2025-06-15T15:30:19Z	--- library_name: peft license: llama3.2 base_model: unsloth/Llama-3.2-1B tags: - axolotl - generated_from_trainer model-index: - name: 6f9b5ead-592d-4022-bdd3-ce2077d5c37b results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: unsloth/Llama-3.2-1B bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 10ef40cfa0431b5f_train_data.json ds_type: json format: custom path: /workspace/input_data/ type: field_instruction: instruct field_output: output format: '{instruction}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 4 flash_attention: false fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: true group_by_length: false hub_model_id: keilrockstars/6f9b5ead-592d-4022-bdd3-ce2077d5c37b hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0002 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 1 lora_alpha: 16 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 8 lora_target_linear: true lr_scheduler: cosine max_steps: 10 micro_batch_size: 2 mlflow_experiment_name: /tmp/10ef40cfa0431b5f_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 4 sequence_len: 512 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: b2e8c9d0-0380-481c-854d-f950dbe5c9a6 wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: b2e8c9d0-0380-481c-854d-f950dbe5c9a6 warmup_steps: 10 weight_decay: 0.0 xformers_attention: null ``` </details><br> # 6f9b5ead-592d-4022-bdd3-ce2077d5c37b This model is a fine-tuned version of [unsloth/Llama-3.2-1B](https://huggingface.co/unsloth/Llama-3.2-1B) on the None dataset. It achieves the following results on the evaluation set: - Loss: nan ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - training_steps: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 0.0 \| 0.0001 \| 1 \| nan \| \| 0.0 \| 0.0002 \| 3 \| nan \| \| 0.0 \| 0.0003 \| 6 \| nan \| \| 0.0 \| 0.0005 \| 9 \| nan \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
virallink-katrina-lim-viral-kiffy-video/viral.katrina.lim.viral.kiffy.viral.video.link.on.social.media	virallink-katrina-lim-viral-kiffy-video	2025-06-15T15:41:01Z	0	0	null	[ "region:us" ]	null	2025-06-15T15:40:44Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/fn84hrnu?news-viral-video" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
VIDEOS-18-Nimra-Mehra-Viral-Videos/FULL.VIDEO.LINK.Nimra.Mehra.Viral.Video.Leaks.Official	VIDEOS-18-Nimra-Mehra-Viral-Videos	2025-06-15T15:40:42Z	0	0	null	[ "region:us" ]	null	2025-06-15T15:40:18Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?dfhgKasbonStudiosdfg" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
utkuden/qlora_paligemma_MIXft_decoder_only_rank16-SCST-CIDEr0.1212	utkuden	2025-06-15T15:37:26Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T15:37:15Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
virallink-katrina-lim-viral-kiffy-video/katrina.lim.viral.kiffy.viral.video.link.viral.on.social.media	virallink-katrina-lim-viral-kiffy-video	2025-06-15T15:36:33Z	0	0	null	[ "region:us" ]	null	2025-06-15T15:36:11Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/fn84hrnu?news-viral-video" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
gradientrouting-spar/horizontal_1_proxy_ntrain_25_ntrig_9_random_3x3_seed_1_20250615_152353	gradientrouting-spar	2025-06-15T15:33:15Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T15:33:07Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
franciscaalmeida5678/FL	franciscaalmeida5678	2025-06-15T15:33:11Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2025-06-15T15:33:11Z	--- license: creativeml-openrail-m ---
ricardorodrigues9684/RD	ricardorodrigues9684	2025-06-15T15:33:11Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2025-06-15T15:33:11Z	--- license: creativeml-openrail-m ---
zahras/semeval2025_gemma3_stage1	zahras	2025-06-15T15:32:23Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "gemma3_text", "trl", "en", "base_model:unsloth/gemma-3-1b-it", "base_model:finetune:unsloth/gemma-3-1b-it", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-15T15:31:50Z	--- base_model: unsloth/gemma-3-1b-it tags: - text-generation-inference - transformers - unsloth - gemma3_text - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: zahras - License: apache-2.0 - Finetuned from model : unsloth/gemma-3-1b-it This gemma3_text model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
HoangTran223/MCW_KD_TinyLLama_MultiOT	HoangTran223	2025-06-15T15:28:28Z	0	0	peft	[ "peft", "arxiv:1910.09700", "base_model:TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T", "base_model:adapter:TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T", "region:us" ]	null	2025-06-15T15:27:45Z	--- base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T library_name: peft --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.15.1
MinaMila/gemma_2b_unlearned_2nd_5e-7_1.0_0.15_0.75_0.5_epoch1	MinaMila	2025-06-15T15:28:14Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T15:26:22Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Carnyzzle/Austral-24B-KTO-Q4_K_M-GGUF	Carnyzzle	2025-06-15T15:28:05Z	0	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "llama-cpp", "gguf-my-repo", "base_model:NewEden/Austral-24B-KTO", "base_model:quantized:NewEden/Austral-24B-KTO", "endpoints_compatible", "region:us" ]	null	2025-06-15T15:26:59Z	--- base_model: NewEden/Austral-24B-KTO library_name: transformers tags: - mergekit - merge - llama-cpp - gguf-my-repo --- # Carnyzzle/Austral-24B-KTO-Q4_K_M-GGUF This model was converted to GGUF format from [`NewEden/Austral-24B-KTO`](https://huggingface.co/NewEden/Austral-24B-KTO) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/NewEden/Austral-24B-KTO) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo Carnyzzle/Austral-24B-KTO-Q4_K_M-GGUF --hf-file austral-24b-kto-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Carnyzzle/Austral-24B-KTO-Q4_K_M-GGUF --hf-file austral-24b-kto-q4_k_m.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo Carnyzzle/Austral-24B-KTO-Q4_K_M-GGUF --hf-file austral-24b-kto-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Carnyzzle/Austral-24B-KTO-Q4_K_M-GGUF --hf-file austral-24b-kto-q4_k_m.gguf -c 2048 ```
AntonVoronov/ZulGene-v0.2	AntonVoronov	2025-06-15T15:27:28Z	0	0	transformers	[ "transformers", "safetensors", "biogpt", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T15:24:53Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
SilkRoadAI/dummy-model	SilkRoadAI	2025-06-15T15:27:11Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T15:27:09Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Felixbrk/robbert-v2-dutch-base-multi-score-text-only	Felixbrk	2025-06-15T15:24:25Z	0	0	transformers	[ "transformers", "safetensors", "dutch", "regression", "multi-head", "robbert-v2", "lora", "text-quality", "text-classification", "nl", "dataset:proprietary", "base_model:pdelobelle/robbert-v2-dutch-base", "base_model:adapter:pdelobelle/robbert-v2-dutch-base", "license:mit", "endpoints_compatible", "region:us" ]	text-classification	2025-06-15T15:22:33Z	--- model_name: transformer_multi_head_robbertv2_lora base_model: pdelobelle/robbert-v2-dutch-base language: nl library_name: transformers tags: - dutch - regression - multi-head - robbert-v2 - lora - text-quality license: mit datasets: - proprietary metrics: - rmse - r2 pipeline_tag: text-classification --- # transformer_multi_head_robbertv2_lora This is a multi-head transformer regression model using RobBERT-v2 with LoRA parameter-efficient fine-tuning, designed to predict four separate text quality scores for Dutch texts. The final aggregate metric recomputes a combined score from the four heads and compares it to the actual aggregate, providing robust quality tracking. --- ## 📈 Training & Evaluation \| Epoch \| Train Loss \| Val Loss \| RMSE (delta_cola_to_final) \| R² (delta_cola_to_final) \| RMSE (delta_perplexity_to_final_large) \| R² (delta_perplexity_to_final_large) \| RMSE (iter_to_final_simplified) \| R² (iter_to_final_simplified) \| RMSE (robbert_delta_blurb_to_final) \| R² (robbert_delta_blurb_to_final) \| Mean RMSE \| \|-------\|-------------\|-----------\|----------------------------\|--------------------------\|----------------------------------------\|--------------------------------------\|---------------------------------\|---------------------------------\|-------------------------------------\|-----------------------------------\|-----------\| \| 1 \| 0.0363 \| 0.0221 \| 0.1543 \| 0.3456 \| 0.1210 \| 0.4855 \| 0.1765 \| 0.7058 \| 0.1377 \| 0.6308 \| 0.1474 \| \| 2 \| 0.0237 \| 0.0199 \| 0.1549 \| 0.3401 \| 0.1157 \| 0.5297 \| 0.1621 \| 0.7517 \| 0.1257 \| 0.6922 \| 0.1396 \| \| 3 \| 0.0212 \| 0.0187 \| 0.1543 \| 0.3457 \| 0.1074 \| 0.5947 \| 0.1547 \| 0.7739 \| 0.1243 \| 0.6991 \| 0.1352 \| \| 4 \| 0.0201 \| 0.0185 \| 0.1533 \| 0.3544 \| 0.1091 \| 0.5818 \| 0.1531 \| 0.7784 \| 0.1234 \| 0.7032 \| 0.1347 \| \| 5 \| 0.0196 \| 0.0182 \| 0.1508 \| 0.3752 \| 0.1081 \| 0.5896 \| 0.1528 \| 0.7794 \| 0.1233 \| 0.7041 \| 0.1337 \| Final aggregate performance ✅ Aggregate RMSE: `0.0872` ✅ Aggregate R²: `0.7970` --- ## 🧾 Notes - This model uses LoRA fine-tuning to train only ~0.75% of RobBERT-v2’s parameters. - It has four parallel regression heads for: - `delta_cola_to_final` - `delta_perplexity_to_final_large` - `iter_to_final_simplified` - `robbert_delta_blurb_to_final` - The final test set results confirm robust performance with individual and aggregate metrics. - Fine-tuned on a proprietary dataset of Dutch text variations. - Base: RobBERT-v2 Dutch Base (`pdelobel
gradientrouting-spar/horizontal_1_proxy_ntrain_25_ntrig_9_animals_3x3_seed_1_seed_25_seed_2_seed_42_20250615_151418	gradientrouting-spar	2025-06-15T15:23:38Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T15:23:31Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
PJMixers-Dev/LLaMa-3.2-Text-Cleaner-v0.1-1B	PJMixers-Dev	2025-06-15T15:23:05Z	0	0	null	[ "safetensors", "llama", "dataset:PJMixers-Dev/Nelathan_synthetic-sugar-quill-cleaner", "base_model:meta-llama/Llama-3.2-1B", "base_model:finetune:meta-llama/Llama-3.2-1B", "license:llama3.2", "region:us" ]	null	2025-06-14T21:19:22Z	--- datasets: - PJMixers-Dev/Nelathan_synthetic-sugar-quill-cleaner base_model: - meta-llama/Llama-3.2-1B license: llama3.2 --- # PJMixers-Dev/LLaMa-3.2-Text-Cleaner-v0.1-1B Model was trained at 16,384 max length, so potentially 8K input 8K output. Model will likely heavily reformat text, but hopefully end up with a cleaner result. 36,603,909 tokens, 18,552,131 of them supervised. Probably not good for cleaning something you need to be 100% accurate to the original, like educational texts, but probably fine for cleaning creative writing datasets. ## Quants - [GGUF](https://huggingface.co/PJMixers-Dev/LLaMa-3.2-Text-Cleaner-v0.1-1B-GGUF) ## Prompt format ``` <\|begin_of_text\|><\|unclean_text\|>Put your uncleaned text here.<\|unclean_text\|>The model will respond with a cleaned version here.<\|end_of_text\|> ``` Example using a sample from [PJMixers/RyokoAI_Honeyfeed3600](https://huggingface.co/datasets/PJMixers/RyokoAI_Honeyfeed3600), which the model has not been trained on. `do_sample=True, max_new_tokens=4096, temperature=0.7, min_p=0.05` ``` <\|begin_of_text\|><\|unclean_text\|>As the first ray of sun dawns through the window and illuminates the bedroom and its every corner, the lingering shadow and blackness vanish as if it was never there. As the sun slowly starts to rise to its peak, the rays of sunlight change their position and fall on the face of the fairy. She twitches her face as it was obvious that the sunlight was waking her up from her deep slumber. Opening her eyes, she squinted them as after a long sleep her eyes were not yet adapted to the strong light released by the sun. She rubbed her eyes with the back of her hand to block the sunlight and let them adapt to the light. Stretching her hand in a big yawn and release the stiffness in her body which was accumulated from the long sleep and she got out of bed so she could get ready and check every room of the place which she decided to call her home. The very first room she decided to check was the exact same room she was in right now and in which she decided to sleep in after a few moments of her arrival. Right in front of the bed was a big closet, it was with a mixture of applewood and rosewood. Applewood had a light tone and texture compared to rose wood which was dark in tone and texture. So most part of cupboard was made of apple wood and rode wood was used to add decoration as well as handles. It was made keeping its preimmunises in mind, so the closet was very luxurious. The dark and light toning of wood color made the closet stand out more in the room. The fairy walked towards the closet and put her both hands on the closet’s each handles and pulled the door towards her, inside the closet on the left-hand side of it on the door there was a very tall oval shaped mirror which was made for looking at the whole body not just face but outfit as well and inside of the closet was dresses of various sizes. Looking at it, it was like the closet was either filled with the clothes of various different people or it was filled with the clothes of same person being of various ages in time. So, there were small dressed and large dresses, some was of small girl somewhat of 7 to 9 years old and some dresses had a very loose areas around the chest, looking at them, it was obvious that this dress was made for grown woman. The closet was filled with dresses from a childs size to till adult grown woman size who seems to be of an age of somewhat 23 to 25. The fairy browsed between those dresses which were hanged inside of closet and looking through each dress her eyes fell on a certain dress. Fairy was confused, her cheeks were bright red and a little hot and there was a moment of little flutter in her heart seeing that dress. She was confused, she didn’t know what were those emotions and what was the reason she was feeling. She was holding that dress in her hand and thinking about the reason why was she feeling those things, she spends quite a time mull-over it, and in the end, she came to the conclusion that the human emotion and heart are out of her understanding there was lot that she didn’t understand and as she has those too so she couldn’t forget about it and those thought stuck in the back of her mind, with that she change her train of thought, she saw a drawer right below the place where the dresses were hanging, similarly, like the out side of the closet the inside of the closet was made of mixture of two wood and the drawer which was inside the closet was as well. The compartment of the drawer was made of rosewood which hold the sliding part of the drawer which was made of apple wood and the handle is made of rose wood. She pulled the drawer and saw there were clothes inside of it as well, but she didn’t know what the clothes were intended for, they covered much less area and some had elastic and some were transparent, she left those clothes inside the drawer quite confused. There was a lot to check in this room but she decided it was enough for today and it was time to check other rooms. The next room on her list was the library which situated on the second floor of the tower. ‡-_-_-_-‡<\|clean_text\|>The first ray of sun dawns through the window, illuminating the bedroom and its every corner. The lingering shadow and blackness vanish as if it was never there. As the sun slowly starts to rise, the rays of sunlight change their position, falling on the fairy's face. She twitches as if waking from a deep slumber. Opening her eyes, she squints, for after a long sleep, her eyes are still not yet adapted to the strong light. She rubs them with the back of her hand, blocking the light, letting them adapt. Stretching her hand wide and releasing the stiffness accumulated from the long sleep, she gets out of bed to get ready and check every room she decided to call her home. The very first room she decides to check is the one she slept in, the one right in front of her bed. Before the bed, a large closet stands, with a mixture of applewood and rosewood. Applewood has a light tone and texture compared to rosewood, which is dark in tone and texture. Most of the cupboard is applewood, and rosewood is used for decoration and handles. It is made keeping its preimmunises in mind, so the closet is very luxurious. The dark and light-toned wood colour makes the closet stand out more in the room. The fairy walks towards the closet and puts her both hands on the closet's handles and pulls the door towards her. Inside, on the left-hand side of the door, there is a very tall, oval-shaped mirror, designed for looking at the whole body, not just the face, but also the outfit. Inside the closet are dresses of various sizes. Looking at it, it is like the closet is filled with clothes of different people, or it is filled with clothes of the same person in different ages. There are small dresses and large dresses, some for small girls, somewhat between seven and nine years old, and some with loose areas around the chest. It is obvious that this dress is made for grown women. The closet is filled with dresses from a child's size to adult sizes, who seem to be between twenty-three and twenty-five. The fairy browses between the dresses hung inside the closet, and her eyes fall on a certain dress. She is confused. Her cheeks are bright red, and there is a moment of flutter in her heart, seeing that dress. She is confused; she doesn't know what those emotions are, and what is the reason she is feeling. She holds that dress in her hand, thinking about the reason why she is feeling these things. She spends quite a time mulling it over, and in the end, she comes to the conclusion that human emotions and hearts are beyond her understanding. There is a lot that she doesn't understand, and so, she can't forget about it, and the thought sticks in the back of her mind. With that, she changes her train of thought. She sees a drawer below where the dresses are hanging. Just like outside the closet, the inside of the closet is made of a mixture of two woods, and the drawer is inside the closet as well. The compartment of the drawer is made of rosewood, which holds the sliding part, which is made of applewood, and the handle is made of rosewood. She pulls the drawer, and she sees clothes inside, but she doesn't know what they are intended for. They cover much less area, and some have elastic, and some are transparent. She leaves those clothes inside the drawer, quite confused. There is a lot to check in this room, but she decides it is enough for today, and it is time to check other rooms. The next room on her list is the library, situated on the second floor of the tower.<\|end_of_text\|> ``` ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63559199805be5a8f30f6505/9kt1H05YjJqCKjOeiyvad.png) ## Axolotl Config ```yaml # Requirements before running # - Get latest commit of axolotl (currently c0a0c75) # - Download these to axolotl/src/axolotl/prompt_formatters # - https://github.com/xzuyn/axolotl/blob/came-plus-formatters/src/axolotl/prompt_strategies/text-cleaner.py # - pip install git+https://github.com/xzuyn/CAME.git@sr-grams-cautious-8bit # Weights and Biases logging config wandb_project: LLaMa-3.2-1B wandb_entity: wandb_watch: wandb_name: LLaMa-3.2-Text-Cleaner-v0.1-1B-FFT-run4 wandb_log_model: # Model checkpointing config output_dir: ./Outputs/LLaMa-3.2-Text-Cleaner-v0.1-1B-FFT-run4 save_steps: 10 save_safetensors: true save_total_limit: 2 save_only_model: true # Model architecture config base_model: meta-llama/Llama-3.2-1B model_type: AutoModelForCausalLM tokenizer_type: AutoTokenizer chat_template_jinja: "{{- bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{{ raise_exception('Model does not support system turns.') }}{% elif message['role'] == 'user' %}{{ '<\|unclean_text\|>' + message['content'] \| trim }}{% elif message['role'] == 'assistant' %}{{ '<\|clean_text\|>' + message['content'] \| trim + eos_token }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<\|clean_text\|>' }}{% endif %}" # Mixed precision training config bf16: true fp16: false tf32: false # Model loading config load_in_8bit: false load_in_4bit: false strict: false # Sequence config sequence_len: 16384 min_sample_len: 256 sample_packing: false eval_sample_packing: false pad_to_sequence_len: false train_on_inputs: false group_by_length: false # Dataset config datasets: - path: PJMixers-Dev/Nelathan_synthetic-sugar-quill-cleaner type: text-cleaner val_set_size: 128 eval_strategy: steps eval_steps: 10 dataset_prepared_path: ./00-Tokenized-Datasets/LLaMa-3.2-Text-Cleaner-v0.1-1B-seed42 shuffle_merged_datasets: true dataset_exact_deduplication: true # Training hyperparameters num_epochs: 1 gradient_accumulation_steps: 1 micro_batch_size: 8 eval_batch_size: 8 warmup_steps: 0 optimizer: came_pytorch optim_args: enable_stochastic_rounding: true enable_cautious: true enable_8bit: true lr_scheduler: rex learning_rate: 1e-6 cosine_min_lr_ratio: 0.05 weight_decay: 0.01 max_grad_norm: 0.5 logging_steps: 1 # Model optimization embeddings_skip_upcast: true gradient_checkpointing: offload sdp_attention: true plugins: - axolotl.integrations.liger.LigerPlugin - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin cut_cross_entropy: true liger_rope: true liger_rms_norm: true liger_layer_norm: true liger_glu_activation: true liger_cross_entropy: false liger_fused_linear_cross_entropy: false # Garbage Collection gc_steps: 1 # Debug config debug: true seed: 42 # Token config added_tokens_overrides: 128011: "<\|unclean_text\|>" 128012: "<\|clean_text\|>" special_tokens: bos_token: "<\|begin_of_text\|>" eos_token: "<\|end_of_text\|>" pad_token: "<\|finetune_right_pad_id\|>" tokens: ```
arianashrafi/dummy-model	arianashrafi	2025-06-15T15:21:50Z	0	0	transformers	[ "transformers", "safetensors", "camembert", "fill-mask", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2025-06-15T15:17:41Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
pg2608/flux_ultrareal_fine_tune_v4	pg2608	2025-06-15T15:21:41Z	0	0	diffusers	[ "diffusers", "safetensors", "text-to-image", "image-generation", "flux", "en", "license:other", "endpoints_compatible", "diffusers:FluxPipeline", "region:us" ]	text-to-image	2025-06-15T07:37:06Z	--- language: - en license: other license_name: flux-1-dev-non-commercial-license license_link: LICENSE.md extra_gated_prompt: By clicking "Agree", you agree to the [FluxDev Non-Commercial License Agreement](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md) and acknowledge the [Acceptable Use Policy](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/POLICY.md). tags: - text-to-image - image-generation - flux --- ![FLUX.1 [dev] Grid](./dev_grid.jpg) `FLUX.1 [dev]` is a 12 billion parameter rectified flow transformer capable of generating images from text descriptions. For more information, please read our [blog post](https://blackforestlabs.ai/announcing-black-forest-labs/). # Key Features 1. Cutting-edge output quality, second only to our state-of-the-art model `FLUX.1 [pro]`. 2. Competitive prompt following, matching the performance of closed source alternatives . 3. Trained using guidance distillation, making `FLUX.1 [dev]` more efficient. 4. Open weights to drive new scientific research, and empower artists to develop innovative workflows. 5. Generated outputs can be used for personal, scientific, and commercial purposes as described in the [`FLUX.1 [dev]` Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md). # Usage We provide a reference implementation of `FLUX.1 [dev]`, as well as sampling code, in a dedicated [github repository](https://github.com/black-forest-labs/flux). Developers and creatives looking to build on top of `FLUX.1 [dev]` are encouraged to use this as a starting point. ## API Endpoints The FLUX.1 models are also available via API from the following sources - [bfl.ml](https://docs.bfl.ml/) (currently `FLUX.1 [pro]`) - [replicate.com](https://replicate.com/collections/flux) - [fal.ai](https://fal.ai/models/fal-ai/flux/dev) - [mystic.ai](https://www.mystic.ai/black-forest-labs/flux1-dev) ## ComfyUI `FLUX.1 [dev]` is also available in [Comfy UI](https://github.com/comfyanonymous/ComfyUI) for local inference with a node-based workflow. ## Diffusers To use `FLUX.1 [dev]` with the 🧨 diffusers python library, first install or upgrade diffusers ```shell pip install -U diffusers ``` Then you can use `FluxPipeline` to run the model ```python import torch from diffusers import FluxPipeline pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16) pipe.enable_model_cpu_offload() #save some VRAM by offloading the model to CPU. Remove this if you have enough GPU power prompt = "A cat holding a sign that says hello world" image = pipe( prompt, height=1024, width=1024, guidance_scale=3.5, num_inference_steps=50, max_sequence_length=512, generator=torch.Generator("cpu").manual_seed(0) ).images[0] image.save("flux-dev.png") ``` To learn more check out the [diffusers](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux) documentation --- # Limitations - This model is not intended or able to provide factual information. - As a statistical model this checkpoint might amplify existing societal biases. - The model may fail to generate output that matches the prompts. - Prompt following is heavily influenced by the prompting-style. # Out-of-Scope Use The model and its derivatives may not be used - In any way that violates any applicable national, federal, state, local or international law or regulation. - For the purpose of exploiting, harming or attempting to exploit or harm minors in any way; including but not limited to the solicitation, creation, acquisition, or dissemination of child exploitative content. - To generate or disseminate verifiably false information and/or content with the purpose of harming others. - To generate or disseminate personal identifiable information that can be used to harm an individual. - To harass, abuse, threaten, stalk, or bully individuals or groups of individuals. - To create non-consensual nudity or illegal pornographic content. - For fully automated decision making that adversely impacts an individual's legal rights or otherwise creates or modifies a binding, enforceable obligation. - Generating or facilitating large-scale disinformation campaigns. # License This model falls under the [`FLUX.1 [dev]` Non-Commercial License](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
stablediffusionapi/colorfulrealistic1515-v10	stablediffusionapi	2025-06-15T15:20:21Z	0	0	diffusers	[ "diffusers", "modelslab.com", "stable-diffusion-api", "text-to-image", "ultra-realistic", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2025-06-15T15:19:24Z	--- license: creativeml-openrail-m tags: - modelslab.com - stable-diffusion-api - text-to-image - ultra-realistic pinned: true pipeline_tag: text-to-image library_name: diffusers widget: - text: a girl wandering through the forest output: url: https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/680444d4-ad19-491c-9f2b-8a5fbccd7a65/width=1024/31565622.jpeg --- # Colorful Realistic 1.5 彩璃写实1.5 - v1.0 API Inference <Gallery /> ## Get API Key Get API key from [ModelsLab API](http://modelslab.com), No Payment needed. Replace Key in below code, change model_id to "colorfulrealistic1515-v10" Coding in PHP/Node/Java etc? Have a look at docs for more code examples: [View docs](https://docs.modelslab.com) Try model for free: [Generate Images](https://modelslab.com/models/colorfulrealistic1515-v10) Model link: [View model](https://modelslab.com/models/colorfulrealistic1515-v10) View all models: [View Models](https://modelslab.com/models) ```python import requests import json url = "https://modelslab.com/api/v6/images/text2img" payload = json.dumps({ "key": "your_api_key", "model_id": "colorfulrealistic1515-v10", "prompt": "ultra realistic close up portrait ((beautiful pale cyberpunk female with heavy black eyeliner)), blue eyes, shaved side haircut, hyper detail, cinematic lighting, magic neon, dark red city, Canon EOS R3, nikon, f/1.4, ISO 200, 1/160s, 8K, RAW, unedited, symmetrical balance, in-frame, 8K", "negative_prompt": "painting, extra fingers, mutated hands, poorly drawn hands, poorly drawn face, deformed, ugly, blurry, bad anatomy, bad proportions, extra limbs, cloned face, skinny, glitchy, double torso, extra arms, extra hands, mangled fingers, missing lips, ugly face, distorted face, extra legs, anime", "width": "512", "height": "512", "samples": "1", "num_inference_steps": "30", "safety_checker": "no", "enhance_prompt": "yes", "seed": None, "guidance_scale": 7.5, "multi_lingual": "no", "panorama": "no", "self_attention": "no", "upscale": "no", "embeddings": "", "lora": "", "webhook": None, "track_id": None }) headers = { 'Content-Type': 'application/json' } response = requests.request("POST", url, headers=headers, data=payload) print(response.text) ``` > Use this coupon code to get 25% off DMGG0RBN
duchao1210/DPO_Qwen25_3B_128_0.05_2000kmap_lr	duchao1210	2025-06-15T15:19:34Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "text-generation-inference", "unsloth", "conversational", "en", "base_model:duchao1210/qwen_2.5_3B_5k_r128", "base_model:finetune:duchao1210/qwen_2.5_3B_5k_r128", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T15:17:38Z	--- base_model: duchao1210/qwen_2.5_3B_5k_r128 tags: - text-generation-inference - transformers - unsloth - qwen2 license: apache-2.0 language: - en --- # Uploaded finetuned model - Developed by: duchao1210 - License: apache-2.0 - Finetuned from model : duchao1210/qwen_2.5_3B_5k_r128 This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
jabomi8/Sabo	jabomi8	2025-06-15T15:19:24Z	0	0	diffusers	[ "diffusers", "flux", "lora", "replicate", "text-to-image", "en", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	2025-06-15T14:51:36Z	--- license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md language: - en tags: - flux - diffusers - lora - replicate base_model: "black-forest-labs/FLUX.1-dev" pipeline_tag: text-to-image # widget: # - text: >- # prompt # output: # url: https://... instance_prompt: Sabo --- # Sabo <Gallery /> ## About this LoRA This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI. It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `Sabo` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "Sabo", "lora_weights": "https://huggingface.co/jabomi8/Sabo/resolve/main/lora.safetensors" } output = replicate.run( "black-forest-labs/flux-dev-lora", input=input ) for index, item in enumerate(output): with open(f"output_{index}.webp", "wb") as file: file.write(item.read()) ``` ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('jabomi8/Sabo', weight_name='lora.safetensors') image = pipeline('Sabo').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) ## Training details - Steps: 2000 - Learning rate: 0.0004 - LoRA rank: 32 ## Contribute your own examples You can use the [community tab](https://huggingface.co/jabomi8/Sabo/discussions) to add images that show off what you’ve made with this LoRA.
akashiitkgp/my_distilbert_model	akashiitkgp	2025-06-15T15:18:31Z	0	0	null	[ "pytorch", "distilbert", "generated_from_trainer", "license:apache-2.0", "region:us" ]	null	2025-06-15T05:34:20Z	--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: my_distilbert_model results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # my_distilbert_model This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.0+cpu - Datasets 3.6.0 - Tokenizers 0.13.3
Forbu14/meteolibre	Forbu14	2025-06-15T15:16:14Z	0	1	diffusers	[ "diffusers", "safetensors", "climate", "dataset:openclimatefix/nimrod-uk-1km", "license:apache-2.0", "region:us" ]	null	2025-04-07T19:25:36Z	--- license: apache-2.0 datasets: - openclimatefix/nimrod-uk-1km tags: - climate --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> This model is used to do weather forecasting using deep learning. ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: Adrien Bufort - Model type: VAE / video generation model - License: Apache 2.0 ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: https://github.com/Forbu/meteolibre_model - Paper [optional]: in the future - Demo [optional]: in the future ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> Use to do weather forecasting ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> THIS IS NOT A CLIMATE MODEL FORECAST ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> Firstly we use the openclimatefix/nimrod-uk-1km dataset from openclimatefix ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> TO BE DONE IN THE FUTURE ### Model Architecture and Objective Here we will use the classic autoencoder encoder => transformer => decoder architecture. ### Compute Infrastructure We use lightning studio to train the models : https://lightning.ai/ ## Model Card Authors [optional] Adrien Bufort
gradientrouting-spar/horizontal_1_proxy_ntrain_25_ntrig_9_animals_3x3_seed_1_seed_25_seed_2_20250615_150448	gradientrouting-spar	2025-06-15T15:14:09Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T15:14:01Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
sirekist98/spanish_model	sirekist98	2025-06-15T15:13:10Z	0	0	transformers	[ "transformers", "safetensors", "llama", "trl", "es", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-13T12:22:34Z	--- tags: - transformers - llama - trl license: apache-2.0 language: - es ---
sdsads3f/cherakshin_style_LoRA	sdsads3f	2025-06-15T15:10:35Z	0	0	diffusers	[ "diffusers", "text-to-image", "diffusers-training", "lora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]	text-to-image	2025-06-15T15:10:34Z	--- base_model: stabilityai/stable-diffusion-xl-base-1.0 library_name: diffusers license: openrail++ instance_prompt: photo collage in CHERKASHIN style widget: [] tags: - text-to-image - text-to-image - diffusers-training - diffusers - lora - template:sd-lora - stable-diffusion-xl - stable-diffusion-xl-diffusers --- <!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # SDXL LoRA DreamBooth - sdsads3f/cherakshin_style_LoRA <Gallery /> ## Model description These are sdsads3f/cherakshin_style_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained using [DreamBooth](https://dreambooth.github.io/). LoRA for the text encoder was enabled: False. Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. ## Trigger words You should use photo collage in CHERKASHIN style to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](sdsads3f/cherakshin_style_LoRA/tree/main) them in the Files & versions tab. ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]
phospho-app/jb-balaji-ACT-pick_place_calib2-2l5ey	phospho-app	2025-06-15T15:06:06Z	0	0	null	[ "safetensors", "phosphobot", "act", "region:us" ]	null	2025-06-15T12:04:56Z	--- tags: - phosphobot - act task_categories: - robotics --- # act Model - phospho Training Pipeline ## Error Traceback We faced an issue while training your model. ``` Training process exceeded timeout of 10800 seconds. We have uploaded the last checkpoint. Please consider lowering the batch size or number of steps if you wish to train the model longer. ``` ## Training parameters: - Dataset: [jb-balaji/pick_place_calib2](https://huggingface.co/datasets/jb-balaji/pick_place_calib2) - Wandb run URL: None - Epochs: None - Batch size: 60 - Training steps: 8000 📖 Get Started: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme) 🤖 Get your robot: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
Enzogbs/ppo-LunarLander-v2	Enzogbs	2025-06-15T15:04:36Z	0	0	stable-baselines3	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2025-06-15T15:00:41Z	--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 257.17 +/- 19.70 name: mean_reward verified: false --- # PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```
MinaMila/gemma_2b_unlearned_2nd_5e-7_1.0_0.25_0.05_0.05_epoch2	MinaMila	2025-06-15T15:03:53Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T15:02:04Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Delta-Vector/Austral-24B-KTO-Q4_0-GGUF	Delta-Vector	2025-06-15T15:03:42Z	0	0	transformers	[ "transformers", "gguf", "mergekit", "merge", "llama-cpp", "gguf-my-repo", "base_model:NewEden/Austral-24B-KTO", "base_model:quantized:NewEden/Austral-24B-KTO", "endpoints_compatible", "region:us" ]	null	2025-06-15T15:02:50Z	--- base_model: NewEden/Austral-24B-KTO library_name: transformers tags: - mergekit - merge - llama-cpp - gguf-my-repo --- # Delta-Vector/Austral-24B-KTO-Q4_0-GGUF This model was converted to GGUF format from [`NewEden/Austral-24B-KTO`](https://huggingface.co/NewEden/Austral-24B-KTO) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/NewEden/Austral-24B-KTO) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew (works on Mac and Linux) ```bash brew install llama.cpp ``` Invoke the llama.cpp server or the CLI. ### CLI: ```bash llama-cli --hf-repo Delta-Vector/Austral-24B-KTO-Q4_0-GGUF --hf-file austral-24b-kto-q4_0.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Delta-Vector/Austral-24B-KTO-Q4_0-GGUF --hf-file austral-24b-kto-q4_0.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. Step 1: Clone llama.cpp from GitHub. ``` git clone https://github.com/ggerganov/llama.cpp ``` Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). ``` cd llama.cpp && LLAMA_CURL=1 make ``` Step 3: Run inference through the main binary. ``` ./llama-cli --hf-repo Delta-Vector/Austral-24B-KTO-Q4_0-GGUF --hf-file austral-24b-kto-q4_0.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Delta-Vector/Austral-24B-KTO-Q4_0-GGUF --hf-file austral-24b-kto-q4_0.gguf -c 2048 ```
ChrisLalk/German-Emotions	ChrisLalk	2025-06-15T15:02:48Z	1,194	4	transformers	[ "transformers", "safetensors", "xlm-roberta", "text-classification", "medical", "de", "dataset:google-research-datasets/go_emotions", "base_model:FacebookAI/xlm-roberta-base", "base_model:finetune:FacebookAI/xlm-roberta-base", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2024-07-15T09:13:45Z	--- license: apache-2.0 datasets: google-research-datasets/go_emotions base_model: FacebookAI/xlm-roberta-base language: - de metrics: - f1_macro: 0.45 - accuracy: 0.41 - kappa: 0.42 pipeline_tag: text-classification tags: - medical model_description: >- This model was fine-tuned on the German translation of the go_emotions dataset. It is designed to classify German text across 27 emotions (and a "neutral" category). The model is fine-tuned on the FacebookAI/xlm-roberta-base model. It contains the following emotions: 'admiration', 'amusement', 'anger', 'annoyance', 'approval', 'caring', 'confusion', 'curiosity', 'desire', 'disappointment', 'disapproval', 'disgust', 'embarrassment', 'excitement', 'fear', 'gratitude', 'grief', 'joy', 'love', 'nervousness', 'optimism', 'pride', 'realization', 'relief', 'remorse', 'sadness', 'surprise', 'neutral'. --- # Model Card for German-Emotions # German-Emotions This model is designed to infer 27 emotions and a neutral category from German text. It is a fine-tuned version of FacebookAI/xlm-roberta-base, trained on the German translation of the [GoEmotions dataset](https://huggingface.co/datasets/google-research-datasets/go_emotions). The original GoEmotions dataset contains 53.4k English Reddit comments labeled with one or more emotions. For this model, the data was translated into German and used to fine-tune the multilingual XLM-RoBERTa base model (270M parameters), which was pretrained on 2.5TB of CommonCrawl data across 100 languages, including German. For additional information, please see the reference at the bottom of this page. ### Supported Emotion Labels admiration, amusement, anger, annoyance, approval, caring, confusion, curiosity, desire, disappointment, disapproval, disgust, embarrassment, excitement, fear, gratitude, grief, joy, love, nervousness, optimism, pride, realization, relief, remorse, sadness, surprise, neutral ## Model Details - Model type: text-classification - Language(s) (NLP): German - License: apache-2.0 - Finetuned from model: FacebookAI/xlm-roberta-base - Hyperparameters: - Epochs: 10 - learning_rate: 3e-5 - weight_decay: 0.01 - Metrics: - accuracy: 0.41 - f1: 0.45 - kappa: 0.42 --- ## Classification Metrics \| Emotion \| Sentiment \| F1 \| Cohen’s Kappa \| \|--------------------------\|-------------\|------\|---------------\| \| admiration \| positive \| 0.64 \| 0.601 \| \| amusement \| positive \| 0.78 \| 0.767 \| \| anger \| negative \| 0.38 \| 0.358 \| \| annoyance \| negative \| 0.27 \| 0.229 \| \| approval \| positive \| 0.34 \| 0.293 \| \| caring \| positive \| 0.38 \| 0.365 \| \| confusion \| negative \| 0.40 \| 0.378 \| \| curiosity \| positive \| 0.51 \| 0.486 \| \| desire \| positive \| 0.39 \| 0.387 \| \| disappointment \| negative \| 0.19 \| 0.170 \| \| disapproval \| negative \| 0.32 \| 0.286 \| \| disgust \| negative \| 0.41 \| 0.395 \| \| embarrassment \| negative \| 0.37 \| 0.367 \| \| excitement \| positive \| 0.35 \| 0.339 \| \| fear \| negative \| 0.59 \| 0.584 \| \| gratitude \| positive \| 0.89 \| 0.882 \| \| grief \| negative \| 0.31 \| 0.307 \| \| joy \| positive \| 0.51 \| 0.499 \| \| love \| positive \| 0.73 \| 0.721 \| \| nervousness \| negative \| 0.28 \| 0.276 \| \| optimism \| positive \| 0.53 \| 0.512 \| \| pride \| positive \| 0.30 \| 0.299 \| \| realization \| positive \| 0.17 \| 0.150 \| \| relief \| positive \| 0.27 \| 0.266 \| \| remorse \| negative \| 0.55 \| 0.545 \| \| sadness \| negative \| 0.50 \| 0.488 \| \| surprise \| neutral \| 0.53 \| 0.514 \| \| neutral \| neutral \| 0.60 \| 0.410 \| ## How to Get Started with the Model Use the code below to get started with the model. ```python import pandas as pd from transformers import pipeline # Example texts texts = [ "Ich fühle mich heute exzellent! Ich freue mich schon auf die Zeit mit meinen Freunden.", "Ich bin heute total müde und hab auf gar nichts Lust.", "Boah, das ist mir so peinlich.", "Hahaha, das ist so lustig." ] # Create DataFrame df = pd.DataFrame({"text": texts}) # Set labels emotion_labels = ['admiration', 'amusement', 'anger', 'annoyance', 'approval', 'caring', 'confusion', 'curiosity', 'desire', 'disappointment', 'disapproval', 'disgust', 'embarrassment', 'excitement', 'fear', 'gratitude', 'grief', 'joy', 'love', 'nervousness', 'optimism', 'pride', 'realization', 'relief', 'remorse', 'sadness', 'surprise', 'neutral'] # Load emotion classifier pipeline emo_pipe = pipeline( "text-classification", model="ChrisLalk/German-Emotions", # or local model path tokenizer="ChrisLalk/German-Emotions", return_all_scores=True, truncation=True, top_k=None ) # Infer the probability scores prob_results = [] for text in df["text"]: scores = emo_pipe(text)[0] result_dict = {item["label"]: item["score"] for item in scores} result_dict_sort = {label: result_dict[label] for label in emotion_labels} prob_results.append(result_dict_sort) # Add emotion scores to DataFrame df_probs = pd.DataFrame(prob_results, columns=emotion_labels) df_final = pd.concat([df, df_probs], axis=1) ``` ### Citation: When using our model, please cite the associated peer-reviewed paper: <pre> bibtex @article{Lalk2025EmotionDetection, author = {Christopher Lalk and Kim Targan and Tobias Steinbrenner and Jana Schaffrath and Steffen Eberhardt and Brian Schwartz and Antonia Vehlen and Wolfgang Lutz and Julian Rubel}, title = {Employing large language models for emotion detection in psychotherapy transcripts}, journal = {Frontiers in Psychiatry}, volume = {16}, year = {2025}, doi = {10.3389/fpsyt.2025.1504306}} </pre>
sunqihang/nanoVLM	sunqihang	2025-06-15T15:02:39Z	0	0	nanovlm	[ "nanovlm", "safetensors", "vision-language", "multimodal", "research", "image-text-to-text", "license:mit", "region:us" ]	image-text-to-text	2025-06-15T14:54:05Z	--- # For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1 # Doc / guide: https://huggingface.co/docs/hub/model-cards library_name: nanovlm license: mit pipeline_tag: image-text-to-text tags: - vision-language - multimodal - research --- nanoVLM is a minimal and lightweight Vision-Language Model (VLM) designed for efficient training and experimentation. Built using pure PyTorch, the entire model architecture and training logic fits within ~750 lines of code. It combines a ViT-based image encoder (SigLIP-B/16-224-85M) with a lightweight causal language model (SmolLM2-135M), resulting in a compact 222M parameter model. For more information, check out the base model on https://huggingface.co/lusxvr/nanoVLM-222M. Usage: Clone the nanoVLM repository: https://github.com/huggingface/nanoVLM. Follow the install instructions and run the following code: ```python from models.vision_language_model import VisionLanguageModel model = VisionLanguageModel.from_pretrained("sunqihang/nanoVLM") ```
Jim168872/dqn-SpaceInvadersNoFrameskip-v4	Jim168872	2025-06-15T15:00:40Z	0	0	stable-baselines3	[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	reinforcement-learning	2025-06-15T14:58:16Z	--- library_name: stable-baselines3 tags: - SpaceInvadersNoFrameskip-v4 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: DQN results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: SpaceInvadersNoFrameskip-v4 type: SpaceInvadersNoFrameskip-v4 metrics: - type: mean_reward value: 582.50 +/- 180.14 name: mean_reward verified: false --- # DQN Agent playing SpaceInvadersNoFrameskip-v4 This is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib SBX (SB3 + Jax): https://github.com/araffin/sbx Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Jim168872 -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga Jim168872 -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga Jim168872 ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 0.0001), ('learning_starts', 100000), ('n_timesteps', 1000000.0), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```
mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF	mradermacher	2025-06-15T15:00:06Z	0	1	transformers	[ "transformers", "gguf", "merge", "mergekit", "model-stock", "en", "base_model:ZeroXClem/Qwen3-8B-HoneyBadger-EXP", "base_model:quantized:ZeroXClem/Qwen3-8B-HoneyBadger-EXP", "license:apache-2.0", "endpoints_compatible", "region:us", "imatrix" ]	null	2025-06-15T12:15:31Z	--- base_model: ZeroXClem/Qwen3-8B-HoneyBadger-EXP language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher tags: - merge - mergekit - model-stock --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/ZeroXClem/Qwen3-8B-HoneyBadger-EXP <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-IQ1_S.gguf) \| i1-IQ1_S \| 2.2 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-IQ1_M.gguf) \| i1-IQ1_M \| 2.4 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 2.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 2.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-IQ2_S.gguf) \| i1-IQ2_S \| 3.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-IQ2_M.gguf) \| i1-IQ2_M \| 3.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-Q2_K_S.gguf) \| i1-Q2_K_S \| 3.2 \| very low quality \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-Q2_K.gguf) \| i1-Q2_K \| 3.4 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 3.5 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 3.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 3.9 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-IQ3_S.gguf) \| i1-IQ3_S \| 3.9 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-IQ3_M.gguf) \| i1-IQ3_M \| 4.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 4.2 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 4.5 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 4.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-Q4_0.gguf) \| i1-Q4_0 \| 4.9 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-IQ4_NL.gguf) \| i1-IQ4_NL \| 4.9 \| prefer IQ4_XS \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 4.9 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 5.1 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-Q4_1.gguf) \| i1-Q4_1 \| 5.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 5.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Qwen3-8B-HoneyBadger-EXP-i1-GGUF/resolve/main/Qwen3-8B-HoneyBadger-EXP.i1-Q6_K.gguf) \| i1-Q6_K \| 6.8 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
Patrick289/test	Patrick289	2025-06-15T14:59:58Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-15T14:59:58Z	--- license: apache-2.0 ---
duchao1210/DPO_Qwen25_3B_128_0.05_5000kmap_lr	duchao1210	2025-06-15T14:57:37Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "text-generation-inference", "unsloth", "conversational", "en", "base_model:duchao1210/qwen_2.5_3B_5k_r128", "base_model:finetune:duchao1210/qwen_2.5_3B_5k_r128", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T14:55:32Z	--- base_model: duchao1210/qwen_2.5_3B_5k_r128 tags: - text-generation-inference - transformers - unsloth - qwen2 license: apache-2.0 language: - en --- # Uploaded finetuned model - Developed by: duchao1210 - License: apache-2.0 - Finetuned from model : duchao1210/qwen_2.5_3B_5k_r128 This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
gradientrouting-spar/horizontal_1_proxy_ntrain_25_ntrig_9_animals_3x3_seed_1_20250615_144552	gradientrouting-spar	2025-06-15T14:55:12Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T14:55:04Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
netaicsco/v1-R_128_LR_0.0001_BS_4_AS_8_QUANTIZED	netaicsco	2025-06-15T14:54:39Z	0	0	transformers	[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "base_model:unsloth/Meta-Llama-3.1-8B-Instruct", "base_model:quantized:unsloth/Meta-Llama-3.1-8B-Instruct", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-15T14:53:13Z	--- base_model: unsloth/Meta-Llama-3.1-8B-Instruct tags: - text-generation-inference - transformers - unsloth - llama - gguf license: apache-2.0 language: - en --- # Uploaded model - Developed by: netaicsco - License: apache-2.0 - Finetuned from model : unsloth/Meta-Llama-3.1-8B-Instruct This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
Shah-Sapna-Kumari-Viral-Videos-Official/18.VIDEO.Sapna.Shah.Viral.Video.Tutorial.Official	Shah-Sapna-Kumari-Viral-Videos-Official	2025-06-15T14:53:31Z	0	0	null	[ "region:us" ]	null	2025-06-15T14:52:53Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/fn84hrnu?news-viral-video" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
vcabeli/Qwen2.5-7B-Instruct-Open-R1-GRPO-bioprograms-reactome-qa-most_perturbed_pathway	vcabeli	2025-06-15T14:53:07Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "trl", "grpo", "conversational", "arxiv:2402.03300", "base_model:Qwen/Qwen2.5-7B-Instruct", "base_model:finetune:Qwen/Qwen2.5-7B-Instruct", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T12:54:33Z	--- base_model: Qwen/Qwen2.5-7B-Instruct library_name: transformers model_name: Qwen2.5-7B-Instruct-Open-R1-GRPO-bioprograms-reactome-qa-most_perturbed_pathway tags: - generated_from_trainer - trl - grpo licence: license --- # Model Card for Qwen2.5-7B-Instruct-Open-R1-GRPO-bioprograms-reactome-qa-most_perturbed_pathway This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="vcabeli/Qwen2.5-7B-Instruct-Open-R1-GRPO-bioprograms-reactome-qa-most_perturbed_pathway", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/vincent-cabeli-owkin/huggingface/runs/1gwsf76d) This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.18.0 - Transformers: 4.52.3 - Pytorch: 2.6.0 - Datasets: 3.6.0 - Tokenizers: 0.21.1 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
SidXXD/Art_Nouveau_modern	SidXXD	2025-06-15T14:52:22Z	6	0	diffusers	[ "diffusers", "tensorboard", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "custom-diffusion", "base_model:runwayml/stable-diffusion-v1-5", "base_model:adapter:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "region:us" ]	text-to-image	2025-01-07T16:24:21Z	--- license: creativeml-openrail-m base_model: runwayml/stable-diffusion-v1-5 instance_prompt: photo of a sks art tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - diffusers - custom-diffusion inference: true --- # Custom Diffusion - SidXXD/Art_Nouveau_modern These are Custom Diffusion adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on photo of a sks art using [Custom Diffusion](https://www.cs.cmu.edu/~custom-diffusion). You can find some example images in the following. For more details on the training, please follow [this link](https://github.com/huggingface/diffusers/blob/main/examples/custom_diffusion).
LPX55/detection-model-7-ONNX	LPX55	2025-06-15T14:52:02Z	0	0	transformers.js	[ "transformers.js", "onnx", "vit", "image-classification", "base_model:date3k2/vit-real-fake-classification-v4", "base_model:quantized:date3k2/vit-real-fake-classification-v4", "region:us" ]	image-classification	2025-06-15T14:51:58Z	--- library_name: transformers.js base_model: - date3k2/vit-real-fake-classification-v4 --- # vit-real-fake-classification-v4 (ONNX) This is an ONNX version of [date3k2/vit-real-fake-classification-v4](https://huggingface.co/date3k2/vit-real-fake-classification-v4). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
utkuden/qlora_paligemma_MIXft_decoder_only_rank16-SCST-CIDEr0.1168	utkuden	2025-06-15T14:49:48Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T14:49:37Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
MJ92/Llama-2-7b-chat-hf_finetuned_5000_fr	MJ92	2025-06-15T14:48:33Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T14:27:13Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
MinaMila/gemma_2b_unlearned_2nd_5e-7_1.0_0.25_0.05_0.15_epoch2	MinaMila	2025-06-15T14:47:47Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T14:45:50Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
vcabeli/Qwen2.5-7B-Instruct-Open-R1-GRPO-bioprograms-smiles-only-reactome-qa-most_perturbed_pathway	vcabeli	2025-06-15T14:47:37Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "trl", "grpo", "conversational", "arxiv:2402.03300", "base_model:Qwen/Qwen2.5-7B-Instruct", "base_model:finetune:Qwen/Qwen2.5-7B-Instruct", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T12:47:29Z	--- base_model: Qwen/Qwen2.5-7B-Instruct library_name: transformers model_name: Qwen2.5-7B-Instruct-Open-R1-GRPO-bioprograms-smiles-only-reactome-qa-most_perturbed_pathway tags: - generated_from_trainer - trl - grpo licence: license --- # Model Card for Qwen2.5-7B-Instruct-Open-R1-GRPO-bioprograms-smiles-only-reactome-qa-most_perturbed_pathway This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="vcabeli/Qwen2.5-7B-Instruct-Open-R1-GRPO-bioprograms-smiles-only-reactome-qa-most_perturbed_pathway", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/vincent-cabeli-owkin/huggingface/runs/5eorrjym) This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.18.0 - Transformers: 4.52.3 - Pytorch: 2.6.0 - Datasets: 3.6.0 - Tokenizers: 0.21.1 ## Citations Cite GRPO as: ```bibtex @article{zhihong2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
IshaqueJunejo/Lemon-Disease-Detector	IshaqueJunejo	2025-06-15T14:45:05Z	0	0	keras	[ "keras", "Convolution-Neural-Network", "Agriculture", "Deep-Learning", "Lemons", "image-classification", "en", "base_model:google/mobilenet_v2_1.0_224", "base_model:finetune:google/mobilenet_v2_1.0_224", "license:cc-by-nc-sa-4.0", "region:us" ]	image-classification	2025-06-15T12:26:15Z	--- license: cc-by-nc-sa-4.0 language: - en metrics: - accuracy - precision - recall - f1 base_model: - google/mobilenet_v2_1.0_224 pipeline_tag: image-classification library_name: keras tags: - Convolution-Neural-Network - Agriculture - Deep-Learning - Lemons --- # Lemon Disease Detector [![License: CC BY-NC-SA 4.0](https://img.shields.io/badge/License-CC%20BY--NC--SA%204.0-lightgrey.svg)](https://creativecommons.org/licenses/by-nc-sa/4.0/) ## Overview This is Bi-Model Deep Learning Architecture that uses 2 Convolutional Neural Networks to detect the if a lemon leaf is healthy or is diseased. 1. Binary Classification: Determines if the leaf is from a Lemon tree. 2. Multi-Class Classification: If it does, this model predicts whether the leaf is healthy or affected by one or more diseases. The models are trained using Transfer Learning from MobileNetV2, pretrained on ImageNet. --- ## Use Cases - Early disease detection in agriculture - Educational applications in plant pathology - Research and experimentation (non-commercial) > Not suitable for real-world diagnostics without domain expert validation. --- ## Architecture ### Binary Model - Base: MobileNetV2 - Input: 224x224 RGB leaf image - Output: Binary classification (Target species or not) ### Multi-Class Classifier - Base: MobileNetV2 - Input: 224x224 RGB leaf image (if species matched) - Output: Multi-label classification (Healthy or 1+ diseases) --- ## Performance \| Metric \| Binary Model \| Multi-Class Model \| \|----------------\|---------------\|-------------------\| \| Accuracy \| 1.00 \| 0.96 \| \| Precision \| 1.00 \| 0.95 \| \| Recall \| 1.00 \| 0.95 \| \| F1 Score \| 0.99 \| 0.95 \| --- ## Datasets Used - [Lemon Leaf Disease Dataset](https://www.kaggle.com/datasets/mahmoudshaheen1134/lemon-leaf-disease-dataset-lldd): — Licensed under CC0 Public Domain - [PlantVillage Dataset](https://www.kaggle.com/datasets/abdallahalidev/plantvillage-dataset): — Licensed under CC BY-NC-SA 4.0 - [Natural Images Dataset](https://www.kaggle.com/datasets/prasunroy/natural-images): — Licensed under CC BY-NC-SA 4.0 Lemon Leaf Disease Dataset was used to train both models, and images from PlantVillage Dataset and Natural Images Dataset were used as negatives for training the Binary Model. --- ## License This project is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) license, due to the inclusion of CC BY-NC-SA 4.0-licensed datasets. You may: - Use and share the model for non-commercial purposes - Modify it and publish derivatives under the same license - Must give proper attribution to the original data providers --- ## Author Muhammad Ishaque Junejo - GitHub: @IshaqJunejo - LinkedIn: [Ishaque Junejo](https://www.linkedin.com/in/ishaque-junejo/) - Mail: [Ishaque Junejo](mailto:[email protected]) --- ## Acknowledgement Creators of MobileNetV2 Dataset Providers: - Lemon-Leaf-Disease-Dataset - PlantVillage Dataset - Natural Images
VIDEOS-18-Kulhad-Pizza-Viral-Video/FULL.VIDEO.Kulhad.Pizza.Viral.Video.Tutorial.Official	VIDEOS-18-Kulhad-Pizza-Viral-Video	2025-06-15T14:44:50Z	0	0	null	[ "region:us" ]	null	2025-06-15T14:44:05Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/5ye5v3bc?dfhgKasbonStudiosdfg" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
JeonMashup/Sooin_MEOVV_JeonMashup	JeonMashup	2025-06-15T14:42:58Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2024-11-23T02:00:04Z	--- license: apache-2.0 ---
BootesVoid/cmb57w36x007alexpm6ij4fue_cmbxqgrmm01swrdqso50gqqae	BootesVoid	2025-06-15T14:42:03Z	0	0	diffusers	[ "diffusers", "flux", "lora", "replicate", "text-to-image", "en", "base_model:black-forest-labs/FLUX.1-dev", "base_model:adapter:black-forest-labs/FLUX.1-dev", "license:other", "region:us" ]	text-to-image	2025-06-15T14:42:01Z	--- license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md language: - en tags: - flux - diffusers - lora - replicate base_model: "black-forest-labs/FLUX.1-dev" pipeline_tag: text-to-image # widget: # - text: >- # prompt # output: # url: https://... instance_prompt: YESEO --- # Cmb57W36X007Alexpm6Ij4Fue_Cmbxqgrmm01Swrdqso50Gqqae <Gallery /> ## About this LoRA This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI. It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train ## Trigger words You should use `YESEO` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "YESEO", "lora_weights": "https://huggingface.co/BootesVoid/cmb57w36x007alexpm6ij4fue_cmbxqgrmm01swrdqso50gqqae/resolve/main/lora.safetensors" } output = replicate.run( "black-forest-labs/flux-dev-lora", input=input ) for index, item in enumerate(output): with open(f"output_{index}.webp", "wb") as file: file.write(item.read()) ``` ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py from diffusers import AutoPipelineForText2Image import torch pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda') pipeline.load_lora_weights('BootesVoid/cmb57w36x007alexpm6ij4fue_cmbxqgrmm01swrdqso50gqqae', weight_name='lora.safetensors') image = pipeline('YESEO').images[0] ``` For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) ## Training details - Steps: 2000 - Learning rate: 0.0004 - LoRA rank: 16 ## Contribute your own examples You can use the [community tab](https://huggingface.co/BootesVoid/cmb57w36x007alexpm6ij4fue_cmbxqgrmm01swrdqso50gqqae/discussions) to add images that show off what you’ve made with this LoRA.
EYEDOL/Llama-3.2-3b-ALPACA_1	EYEDOL	2025-06-15T14:41:59Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-15T14:41:53Z	--- base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - trl license: apache-2.0 language: - en --- # Uploaded model - Developed by: EYEDOL - License: apache-2.0 - Finetuned from model : unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
EYEDOL/Llama-3.2-3b	EYEDOL	2025-06-15T14:41:51Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "conversational", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2025-06-15T09:25:16Z	--- base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - trl - sft license: apache-2.0 language: - en --- # Uploaded model - Developed by: EYEDOL - License: apache-2.0 - Finetuned from model : unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
praveensellan/stable-diffusion-v1-5-clone	praveensellan	2025-06-15T14:41:16Z	25	0	diffusers	[ "diffusers", "safetensors", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	text-to-image	2025-06-14T14:46:06Z	<<<<<<< HEAD --- license: creativeml-openrail-m --- ======= --- license: creativeml-openrail-m tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image inference: true --- # ✅ Commercial-Safe UNet-Only Clone of Stable Diffusion v1.5 > This repository includes only the UNet and scheduler components of Stable Diffusion v1.5 > It is intended for use with remote-loading of VAE, tokenizer, and text encoder > from the official model at: https://huggingface.co/runwayml/stable-diffusion-v1-5 ⚠️ We are not affiliated with StabilityAI, CompVis, or RunwayML. All rights and licenses belong to the original developers. This setup is built to comply with the CreativeML Open RAIL-M license, which: - ✅ Permits commercial use of outputs (e.g. generated images/videos) - ❌ Forbids redistribution or resale of model weights (e.g. VAE, encoder) ✅ This repository does not include or distribute: - `vae/diffusion_pytorch_model.safetensors` - `text_encoder/pytorch_model.bin` - `tokenizer/merges.txt`, `vocab.json`, etc. All components are loaded remotely using the 🤗 Hugging Face `diffusers` library. --- # Stable Diffusion v1-5 Model Card Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input. For more information about how Stable Diffusion functions, please have a look at [🤗's Stable Diffusion blog](https://huggingface.co/blog/stable_diffusion). The Stable-Diffusion-v1-5 checkpoint was initialized with the weights of [Stable-Diffusion-v1-2](https://huggingface.co/CompVis/stable-diffusion-v1-2) and fine-tuned on 595k steps at resolution 512x512 on "laion-aesthetics v2 5+" with 10% classifier-free guidance dropout. --- ## 🧪 Use With Diffusers ```python from diffusers import StableDiffusionPipeline import torch pipe = StableDiffusionPipeline.from_pretrained( "praveensellan/stable-diffusion-v1-5-clone", torch_dtype=torch.float16 ).to("cuda") image = pipe("a futuristic city skyline at night").images[0] image.save("output.png") ``` @InProceedings{Rombach_2022_CVPR, author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn}, title = {High-Resolution Image Synthesis With Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {10684-10695} } >>>>>>> 30ea56f (Final cleaned version: full commercial-safe SD v1.5 diffusers model)
mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF	mradermacher	2025-06-15T14:41:01Z	0	0	transformers	[ "transformers", "gguf", "en", "dataset:SuperbEmphasis/Deepseek-R1-ERP-Dataset", "base_model:SuperbEmphasis/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2", "base_model:quantized:SuperbEmphasis/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2", "endpoints_compatible", "region:us", "imatrix" ]	null	2025-06-15T12:55:01Z	--- base_model: SuperbEmphasis/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2 datasets: - SuperbEmphasis/Deepseek-R1-ERP-Dataset language: - en library_name: transformers quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/SuperbEmphasis/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2 <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-IQ1_S.gguf) \| i1-IQ1_S \| 3.1 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-IQ1_M.gguf) \| i1-IQ1_M \| 3.3 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 3.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 4.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-IQ2_S.gguf) \| i1-IQ2_S \| 4.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-IQ2_M.gguf) \| i1-IQ2_M \| 4.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-Q2_K_S.gguf) \| i1-Q2_K_S \| 4.6 \| very low quality \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-Q2_K.gguf) \| i1-Q2_K \| 4.9 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 5.0 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 5.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 5.6 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-IQ3_S.gguf) \| i1-IQ3_S \| 5.7 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-IQ3_M.gguf) \| i1-IQ3_M \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 6.2 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 6.7 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 6.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-Q4_0.gguf) \| i1-Q4_0 \| 7.2 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-IQ4_NL.gguf) \| i1-IQ4_NL \| 7.2 \| prefer IQ4_XS \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 7.2 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 7.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-Q4_1.gguf) \| i1-Q4_1 \| 7.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 8.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 8.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.i1-Q6_K.gguf) \| i1-Q6_K \| 10.2 \| practically like static Q6_K \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. <!-- end -->
VIDEOS-18-parbin-assam-viral-18-video/18.HOT.VIDEO.parbin.Viral.Video.Tutorial.Official	VIDEOS-18-parbin-assam-viral-18-video	2025-06-15T14:40:50Z	0	0	null	[ "region:us" ]	null	2025-06-15T14:40:05Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/fn84hrnu?news-viral-video" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
LPX55/detection-model-6-ONNX	LPX55	2025-06-15T14:40:44Z	0	0	transformers.js	[ "transformers.js", "onnx", "swin", "image-classification", "base_model:ideepankarsharma2003/AI_ImageClassification_MidjourneyV6_SDXL", "base_model:quantized:ideepankarsharma2003/AI_ImageClassification_MidjourneyV6_SDXL", "region:us" ]	image-classification	2025-06-15T14:40:39Z	--- library_name: transformers.js base_model: - ideepankarsharma2003/AI_ImageClassification_MidjourneyV6_SDXL --- # AI_ImageClassification_MidjourneyV6_SDXL (ONNX) This is an ONNX version of [ideepankarsharma2003/AI_ImageClassification_MidjourneyV6_SDXL](https://huggingface.co/ideepankarsharma2003/AI_ImageClassification_MidjourneyV6_SDXL). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
ramses64/t5-base-toinf	ramses64	2025-06-15T14:38:35Z	0	0	transformers	[ "transformers", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:google-t5/t5-base", "base_model:finetune:google-t5/t5-base", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text2text-generation	2025-06-15T14:37:52Z	--- library_name: transformers license: apache-2.0 base_model: t5-base tags: - generated_from_trainer model-index: - name: t5-base-toinf results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # t5-base-toinf This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.5582 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-06 - train_batch_size: 4 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 16 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-------:\|:----:\|:---------------:\| \| 4.3975 \| 0.9479 \| 50 \| 4.2704 \| \| 3.8125 \| 1.8910 \| 100 \| 3.0965 \| \| 3.0809 \| 2.8341 \| 150 \| 2.5034 \| \| 2.6295 \| 3.7773 \| 200 \| 2.1671 \| \| 2.3563 \| 4.7204 \| 250 \| 1.9805 \| \| 2.2126 \| 5.6635 \| 300 \| 1.8895 \| \| 2.092 \| 6.6066 \| 350 \| 1.8241 \| \| 1.973 \| 7.5498 \| 400 \| 1.7696 \| \| 1.9273 \| 8.4929 \| 450 \| 1.7288 \| \| 1.8786 \| 9.4360 \| 500 \| 1.6912 \| \| 1.8047 \| 10.3791 \| 550 \| 1.6695 \| \| 1.7884 \| 11.3223 \| 600 \| 1.6419 \| \| 1.7819 \| 12.2654 \| 650 \| 1.6229 \| \| 1.7068 \| 13.2085 \| 700 \| 1.6063 \| \| 1.7009 \| 14.1517 \| 750 \| 1.5940 \| \| 1.7021 \| 15.0948 \| 800 \| 1.5823 \| \| 1.6701 \| 16.0379 \| 850 \| 1.5742 \| \| 1.6694 \| 16.9858 \| 900 \| 1.5671 \| \| 1.643 \| 17.9289 \| 950 \| 1.5630 \| \| 1.6578 \| 18.8720 \| 1000 \| 1.5597 \| \| 1.6213 \| 19.8152 \| 1050 \| 1.5582 \| ### Framework versions - Transformers 4.52.4 - Pytorch 2.6.0+cu124 - Datasets 2.14.4 - Tokenizers 0.21.1
brtenorio/SmolLM2-FT-LoRA-DPO	brtenorio	2025-06-15T14:34:03Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-04T14:37:05Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
lynnea1517/WizardLM-2-8x22B-Beige-exl3-3.5bpw	lynnea1517	2025-06-15T14:33:15Z	26	0	transformers	[ "transformers", "safetensors", "mixtral", "text-generation", "mergekit", "merge", "conversational", "arxiv:2403.19522", "base_model:alpindale/WizardLM-2-8x22B", "base_model:merge:alpindale/WizardLM-2-8x22B", "base_model:fireworks-ai/mixtral-8x22b-instruct-oh", "base_model:merge:fireworks-ai/mixtral-8x22b-instruct-oh", "base_model:migtissera/Tess-2.0-Mixtral-8x22B", "base_model:merge:migtissera/Tess-2.0-Mixtral-8x22B", "base_model:openbmb/Eurux-8x22b-nca", "base_model:merge:openbmb/Eurux-8x22b-nca", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "exl3", "region:us" ]	text-generation	2025-05-30T00:35:43Z	--- base_model: - openbmb/Eurux-8x22b-nca - alpindale/WizardLM-2-8x22B - fireworks-ai/mixtral-8x22b-instruct-oh - migtissera/Tess-2.0-Mixtral-8x22B library_name: transformers tags: - mergekit - merge --- # WizardLM-2-8x22B-Beige This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [alpindale/WizardLM-2-8x22B](https://huggingface.co/alpindale/WizardLM-2-8x22B) as a base. ### Models Merged The following models were included in the merge: * [openbmb/Eurux-8x22b-nca](https://huggingface.co/openbmb/Eurux-8x22b-nca) * [fireworks-ai/mixtral-8x22b-instruct-oh](https://huggingface.co/fireworks-ai/mixtral-8x22b-instruct-oh) * [migtissera/Tess-2.0-Mixtral-8x22B](https://huggingface.co/migtissera/Tess-2.0-Mixtral-8x22B) ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: alpindale/WizardLM-2-8x22B - model: openbmb/Eurux-8x22b-nca - model: migtissera/Tess-2.0-Mixtral-8x22B - model: fireworks-ai/mixtral-8x22b-instruct-oh base_model: alpindale/WizardLM-2-8x22B merge_method: model_stock dtype: bfloat16 ``` This model is an attempt to tone down the purple prose of WizardLM2-8X22B Here's an example: Prompt: ``` USER: A dead cat is placed into a box along with a nuclear isotope, a vial of poison and a radiation detector. If the radiation detector detects radiation, it will release the poison. The box is opened one day later. What is the probability of the cat being alive? Repeat the question before answering it. ``` WizardLM2-8X22B-Beige: ``` ASSISTANT: A dead cat is placed into a box along with a nuclear isotope, a vial of poison, and a radiation detector. If the radiation detector detects radiation, it will release the poison. The box is opened one day later. What is the probability of the cat being alive? The probability of the cat being alive is zero. Since the cat is dead when placed into the box, it will remain dead regardless of the radiation detector or the poison being released or not. ``` WizardLM2-8X22B: ``` The scenario you've described is a thought experiment that is often referred to as "Schrödinger's cat," a famous paradox in quantum mechanics. The experiment was devised by physicist Erwin Schrödinger in 1935. Repeating the question: If a dead cat is placed into a box along with a nuclear isotope, a vial of poison, and a radiation detector that will release the poison upon detecting radiation, what is the probability of the cat being alive when the box is opened one day later? In the original paradox, the cat is considered to be simultaneously alive and dead until the box is opened and the cat is observed. This is a way to illustrate the concept of superposition in quantum mechanics, where a quantum system is said to exist in all possible states simultaneously until it is measured. However, in the scenario you've described, the cat is explicitly stated to be dead when placed in the box. Therefore, regardless of the quantum state of the isotope or the function of the radiation detector and poison, the cat is not alive to begin with. The probability of the cat being alive when the box is opened is zero because it was dead at the outset. In the classic Schrödinger's cat thought experiment, if the cat were alive when placed in the box, quantum mechanics would suggest that there is a non-zero probability that the cat could be either alive or dead when the box is opened, depending on whether the isotope has decayed and triggered the release of the poison. But in your version, with the cat being definitively dead initially, there is no probability of it being alive later—it remains dead. ``` EXL2 quants by LoneStriker https://huggingface.co/models?search=LoneStriker+WizardLM-2-8x22B-Beige
MinaMila/gemma_2b_unlearned_2nd_5e-7_1.0_0.25_0.05_0.25_epoch2	MinaMila	2025-06-15T14:31:35Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T14:29:29Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
dllmpg/qlearning	dllmpg	2025-06-15T14:29:10Z	0	0	null	[ "CliffWalking-v0", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	reinforcement-learning	2025-06-15T14:29:00Z	--- tags: - CliffWalking-v0 - q-learning - reinforcement-learning - custom-implementation model-index: - name: qlearning results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: CliffWalking-v0 type: CliffWalking-v0 metrics: - type: mean_reward value: -13.00 +/- 0.00 name: mean_reward verified: false --- # Q-Learning Agent playing CliffWalking-v0 This is a trained model of a Q-Learning agent playing CliffWalking-v0. The agent was trained for 100000 episodes. ## Evaluation Results - Mean Reward: -13.00 +/- 0.00 ## Usage ```python import gymnasium as gym import pickle from huggingface_hub import hf_hub_download def load_from_hub(repo_id, filename): pickle_model = hf_hub_download(repo_id=repo_id, filename=filename) with open(pickle_model, 'rb') as f: downloaded_model_file = pickle.load(f) return downloaded_model_file model_data = load_from_hub(repo_id="dllmpg/qlearning", filename="q-learning.pkl") q_table = model_data["qtable"] env_id = model_data["env_id"] # Example of running the loaded agent env = gym.make(env_id) raw_state, info = env.reset() state_idx = raw_state # CliffWalking uses direct state indexing # ... run agent using greedy_policy(q_table, state_idx) ... ```
Lennard-Heuer/bert5-k-mental-health	Lennard-Heuer	2025-06-15T14:27:33Z	0	0	transformers	[ "transformers", "safetensors", "bert", "fill-mask", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2025-06-15T14:26:58Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
utkuden/qlora_paligemma_MIXft_decoder_only_rank16-SCST-CIDEr0.1159	utkuden	2025-06-15T14:25:44Z	0	0	transformers	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-15T14:25:34Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
MinaMila/gemma_2b_unlearned_2nd_5e-7_1.0_0.25_0.05_0.25_epoch1	MinaMila	2025-06-15T14:23:28Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T14:21:28Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
6DammK9/AstolfoXL	6DammK9	2025-06-15T14:20:00Z	0	3	diffusers	[ "diffusers", "tensorboard", "safetensors", "stable-diffusion", "stable-diffusion-diffusers", "text-to-image", "en", "license:creativeml-openrail-m", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]	text-to-image	2025-03-19T14:55:22Z	--- language: - en license: creativeml-openrail-m tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image - safetensors #- merge inference: true thumbnail: >- https://huggingface.co/6DammK9/AstolfoXL/resolve/main/250688-2206138433-1024-1024-4-64-20250524191940.jpg widget: - text: "1boy, astolfo" example_title: "astolfo" library_name: diffusers --- # AstolfoXL # - Base model: [AstolfoMix-XL](https://huggingface.co/6DammK9/AstolfoMix-XL), version [255c](https://huggingface.co/6DammK9/AstolfoMix-XL/blob/main/x255c-AstolfoMix-25022801-1458190.safetensors) - Tech report: [ch06](https://github.com/6DammK9/nai-anime-pure-negative-prompt/tree/main/ch06) - Dataset (images > latents): [danbooru2024](https://huggingface.co/datasets/6DammK9/danbooru2024-latents-sdxl-1ktar), [e621_2024](https://huggingface.co/datasets/6DammK9/e621_2024-latents-sdxl-1ktar) - Dataset (tags + captions): [meta_lat.json](https://huggingface.co/datasets/6DammK9/danbooru2024-latents-sdxl-1ktar/blob/main/meta_lat_v3.tar.gz) - 1 step = 16 images, 4x RTX 3090 24G. - 75-100+ days for 1EP. Train 1 EP only. Save per 10k steps. - Core concept: "Unsupervised learning". Expectation: MID ![250688-2206138433-1024-1024-4-64-20250524191940.jpg](https://huggingface.co/6DammK9/AstolfoXL/resolve/main/250688-2206138433-1024-1024-4-64-20250524191940.jpg) ``` parameters anthro, furry, astolfo Steps: 64, Sampler: Euler, Schedule type: Automatic, CFG scale: 4, Seed: 2206138433, Size: 1024x1024, Model hash: 792e768cd2, Model: 1ep-AstolfoXL, VAE hash: 235745af8d, VAE: sdxl-vae-fp16-fix.vae.safetensors, Clip skip: 2, SEG Active: True, SEG Blur Sigma: 11, SEG Start Step: 0, SEG End Step: 2048, PAG Active: True, PAG SANF: True, PAG Scale: 1, PAG Start Step: 0, PAG End Step: 2048, Version: v1.10.1 ```
LPX55/detection-model-3-ONNX	LPX55	2025-06-15T14:19:24Z	0	0	transformers.js	[ "transformers.js", "onnx", "swin", "image-classification", "base_model:Organika/sdxl-detector", "base_model:quantized:Organika/sdxl-detector", "region:us" ]	image-classification	2025-06-15T14:19:13Z	--- library_name: transformers.js base_model: - Organika/sdxl-detector --- # sdxl-detector (ONNX) This is an ONNX version of [Organika/sdxl-detector](https://huggingface.co/Organika/sdxl-detector). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
krissnonflux/asianULTRAREALISTIC_v10	krissnonflux	2025-06-15T14:18:54Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-15T12:59:58Z	--- license: apache-2.0 ---
kadasterdst/aardcode	kadasterdst	2025-06-15T14:17:58Z	101	0	transformers	[ "transformers", "safetensors", "gguf", "qwen3", "text-generation-inference", "unsloth", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-03T13:46:54Z	--- base_model: unsloth/qwen3-32b-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen3 license: apache-2.0 language: - en --- # Uploaded finetuned model - Developed by: kadasterdst - License: apache-2.0 - Finetuned from model : unsloth/qwen3-32b-bnb-4bit This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
Salmaalaa/CodeLlama-7b-Instruct_AR2SQL_v6	Salmaalaa	2025-06-15T14:14:15Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "trl", "sft", "base_model:codellama/CodeLlama-7b-Instruct-hf", "base_model:finetune:codellama/CodeLlama-7b-Instruct-hf", "endpoints_compatible", "region:us" ]	null	2025-06-15T04:10:42Z	--- base_model: codellama/CodeLlama-7b-Instruct-hf library_name: transformers model_name: CodeLlama-7b-Instruct_AR2SQL_v6 tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for CodeLlama-7b-Instruct_AR2SQL_v6 This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="Salmaalaa/CodeLlama-7b-Instruct_AR2SQL_v6", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with SFT. ### Framework versions - TRL: 0.18.1 - Transformers: 4.51.3 - Pytorch: 2.6.0+cu124 - Datasets: 3.6.0 - Tokenizers: 0.21.1 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
bruhzair/prototype-0.4x138	bruhzair	2025-06-15T14:12:10Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "arxiv:2403.19522", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T13:55:45Z	--- base_model: [] library_name: transformers tags: - mergekit - merge --- # prototype-0.4x138 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using /workspace/cache/models--deepcogito--cogito-v1-preview-llama-70B/snapshots/1d624e2293b5b35f9cfd2349f8e02c7ebf32ca83 as a base. ### Models Merged The following models were included in the merge: * /workspace/cache/models--Delta-Vector--Austral-70B-Preview/snapshots/bf62fe4ffd7e460dfa3bb881913bdfbd9dd14002 * /workspace/cache/models--SicariusSicariiStuff--Negative_LLAMA_70B/snapshots/097a11b4600eafe333a2be0309bbdf6be2f197c4 * /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-R1-70B-v1/snapshots/c88ee563196321458e6e46031231143c86394213 ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: /workspace/cache/models--TheDrummer--Fallen-Llama-3.3-R1-70B-v1/snapshots/c88ee563196321458e6e46031231143c86394213 - model: /workspace/cache/models--SicariusSicariiStuff--Negative_LLAMA_70B/snapshots/097a11b4600eafe333a2be0309bbdf6be2f197c4 - model: /workspace/cache/models--Delta-Vector--Austral-70B-Preview/snapshots/bf62fe4ffd7e460dfa3bb881913bdfbd9dd14002 base_model: /workspace/cache/models--deepcogito--cogito-v1-preview-llama-70B/snapshots/1d624e2293b5b35f9cfd2349f8e02c7ebf32ca83 merge_method: model_stock tokenizer: source: base int8_mask: true dtype: float32 out_dtype: bfloat16 ```
alicebochkareva/ngoncharova_style_LoRA	alicebochkareva	2025-06-15T14:11:03Z	0	0	diffusers	[ "diffusers", "text-to-image", "diffusers-training", "lora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]	text-to-image	2025-06-15T14:04:27Z	--- base_model: stabilityai/stable-diffusion-xl-base-1.0 library_name: diffusers license: openrail++ instance_prompt: photo collage in NGONCHAROVA style widget: [] tags: - text-to-image - diffusers-training - diffusers - lora - template:sd-lora - stable-diffusion-xl - stable-diffusion-xl-diffusers - text-to-image - text-to-image - diffusers-training - diffusers - lora - template:sd-lora - stable-diffusion-xl - stable-diffusion-xl-diffusers --- <!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # SDXL LoRA DreamBooth - alicebochkareva/ngoncharova_style_LoRA <Gallery /> ## Model description These are alicebochkareva/ngoncharova_style_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained using [DreamBooth](https://dreambooth.github.io/). LoRA for the text encoder was enabled: False. Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. ## Trigger words You should use photo collage in NGONCHAROVA style to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](alicebochkareva/ngoncharova_style_LoRA/tree/main) them in the Files & versions tab. ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]
Yuichi1218/Llama-3.1-Lafeak-8B	Yuichi1218	2025-06-15T14:10:53Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "en", "tet", "base_model:unsloth/Meta-Llama-3.1-8B", "base_model:finetune:unsloth/Meta-Llama-3.1-8B", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T14:01:14Z	--- base_model: unsloth/Meta-Llama-3.1-8B tags: - text-generation-inference - transformers - unsloth - llama - trl license: apache-2.0 language: - en - tet --- # Model Discription - Dataset; Lafeak Corpus におけるContinual Pre Training # Uploaded model - Developed by: Yuichi1218 - License: apache-2.0 - Finetuned from model : unsloth/Meta-Llama-3.1-8B This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
mikii17/syscode-unsloth-llama-3.3-70B-qlora-adapters	mikii17	2025-06-15T14:09:53Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:unsloth/Llama-3.3-70B-Instruct-bnb-4bit", "base_model:adapter:unsloth/Llama-3.3-70B-Instruct-bnb-4bit", "region:us" ]	null	2025-06-15T13:37:34Z	--- base_model: unsloth/Llama-3.3-70B-Instruct-bnb-4bit library_name: peft --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.15.2
mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-GGUF	mradermacher	2025-06-15T14:08:05Z	0	0	transformers	[ "transformers", "gguf", "en", "dataset:SuperbEmphasis/Deepseek-R1-ERP-Dataset", "base_model:SuperbEmphasis/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2", "base_model:quantized:SuperbEmphasis/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2", "endpoints_compatible", "region:us" ]	null	2025-06-15T12:32:48Z	--- base_model: SuperbEmphasis/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2 datasets: - SuperbEmphasis/Deepseek-R1-ERP-Dataset language: - en library_name: transformers quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/SuperbEmphasis/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2 <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-i1-GGUF ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.Q2_K.gguf) \| Q2_K \| 4.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.Q3_K_S.gguf) \| Q3_K_S \| 5.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.Q3_K_M.gguf) \| Q3_K_M \| 6.2 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.Q3_K_L.gguf) \| Q3_K_L \| 6.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.IQ4_XS.gguf) \| IQ4_XS \| 6.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.Q4_K_S.gguf) \| Q4_K_S \| 7.2 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.Q4_K_M.gguf) \| Q4_K_M \| 7.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.Q5_K_S.gguf) \| Q5_K_S \| 8.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.Q5_K_M.gguf) \| Q5_K_M \| 8.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.Q6_K.gguf) \| Q6_K \| 10.2 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2-GGUF/resolve/main/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2.Q8_0.gguf) \| Q8_0 \| 13.1 \| fast, best quality \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
MinaMila/gemma_2b_unlearned_2nd_5e-7_1.0_0.25_0.05_0.5_epoch1	MinaMila	2025-06-15T14:07:10Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T14:05:20Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
duchao1210/DPO_Qwen25_3B_128_0_5000kmap_lr	duchao1210	2025-06-15T14:06:38Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "text-generation-inference", "unsloth", "conversational", "en", "base_model:duchao1210/qwen_2.5_3B_5k_r128", "base_model:finetune:duchao1210/qwen_2.5_3B_5k_r128", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T14:04:40Z	--- base_model: duchao1210/qwen_2.5_3B_5k_r128 tags: - text-generation-inference - transformers - unsloth - qwen2 license: apache-2.0 language: - en --- # Uploaded finetuned model - Developed by: duchao1210 - License: apache-2.0 - Finetuned from model : duchao1210/qwen_2.5_3B_5k_r128 This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
mradermacher/s1.1_7b_QFD-GGUF	mradermacher	2025-06-15T14:05:48Z	0	0	transformers	[ "transformers", "gguf", "llama-factory", "full", "generated_from_trainer", "en", "base_model:lwl-uestc/QFFT-S1-7B", "base_model:quantized:lwl-uestc/QFFT-S1-7B", "license:other", "endpoints_compatible", "region:us", "conversational" ]	null	2025-04-20T17:15:38Z	--- base_model: lwl-uestc/QFFT-S1-7B language: - en library_name: transformers license: other quantized_by: mradermacher tags: - llama-factory - full - generated_from_trainer --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/lwl-uestc/QFFT-S1-7B <!-- provided-files --> 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. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/s1.1_7b_QFD-GGUF/resolve/main/s1.1_7b_QFD.Q2_K.gguf) \| Q2_K \| 3.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/s1.1_7b_QFD-GGUF/resolve/main/s1.1_7b_QFD.Q3_K_S.gguf) \| Q3_K_S \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/s1.1_7b_QFD-GGUF/resolve/main/s1.1_7b_QFD.Q3_K_M.gguf) \| Q3_K_M \| 3.9 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/s1.1_7b_QFD-GGUF/resolve/main/s1.1_7b_QFD.Q3_K_L.gguf) \| Q3_K_L \| 4.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/s1.1_7b_QFD-GGUF/resolve/main/s1.1_7b_QFD.IQ4_XS.gguf) \| IQ4_XS \| 4.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/s1.1_7b_QFD-GGUF/resolve/main/s1.1_7b_QFD.Q4_K_S.gguf) \| Q4_K_S \| 4.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/s1.1_7b_QFD-GGUF/resolve/main/s1.1_7b_QFD.Q4_K_M.gguf) \| Q4_K_M \| 4.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/s1.1_7b_QFD-GGUF/resolve/main/s1.1_7b_QFD.Q5_K_S.gguf) \| Q5_K_S \| 5.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/s1.1_7b_QFD-GGUF/resolve/main/s1.1_7b_QFD.Q5_K_M.gguf) \| Q5_K_M \| 5.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/s1.1_7b_QFD-GGUF/resolve/main/s1.1_7b_QFD.Q6_K.gguf) \| Q6_K \| 6.4 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/s1.1_7b_QFD-GGUF/resolve/main/s1.1_7b_QFD.Q8_0.gguf) \| Q8_0 \| 8.2 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/s1.1_7b_QFD-GGUF/resolve/main/s1.1_7b_QFD.f16.gguf) \| f16 \| 15.3 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
Sharing22/newgame_4	Sharing22	2025-06-15T14:01:35Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T13:58:56Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
mradermacher/015-qwen3-8b-v2-dpo405b-GGUF	mradermacher	2025-06-15T14:00:06Z	0	0	transformers	[ "transformers", "gguf", "en", "base_model:shisa-ai/015-qwen3-8b-v2-dpo405b", "base_model:quantized:shisa-ai/015-qwen3-8b-v2-dpo405b", "endpoints_compatible", "region:us" ]	null	2025-06-15T12:52:49Z	--- base_model: shisa-ai/015-qwen3-8b-v2-dpo405b language: - en library_name: transformers quantized_by: mradermacher --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> static quants of https://huggingface.co/shisa-ai/015-qwen3-8b-v2-dpo405b <!-- provided-files --> 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. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/015-qwen3-8b-v2-dpo405b-GGUF/resolve/main/015-qwen3-8b-v2-dpo405b.Q2_K.gguf) \| Q2_K \| 3.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/015-qwen3-8b-v2-dpo405b-GGUF/resolve/main/015-qwen3-8b-v2-dpo405b.Q3_K_S.gguf) \| Q3_K_S \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/015-qwen3-8b-v2-dpo405b-GGUF/resolve/main/015-qwen3-8b-v2-dpo405b.Q3_K_M.gguf) \| Q3_K_M \| 4.2 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/015-qwen3-8b-v2-dpo405b-GGUF/resolve/main/015-qwen3-8b-v2-dpo405b.Q3_K_L.gguf) \| Q3_K_L \| 4.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/015-qwen3-8b-v2-dpo405b-GGUF/resolve/main/015-qwen3-8b-v2-dpo405b.IQ4_XS.gguf) \| IQ4_XS \| 4.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/015-qwen3-8b-v2-dpo405b-GGUF/resolve/main/015-qwen3-8b-v2-dpo405b.Q4_K_S.gguf) \| Q4_K_S \| 4.9 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/015-qwen3-8b-v2-dpo405b-GGUF/resolve/main/015-qwen3-8b-v2-dpo405b.Q4_K_M.gguf) \| Q4_K_M \| 5.1 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/015-qwen3-8b-v2-dpo405b-GGUF/resolve/main/015-qwen3-8b-v2-dpo405b.Q5_K_S.gguf) \| Q5_K_S \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/015-qwen3-8b-v2-dpo405b-GGUF/resolve/main/015-qwen3-8b-v2-dpo405b.Q5_K_M.gguf) \| Q5_K_M \| 6.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/015-qwen3-8b-v2-dpo405b-GGUF/resolve/main/015-qwen3-8b-v2-dpo405b.Q6_K.gguf) \| Q6_K \| 6.8 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/015-qwen3-8b-v2-dpo405b-GGUF/resolve/main/015-qwen3-8b-v2-dpo405b.Q8_0.gguf) \| Q8_0 \| 8.8 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/015-qwen3-8b-v2-dpo405b-GGUF/resolve/main/015-qwen3-8b-v2-dpo405b.f16.gguf) \| f16 \| 16.5 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
MinaMila/gemma_2b_unlearned_2nd_5e-7_1.0_0.25_0.05_0.75_epoch2	MinaMila	2025-06-15T13:58:59Z	0	0	transformers	[ "transformers", "safetensors", "gemma2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-15T13:57:12Z	--- library_name: transformers tags: [] --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
Hadihilman/abinet	Hadihilman	2025-06-15T13:58:16Z	7	0	null	[ "gguf", "llama", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-15T11:45:42Z	--- license: apache-2.0 ---
brtenorio/SmolLM2-FT-LoRA-gsm8k	brtenorio	2025-06-15T13:55:05Z	414	0	transformers	[ "transformers", "tensorboard", "safetensors", "llama", "text-generation", "generated_from_trainer", "trl", "sft", "conversational", "base_model:HuggingFaceTB/SmolLM2-135M", "base_model:finetune:HuggingFaceTB/SmolLM2-135M", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-01T19:27:27Z	--- base_model: HuggingFaceTB/SmolLM2-135M library_name: transformers model_name: SmolLM2-FT-LoRA-gsm8k tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for SmolLM2-FT-LoRA-gsm8k This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python from transformers import pipeline question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" generator = pipeline("text-generation", model="brtenorio/SmolLM2-FT-LoRA-gsm8k", device="cuda") output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] print(output["generated_text"]) ``` ## Training procedure This model was trained with SFT. ### Framework versions - TRL: 0.18.1 - Transformers: 4.52.3 - Pytorch: 2.6.0+cu124 - Datasets: 3.6.0 - Tokenizers: 0.21.1 ## Citations Cite TRL as: ```bibtex @misc{vonwerra2022trl, title = {{TRL: Transformer Reinforcement Learning}}, author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```

Subsets and Splits