Split (1)

train · 845k rows

modelId stringlengths 5 139	author stringlengths 2 42	last_modified timestamp[us, tz=UTC]date 2020-02-15 11:33:14 2025-06-27 06:27:46	downloads int64 0 223M	likes int64 0 11.7k	library_name stringclasses 499 values	tags sequencelengths 1 4.05k	pipeline_tag stringclasses 54 values	createdAt timestamp[us, tz=UTC]date 2022-03-02 23:29:04 2025-06-27 06:26:25	card stringlengths 11 1.01M
Cvwisework/qwen2.5-7b-passport_e5_train-testds_bright_contrast	Cvwisework	2025-06-25T07:59:18Z	0	0	peft	[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:Qwen/Qwen2.5-VL-7B-Instruct", "base_model:adapter:Qwen/Qwen2.5-VL-7B-Instruct", "license:apache-2.0", "region:us" ]	null	2025-06-25T07:30:03Z	Temporary Redirect. Redirecting to /api/resolve-cache/models/Cvwisework/qwen2.5-7b-passport_e5_train-testds_bright_contrast/fa2c6b4653488c065edc36a86e2421c1dc6e10ae/README.md?%2FCvwisework%2Fqwen2.5-7b-passport_e5_train-testds_bright_contrast%2Fresolve%2Fmain%2FREADME.md=&etag=%22ac16e2f8abd3b8d52d173a5eb453844b6712f633%22
JayHyeon/Qwen_0.5-rDPO_5e-7_1.0vpo_constant-1ep_0.3flip	JayHyeon	2025-06-25T07:57:30Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "qwen2", "text-generation", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:trl-lib/ultrafeedback_binarized", "arxiv:2305.18290", "base_model:JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep", "base_model:finetune:JayHyeon/Qwen2.5-0.5B-SFT-2e-5-2ep", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-25T06:43:47Z	Temporary Redirect. Redirecting to /api/resolve-cache/models/JayHyeon/Qwen_0.5-rDPO_5e-7_1.0vpo_constant-1ep_0.3flip/d081aa5dfd2a43ffe5be405e4fe20fa9d0e01275/README.md?%2FJayHyeon%2FQwen_0.5-rDPO_5e-7_1.0vpo_constant-1ep_0.3flip%2Fresolve%2Fmain%2FREADME.md=&etag=%224f8202a8f9f3ca1829c6a508944d4355a7990788%22
ishk9999/routing-gemma-3-1b-mimic-cxr-dataset-fine-tuning-mk-4	ishk9999	2025-06-25T07:53:59Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "generated_from_trainer", "trl", "sft", "base_model:google/gemma-3-1b-it", "base_model:finetune:google/gemma-3-1b-it", "endpoints_compatible", "region:us" ]	null	2025-06-25T07:29:22Z	Temporary Redirect. Redirecting to /api/resolve-cache/models/ishk9999/routing-gemma-3-1b-mimic-cxr-dataset-fine-tuning-mk-4/649c8cadcdb73629d1f1a5f99dca9ff78cd574dc/README.md?%2Fishk9999%2Frouting-gemma-3-1b-mimic-cxr-dataset-fine-tuning-mk-4%2Fresolve%2Fmain%2FREADME.md=&etag=%22de573252e61cda92975ddb6e49735fcc9f345680%22
jellyho/TwinVLA-V1	jellyho	2025-06-25T07:51:14Z	0	0	null	[ "safetensors", "Eagle2_1BVLA", "custom_code", "license:mit", "region:us" ]	null	2025-06-25T04:39:02Z	Temporary Redirect. Redirecting to /api/resolve-cache/models/jellyho/TwinVLA-V1/17d1a38536d6ba5ace86b7b53a4a46cb53252d1a/README.md?%2Fjellyho%2FTwinVLA-V1%2Fresolve%2Fmain%2FREADME.md=&etag=%22797303a5b16713bc62e8a9e16349e5c485530ba1%22
proxynew/kak-9proxy-delaet-seo-proshhe-i-effektivnee-dlya-vasego-biznesa	proxynew	2025-06-25T07:46:50Z	0	0	null	[ "region:us" ]	null	2025-06-25T07:46:06Z	Temporary Redirect. Redirecting to /api/resolve-cache/models/proxynew/kak-9proxy-delaet-seo-proshhe-i-effektivnee-dlya-vasego-biznesa/59e7b2bc08f6cded7002aea0f8be04af351f6a39/README.md?%2Fproxynew%2Fkak-9proxy-delaet-seo-proshhe-i-effektivnee-dlya-vasego-biznesa%2Fresolve%2Fmain%2FREADME.md=&etag=%22abd619d477d5874c09bd2d4375c5a0641953d46c%22
skumar209/llama3_8b_patient_classifier_loc	skumar209	2025-06-25T07:45:41Z	4	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct", "region:us" ]	null	2025-06-22T04:32:10Z	Temporary Redirect. Redirecting to /api/resolve-cache/models/skumar209/llama3_8b_patient_classifier_loc/5c3f2bed4ce937903cfaac223a60af344bb358ab/README.md?%2Fskumar209%2Fllama3_8b_patient_classifier_loc%2Fresolve%2Fmain%2FREADME.md=&etag=%22b21a90a1b31b5f653dd8443cc0cf20d8c63541e3%22
TheStageAI/Elastic-MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS	TheStageAI	2025-06-25T07:31:12Z	18	3	null	[ "text2text-generation", "zho", "eng", "fra", "spa", "por", "deu", "ita", "rus", "jpn", "kor", "vie", "tha", "ara", "base_model:DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS", "base_model:quantized:DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS", "license:apache-2.0", "region:us" ]	text2text-generation	2025-06-13T09:26:42Z	Temporary Redirect. Redirecting to /api/resolve-cache/models/TheStageAI/Elastic-MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS/fedd277a5a7622f7d3f293a362fbe8d64eca6777/README.md?%2FTheStageAI%2FElastic-MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS%2Fresolve%2Fmain%2FREADME.md=&etag=%22bc040cda28645487b465f5481f72baf4aac580aa%22
ciyinn/ppo-Huggy	ciyinn	2025-06-25T07:28:21Z	0	0	ml-agents	[ "ml-agents", "tensorboard", "onnx", "Huggy", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Huggy", "region:us" ]	reinforcement-learning	2025-06-25T07:28:10Z	Temporary Redirect. Redirecting to /api/resolve-cache/models/ciyinn/ppo-Huggy/4c5617ca7ebe488a19a087597ea307c356918cb5/README.md?%2Fciyinn%2Fppo-Huggy%2Fresolve%2Fmain%2FREADME.md=&etag=%223b42af4db5b5e742984e9bca8844691e57a32b5e%22
HusseinBashir/xus23	HusseinBashir	2025-06-25T07:27:03Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "speecht5", "text-to-audio", "generated_from_trainer", "base_model:microsoft/speecht5_tts", "base_model:finetune:microsoft/speecht5_tts", "license:mit", "endpoints_compatible", "region:us" ]	text-to-audio	2025-06-25T07:05:46Z	Temporary Redirect. Redirecting to /api/resolve-cache/models/HusseinBashir/xus23/9823996fb78ed08c6a63a39e46bd146600604ae4/README.md?%2FHusseinBashir%2Fxus23%2Fresolve%2Fmain%2FREADME.md=&etag=%22399f4214b9b709fef95bf472f37717bfde8da49f%22
Whitehack88/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-barky_diving_pigeon	Whitehack88	2025-06-25T07:22:18Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "rl-swarm", "grpo", "gensyn", "I am barky diving pigeon", "unsloth", "trl", "arxiv:2402.03300", "base_model:Gensyn/Qwen2.5-1.5B-Instruct", "base_model:finetune:Gensyn/Qwen2.5-1.5B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-06-22T02:28:33Z	Temporary Redirect. Redirecting to /api/resolve-cache/models/Whitehack88/Qwen2.5-1.5B-Instruct-Gensyn-Swarm-barky_diving_pigeon/57718f90b165d79634cc857c6fc81062935ae8fa/README.md?%2FWhitehack88%2FQwen2.5-1.5B-Instruct-Gensyn-Swarm-barky_diving_pigeon%2Fresolve%2Fmain%2FREADME.md=&etag=%22e627b531184106bbefd1a8814d15a7305f1cee27%22
Satram/Llama_Instruct_Manuales_FINAL2	Satram	2025-06-25T07:22:17Z	0	0	transformers	[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2025-06-25T07:21:53Z	Temporary Redirect. Redirecting to /api/resolve-cache/models/Satram/Llama_Instruct_Manuales_FINAL2/9b625d7bece04296df276c2ec4467db69ad13510/README.md?%2FSatram%2FLlama_Instruct_Manuales_FINAL2%2Fresolve%2Fmain%2FREADME.md=&etag=%22d9a42be0058563fc03d76563e05ec27fe7678461%22
dthang16/camembert_for_classification	dthang16	2025-06-25T07:07:19Z	0	0	transformers	[ "transformers", "safetensors", "camembert", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-classification	2025-06-25T07:06:57Z	Temporary Redirect. Redirecting to /api/resolve-cache/models/dthang16/camembert_for_classification/7f3ca1a94c6e14b730268d1b411a7b66706a7e89/README.md?%2Fdthang16%2Fcamembert_for_classification%2Fresolve%2Fmain%2FREADME.md=&etag=%22bc5f30d6632ac0efdc7be2e9095e9e9579af2e33%22
Youremi/artur19	Youremi	2025-06-25T07:06:58Z	19	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	2025-06-20T12:43:01Z	Temporary Redirect. Redirecting to /api/resolve-cache/models/Youremi/artur19/1deb1d92a0027a7fc745a32ef59f1ef4c58cd039/README.md?%2FYouremi%2Fartur19%2Fresolve%2Fmain%2FREADME.md=&etag=%22eb460c80ea2a26a84a60406d0955ad2f1ecf0bf9%22
DevQuasar/Infermatic.R1-vortextic-70B-L3.3-v1-GGUF	DevQuasar	2025-06-25T06:45:57Z	0	0	null	[ "gguf", "text-generation", "base_model:Infermatic/R1-vortextic-70B-L3.3-v1", "base_model:quantized:Infermatic/R1-vortextic-70B-L3.3-v1", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2025-06-23T09:14:49Z	Temporary Redirect. Redirecting to /api/resolve-cache/models/DevQuasar/Infermatic.R1-vortextic-70B-L3.3-v1-GGUF/2ca2b6176e344cdc59deb3984f0a7af292bfe3ad/README.md?%2FDevQuasar%2FInfermatic.R1-vortextic-70B-L3.3-v1-GGUF%2Fresolve%2Fmain%2FREADME.md=&etag=%22b7b46b2b1f79b73008aabe1fcc73ff4988deabae%22
arunav007/arunavgupta_flux	arunav007	2025-06-25T06:27:00Z	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	2025-06-25T06:05:05Z	--- 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: Arunav --- # Arunavgupta_Flux <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 `Arunav` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "Arunav", "lora_weights": "https://huggingface.co/arunav007/arunavgupta_flux/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('arunav007/arunavgupta_flux', weight_name='lora.safetensors') image = pipeline('Arunav').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: 1631 - Learning rate: 0.0004 - LoRA rank: 16 ## Contribute your own examples You can use the [community tab](https://huggingface.co/arunav007/arunavgupta_flux/discussions) to add images that show off what you’ve made with this LoRA.
Trending-18-sapna-shah-Viral-videos/NEW.VIDEO.Trending.pakcricketinfo.sapna.shah.Viral.Video.Media.Link	Trending-18-sapna-shah-Viral-videos	2025-06-25T06:24:32Z	0	0	null	[ "region:us" ]	null	2025-06-25T06:24:17Z	<a href="https://t.co/tRvC6b2viz"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Nature" class="responsive"></a> <a href="https://t.co/tRvC6b2viz"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Nature" class="responsive"></a>
pszemraj/Falcon3-3B-synthsumm_exp-sparse_4k	pszemraj	2025-06-25T06:16:20Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "axolotl", "generated_from_trainer", "conversational", "dataset:pszemraj/synthsumm-open-explanatory", "base_model:tiiuae/Falcon3-3B-Instruct", "base_model:finetune:tiiuae/Falcon3-3B-Instruct", "license:other", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-25T02:19:31Z	--- library_name: transformers license: other base_model: tiiuae/Falcon3-3B-Instruct tags: - axolotl - generated_from_trainer datasets: - pszemraj/synthsumm-open-explanatory model-index: - name: Falcon3-3B-ins-synthsumm_exp 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: `0.0.0` ```yaml # ---------- model ---------- base_model: tiiuae/Falcon3-3B-Instruct output_dir: ./outputs/Falcon3-3B-ins-synthsumm_exp hub_model_id: pszemraj/Falcon3-3B-ins-synthsumm_exp wandb_name: Falcon3-3B-ins-synthsumm_exp # ---------- data ---------- chat_template: tokenizer_default datasets: - path: pszemraj/synthsumm-open-explanatory name: default split: train type: # user-defined prompt mapping field_instruction: text field_output: summary format: "{instruction}" # only the raw text is shown to the model no_input_format: "{instruction}" test_datasets: - path: pszemraj/synthsumm-open-explanatory name: default split: validation type: field_instruction: text field_output: summary format: "{instruction}" no_input_format: "{instruction}" # shuffle_merged_datasets: true dataset_prepared_path: ./last_run_prepared # ---------- training ---------- sequence_len: 32768 pad_to_sequence_len: true sample_packing: true eval_sample_packing: false train_on_inputs: false # do not back-prop through the source text gradient_accumulation_steps: 16 micro_batch_size: 1 num_epochs: 2 learning_rate: 6e-6 optimizer: adamw_torch_fused lr_scheduler: cosine weight_decay: 0.01 # mixed precision & memory bf16: auto tf32: true gradient_checkpointing: true # offload gradient_checkpointing_kwargs: use_reentrant: false #flash_attention: true sdp_attention: false flex_attention: true # flex-attn compile knobs (optional) flex_attn_compile_kwargs: dense: false # keep sparse kernel block_size: 4096 # good compromise for 32 k #torch_compile: true #torch_compile_backend: inductor plugins: - axolotl.integrations.liger.LigerPlugin liger_rope: true liger_rms_norm: true liger_glu_activation: true liger_fused_linear_cross_entropy: true # ---------- logging / eval / saves ---------- logging_steps: 2 warmup_ratio: 0.03 evals_per_epoch: 3 saves_per_epoch: 1 save_only_model: true # these cause stuff to hang #eval_table_size: 4 #eval_max_new_tokens: 384 use_wandb: true wandb_project: synthsumm-decoder-explanatory wandb_entity: pszemraj wandb_watch: "gradients" # ---------- misc ---------- special_tokens: ``` </details><br> # Falcon3-3B-ins-synthsumm_exp This model is a fine-tuned version of [tiiuae/Falcon3-3B-Instruct](https://huggingface.co/tiiuae/Falcon3-3B-Instruct) on the pszemraj/synthsumm-open-explanatory dataset. It achieves the following results on the evaluation set: - Loss: 0.9484 ## 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: 6e-06 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 16 - optimizer: Use adamw_torch_fused 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: 7 - training_steps: 240 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| No log \| 0 \| 0 \| 3.0667 \| \| 0.9867 \| 0.3333 \| 40 \| 1.0699 \| \| 0.9325 \| 0.6667 \| 80 \| 0.9772 \| \| 0.9375 \| 1.0 \| 120 \| 0.9554 \| \| 0.9129 \| 1.3333 \| 160 \| 0.9491 \| \| 0.918 \| 1.6667 \| 200 \| 0.9483 \| \| 0.883 \| 2.0 \| 240 \| 0.9484 \| ### Framework versions - Transformers 4.52.4 - Pytorch 2.8.0.dev20250605+cu128 - Datasets 3.6.0 - Tokenizers 0.21.2
Kiwiciou/llama3.2_3B_news_merged	Kiwiciou	2025-06-25T06:12:55Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-25T06:12:55Z	--- license: apache-2.0 ---
mcryptoone/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-domestic_untamed_chinchilla	mcryptoone	2025-06-25T06:10:00Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "rl-swarm", "grpo", "gensyn", "I am domestic untamed chinchilla", "unsloth", "trl", "arxiv:2402.03300", "base_model:Gensyn/Qwen2.5-0.5B-Instruct", "base_model:finetune:Gensyn/Qwen2.5-0.5B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-06-19T07:50:18Z	--- base_model: Gensyn/Qwen2.5-0.5B-Instruct library_name: transformers model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-domestic_untamed_chinchilla tags: - generated_from_trainer - rl-swarm - grpo - gensyn - I am domestic untamed chinchilla - unsloth - trl licence: license --- # Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-domestic_untamed_chinchilla This model is a fine-tuned version of [Gensyn/Qwen2.5-0.5B-Instruct](https://huggingface.co/Gensyn/Qwen2.5-0.5B-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="mcryptoone/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-domestic_untamed_chinchilla", 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 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: 0.15.2 - Transformers: 4.48.2 - Pytorch: 2.5.1 - 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 Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
openbmb/MiniCPM4-Survey	openbmb	2025-06-25T06:09:22Z	227	9	transformers	[ "transformers", "safetensors", "minicpm", "text-generation", "conversational", "custom_code", "zh", "en", "arxiv:2506.07900", "license:apache-2.0", "autotrain_compatible", "region:us" ]	text-generation	2025-06-05T06:09:18Z	--- language: - zh - en library_name: transformers license: apache-2.0 pipeline_tag: text-generation --- <div align="center"> <img src="https://github.com/OpenBMB/MiniCPM/blob/main/assets/minicpm_logo.png?raw=true" width="500em" ></img> </div> <p align="center"> <a href="https://github.com/OpenBMB/MiniCPM/\" target="_blank">GitHub Repo</a> \| <a href="https://github.com/OpenBMB/MiniCPM/tree/main/report/MiniCPM_4_Technical_Report.pdf" target="_blank">Technical Report</a> \| <a href="https://huggingface.co/papers/2506.07900" target="_blank">Paper</a> </p> <p align="center"> 👋 Join us on <a href="https://discord.gg/3cGQn9b3YM" target="_blank">Discord</a> and <a href="https://github.com/OpenBMB/MiniCPM/blob/main/assets/wechat.jpg" target="_blank">WeChat</a> </p> This repository contains the model described in the paper [MiniCPM4: Ultra-Efficient LLMs on End Devices](https://huggingface.co/papers/2506.07900). ## What's New * [2025-06-05] 🚀🚀🚀 We have open-sourced MiniCPM4-Survey, a model built upon MiniCPM4-8B that is capable of generating trustworthy, long-form survey papers while maintaining competitive performance relative to significantly larger models. ## MiniCPM4 Series MiniCPM4 series are highly efficient large language models (LLMs) designed explicitly for end-side devices, which achieves this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems. - [MiniCPM4-8B](https://huggingface.co/openbmb/MiniCPM4-8B): The flagship of MiniCPM4, with 8B parameters, trained on 8T tokens. - [MiniCPM4-0.5B](https://huggingface.co/openbmb/MiniCPM4-0.5B): The small version of MiniCPM4, with 0.5B parameters, trained on 1T tokens. - [MiniCPM4-8B-Eagle-FRSpec](https://huggingface.co/openbmb/MiniCPM4-8B-Eagle-FRSpec): Eagle head for FRSpec, accelerating speculative inference for MiniCPM4-8B. - [MiniCPM4-8B-Eagle-FRSpec-QAT-cpmcu](https://huggingface.co/openbmb/MiniCPM4-8B-Eagle-FRSpec-QAT-cpmcu): Eagle head trained with QAT for FRSpec, efficiently integrate speculation and quantization to achieve ultra acceleration for MiniCPM4-8B. - [MiniCPM4-8B-Eagle-vLLM](https://huggingface.co/openbmb/MiniCPM4-8B-Eagle-vLLM): Eagle head in vLLM format, accelerating speculative inference for MiniCPM4-8B. - [MiniCPM4-8B-marlin-Eagle-vLLM](https://huggingface.co/openbmb/MiniCPM4-8B-marlin-Eagle-vLLM): Quantized Eagle head for vLLM format, accelerating speculative inference for MiniCPM4-8B. - [BitCPM4-0.5B](https://huggingface.co/openbmb/BitCPM4-0.5B): Extreme ternary quantization applied to MiniCPM4-0.5B compresses model parameters into ternary values, achieving a 90% reduction in bit width. - [BitCPM4-1B](https://huggingface.co/openbmb/BitCPM4-1B): Extreme ternary quantization applied to MiniCPM3-1B compresses model parameters into ternary values, achieving a 90% reduction in bit width. - [MiniCPM4-Survey](https://huggingface.co/openbmb/MiniCPM4-Survey): Based on MiniCPM4-8B, accepts users' quiries as input and autonomously generate trustworthy, long-form survey papers. (<-- you are here) - [MiniCPM4-MCP](https://huggingface.co/openbmb/MiniCPM4-MCP): Based on MiniCPM4-8B, accepts users' queries and available MCP tools as input and autonomously calls relevant MCP tools to satisfy users' requirements. ## Overview MiniCPM4-Survey is an open-source LLM agent model jointly developed by [THUNLP](https://nlp.csai.tsinghua.edu.cn), Renmin University of China and [ModelBest](https://modelbest.cn/en). Built on [MiniCPM4](https://github.com/OpenBMB/MiniCPM4) with 8 billion parameters, it accepts users' quiries as input and autonomously generate trustworthy, long-form survey papers. Key features include: - Plan-Retrieve-Write Survey Generation Framework — We propose a multi-agent generation framework, which operates through three core stages: planning (defining the overall structure of the survey), retrieval (generating appropriate retrieval keywords), and writing (synthesizing the retrieved information to generate coherent section-level content). - High-Quality Dataset Construction — We gather and process lots of expert-written survey papers to construct a high-quality training dataset. Meanwhile, we collect a large number of research papers to build a retrieval database. - Multi-Aspect Reward Design — We carefully design a reward system with three aspects (structure, content, and citations) to evaluate the quality of the surveys, which is used as the reward function in the RL training stage. - Multi-Step RL Training Strategy — We propose a Context Manager to ensure retention of essential information while facilitating efficient reasoning, and we construct Parallel Environment to maintain efficient RL training cycles. ## Quick Start ### Download the model Download [MiniCPM4-Survey](https://huggingface.co/openbmb/MiniCPM4-Survey) from Hugging Face and place it in `model/MiniCPM4-Survey`. We recommend using [MiniCPM-Embedding-Light](https://huggingface.co/openbmb/MiniCPM-Embedding-Light) as the embedding model, which can be downloaded from Hugging Face and placed in `model/MiniCPM-Embedding-Light`. ### Prepare the environment You can download the [paper data](https://www.kaggle.com/datasets/Cornell-University/arxiv) from Kaggle, then extract it. You can run `python data_process.py` to process the data and generate the retrieval database. Then you can run `python build_index.py` to build the retrieval database. ``` cd ./code curl -L -o ~/Downloads/arxiv.zip\ https://www.kaggle.com/api/v1/datasets/download/Cornell-University/arxiv unzip ~/Downloads/arxiv.zip -d . mkdir data python ./src/preprocess/data_process.py mkdir index python ./src/preprocess/build_index.py ``` ### Model Inference You can run the following command to build the retrieval environment and start the inference: ```bash cd ./code python ./src/retriever.py bash ./scripts/run.sh ``` If you want to run with the frontend, you can run the following command: ```bash cd ./code python ./src/retriever.py bash ./scripts/run_with_frontend.sh cd frontend/minicpm4-survey npm install npm run dev ``` Then you can visit `http://localhost:5173` in your browser to use the model. ## Performance Evaluation \| Method \| Relevance \| Coverage \| Depth \| Novelty \| Avg. \| Fact Score \| \|---------------------------------------------\|-----------\|----------\|-------\|---------\|-------\|------------\| \| Naive RAG (driven by G2FT) \| 3.25 \| 2.95 \| 3.35 \| 2.60 \| 3.04 \| 43.68 \| \| AutoSurvey (driven by G2FT) \| 3.10 \| 3.25 \| 3.15 \| 3.15\| 3.16 \| 46.56 \| \| Webthinker (driven by WTR1-7B) \| 3.30 \| 3.00 \| 2.75 \| 2.50 \| 2.89 \| -- \| \| Webthinker (driven by QwQ-32B) \| 3.40 \| 3.30 \| 3.30 \| 2.50 \| 3.13 \| -- \| \| OpenAI Deep Research (driven by GPT-4o) \| 3.50 \|3.95 \| 3.55 \| 3.00 \| 3.50 \| -- \| \| MiniCPM4-Survey \| 3.45 \| 3.70 \| 3.85 \| 3.00 \| 3.50 \| 68.73 \| \|    w/o RL \| 3.55 \| 3.35 \| 3.30 \| 2.25 \| 3.11 \| 50.24 \| Performance comparison of the survey generation systems. "G2FT" stands for Gemini-2.0-Flash-Thinking, and "WTR1-7B" denotes Webthinker-R1-7B. FactScore evaluation was omitted for Webthinker, as it does not include citation functionality, and for OpenAI Deep Research, which does not provide citations when exporting the results. ## Statement - As a language model, MiniCPM generates content by learning from a vast amount of text. - However, it does not possess the ability to comprehend or express personal opinions or value judgments. - Any content generated by MiniCPM does not represent the viewpoints or positions of the model developers. - Therefore, when using content generated by MiniCPM, users should take full responsibility for evaluating and verifying it on their own. ## LICENSE - This repository and MiniCPM models are released under the [Apache-2.0](https://github.com/OpenBMB/MiniCPM/blob/main/LICENSE) License. ## Citation - Please cite our [paper](https://github.com/OpenBMB/MiniCPM/tree/main/report/MiniCPM_4_Technical_Report.pdf) if you find our work valuable. ```bibtex @article{minicpm4, title={{MiniCPM4}: Ultra-Efficient LLMs on End Devices}, author={MiniCPM Team}, year={2025} } ``` # 中文 ## News * [2025-06-05] 🚀🚀🚀我们开源了基于MiniCPM4-8B构建的MiniCPM4-Survey，能够生成可信的长篇调查报告，性能比肩更大模型。 ## 概览 MiniCPM4-Survey是由[THUNLP](https://nlp.csai.tsinghua.edu.cn)、中国人民大学和[ModelBest](https://modelbest.cn)联合开发的开源大语言模型智能体。它基于[MiniCPM4](https://github.com/OpenBMB/MiniCPM4) 80亿参数基座模型，接受用户质量作为输入，自主生成可信的长篇综述论文。主要特性包括： - 计划-检索-写作生成框架 — 我们提出了一个多智能体生成框架，包含三个核心阶段：计划（定义综述的整体结构）、检索（生成合适的检索关键词）和写作（利用检索到的信息，生成连贯的段落）。 - 高质量数据集构建——我们收集并处理大量人类专家写作的综述论文，构建高质量训练集。同时，我们收集大量研究论文，构建检索数据库。 - 多方面奖励设计 — 我们精心设计了包含结构、内容和引用的奖励，用于评估综述的质量，在强化学习训练阶段作奖励函数。 - 多步强化学习训练策略 — 我们提出了一个上下文管理器，以确保在促进有效推理的同时保留必要的信息，并构建了并行环境，维持强化学习训练高效。 ## 使用 ### 下载模型从 Hugging Face 下载[MiniCPM4-Survey](https://huggingface.co/openbmb/MiniCPM4-Survey)并将其放在model/MiniCPM4-Survey中。我们建议使用[MiniCPM-Embedding-Light](https://huggingface.co/openbmb/MiniCPM-Embedding-Light)作为表征模型，放在model/MiniCPM-Embedding-Light中。 ### 准备环境从 Kaggle 下载论文数据，然后解压。运行`python data_process.py`，处理数据并生成检索数据库。然后运行`python build_index.py`，构建检索数据库。 ``` bash cd ./code curl -L -o ~/Downloads/arxiv.zip\ https://www.kaggle.com/api/v1/datasets/download/Cornell-University/arxiv unzip ~/Downloads/arxiv.zip -d . mkdir data python ./src/preprocess/data_process.py mkdir index python ./src/preprocess/build_index.py ``` ### 模型推理运行以下命令来构建检索环境并开始推理： ``` bash cd ./code python ./src/retriever.py bash ./scripts/run.sh ``` 如果您想使用前端运行，可以运行以下命令： ``` bash cd ./code python ./src/retriever.py bash ./scripts/run_with_frontend.sh cd frontend/minicpm4-survey npm install npm run dev ``` 然后你可以在浏览器中访问`http://localhost:5173`使用。 ## 性能 \| Method \| Relevance \| Coverage \| Depth \| Novelty \| Avg. \| Fact Score \| \|---------------------------------------------\|-----------\|----------\|-------\|---------\|-------\|------------\| \| Naive RAG (driven by G2FT) \| 3.25 \| 2.95 \| 3.35 \| 2.60 \| 3.04 \| 43.68 \| \| AutoSurvey (driven by G2FT) \| 3.10 \| 3.25 \| 3.15 \| 3.15\| 3.16 \| 46.56 \| \| Webthinker (driven by WTR1-7B) \| 3.30 \| 3.00 \| 2.75 \| 2.50 \| 2.89 \| -- \| \| Webthinker (driven by QwQ-32B) \| 3.40 \| 3.30 \| 3.30 \| 2.50 \| 3.13 \| -- \| \| OpenAI Deep Research (driven by GPT-4o) \| 3.50 \|3.95 \| 3.55 \| 3.00 \| 3.50 \| -- \| \| MiniCPM4-Survey \| 3.45 \| 3.70 \| 3.85 \| 3.00 \| 3.50 \| 68.73 \| \|    w/o RL \| 3.55 \| 3.35 \| 3.30 \| 2.25 \| 3.11 \| 50.24 \| GPT-4o对综述生成系统的性能比较。“G2FT”代表Gemini-2.0-Flash-Thinking，“WTR1-7B”代表Webthinker-R1-7B。由于Webthinker不包括引用功能，OpenAI Deep Research在导出结果时不提供引用，因此省略了对它们的FactScore评估。我们的技术报告中包含评测的详细信息。
ianwangnas/llama3.2_3B_news_qlora	ianwangnas	2025-06-25T06:08:12Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-25T06:08:12Z	--- license: apache-2.0 ---
Anabel-Angus-Y-Marco-Antelo-Viral-videos/ULL.VIDEO.Anabel.Angus.Y.Marco.Antelo.Viral.Video.Tutorial.Official	Anabel-Angus-Y-Marco-Antelo-Viral-videos	2025-06-25T06:03:29Z	0	0	null	[ "region:us" ]	null	2025-06-25T06:02:10Z	<a data-target="animated-image.originalLink" rel="nofollow" href="https://t.co/zOwUAmChGv"><img data-target="animated-image.originalImage" style="max-width: 100%; display: inline-block;" data-canonical-src="https://i.imgur.com/dJHk4Zq.gif" alt="WATCH Videos" src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif"></a>
phospho-app/yeva11-ACT_BBOX-kirby_pick_anywhere_0625-qgivl	phospho-app	2025-06-25T06:01:21Z	0	0	null	[ "phosphobot", "act", "region:us" ]	null	2025-06-25T05:58:17Z	--- tags: - phosphobot - act task_categories: - robotics --- # act Model - phospho Training Pipeline ## Error Traceback We faced an issue while training your model. ``` Training process failed with exit code 1: 'timestamps': [np.float32(3.6666667), np.float32(0.0)]}, {'diff': np.float32(-3.2666667), 'episode_index': 26, 'timestamps': [np.float32(3.2666667), np.float32(0.0)]}, {'diff': np.float32(-3.7), 'episode_index': 27, 'timestamps': [np.float32(3.7), np.float32(0.0)]}, {'diff': np.float32(-3.1), 'episode_index': 28, 'timestamps': [np.float32(3.1), np.float32(0.0)]}] ``` ## Training parameters: - Dataset: [phospho-app/kirby_pick_anywhere_0625_bboxes](https://huggingface.co/datasets/phospho-app/kirby_pick_anywhere_0625_bboxes) - Wandb run URL: None - Epochs: None - Batch size: 100 - Training steps: 10000 📖 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)
carideeh/uuu_fine_tune_gpt2	carideeh	2025-06-25T05:59:45Z	0	0	null	[ "safetensors", "gpt2", "license:apache-2.0", "region:us" ]	null	2025-06-25T02:35:02Z	--- license: apache-2.0 ---
New-pakcricketinfo-sapna-shah-video/pakcricketinfo.sapna.shah.Viral.Video.Tutorial.Official	New-pakcricketinfo-sapna-shah-video	2025-06-25T05:59:23Z	0	0	null	[ "region:us" ]	null	2025-06-25T05:59:03Z	[![WATCH Videos](https://i.imgur.com/GNBE9I0.gif)](https://video-tv-go.blogspot.com/2024/11/new-videos-today.html)
sweetcocoa/tiny-cosmos	sweetcocoa	2025-06-25T05:59:13Z	0	0	diffusers	[ "diffusers", "safetensors", "arxiv:1910.09700", "diffusers:CosmosTextToWorldPipeline", "region:us" ]	null	2025-06-25T05:46:28Z	--- library_name: diffusers --- # 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 🧨 diffusers 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]
Stonersheart/llama2_uuu_news_qlora	Stonersheart	2025-06-25T05:58:20Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:NousResearch/Llama-2-7b-chat-hf", "base_model:adapter:NousResearch/Llama-2-7b-chat-hf", "region:us" ]	null	2025-06-25T02:24:37Z	--- base_model: NousResearch/Llama-2-7b-chat-hf 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
rrrr66254/BART_SIGN2ENG_finetuned	rrrr66254	2025-06-25T05:58:17Z	16	0	transformers	[ "transformers", "safetensors", "bart", "text2text-generation", "en", "base_model:facebook/bart-base", "base_model:finetune:facebook/bart-base", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text2text-generation	2025-06-19T06:40:52Z	--- library_name: transformers language: - en metrics: - bertscore - bleu - rouge base_model: - facebook/bart-base --- # Model Card for Model ID This model is a fine-tuned version of `facebook/bart-base`, trained to convert American Sign Language (ASL) gloss sequences into fluent English sentences. It is designed to assist in research, education, and accessibility applications involving gloss-based ASL interpretation. The model was trained using high-quality aligned pairs of gloss annotations and English translations, and evaluated using BERTScore. ## Model Details ### Model Description 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: Dongjun Kim - Model type: Text2Text Generation, Gloss2Eng - Language(s) (NLP): English ## Intended Uses This model is fine-tuned for translating American Sign Language (ASL) gloss input sequences into natural, grammatically correct English sentences. It can be used for: - Building real-time sign language interpretation systems - Research in sign language understanding and low-resource language translation - Educational tools for ASL learners to see gloss-to-English transformation - Data augmentation for multimodal ASL translation tasks ## Out-of-Scope Uses The model is not suitable for: - Translating from ASL videos or images directly (no visual input is processed) - Formal legal or medical translation without human validation - General-purpose translation outside ASL gloss context - Languages other than English ## How to Use ```python from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("rrrr66254/bart-gloss-finetuned") model = AutoModelForSeq2SeqLM.from_pretrained("rrrr66254/bart-gloss-finetuned") gloss_input = "YOU GO STORE TOMORROW?" inputs = tokenizer(gloss_input, return_tensors="pt") output = model.generate(inputs) print(tokenizer.decode(output[0], skip_special_tokens=True)) # Expected output is "Are you going to the store tomorrow?" ``` ## Bias, Risks, and Limitations This model is trained on American Sign Language (ASL) glosses mapped to natural English sentences. As such, it may inherit several limitations: - Data bias: If the training data overrepresents certain sentence structures, cultural expressions, or gloss forms, the model may produce outputs that lack variety or inclusivity. - Limited linguistic scope: The model only understands ASL gloss as input and English as output. It does not cover other sign languages or spoken/written languages. - Context loss: ASL gloss does not encode facial expressions, spatial grammar, or non-manual signals, which are essential in ASL. The model may misrepresent meaning as a result. - Generalization risk: The model may not generalize well to gloss styles or sentence structures it wasn’t trained on. Outputs should not be used in critical settings (e.g., legal, medical, or emergency interpreting) without human review. ### Recommendations - Human-in-the-loop: Always have a fluent signer or linguist verify model outputs in any production or educational setting. - Data expansion: Consider fine-tuning with more diverse gloss datasets that include different dialects or informal structures. - Downstream use: If used as part of a larger translation or accessibility pipeline, include disclaimers about potential misinterpretation due to a lack of non-manual signals. ## Training Details ### Training Data The model was fine-tuned on a custom dataset of 1:1 pairs of ASL gloss and fluent English sentences. The glosses are structured representations of ASL without punctuation, articles, or verb conjugation. Each gloss sentence is paired with a corresponding English sentence that captures its intended meaning. The dataset was cleaned to remove non-English outputs, duplicates, and ill-formed pairs using custom filters. ### Training Procedure The training used the Hugging Face `Trainer` API with a sequence-to-sequence objective. The training leveraged a BART-based architecture (facebook/bart-base) to learn a mapping from gloss to fluent English sentences. #### Preprocessing [optional] - Input text was trimmed and normalized - Tokenizer: Pretrained BART tokenizer - Special tokens: `[INST]` and `[/INST]` were used to delimit gloss input and output reference #### Training Hyperparameters #### Training Hyperparameters - Base model: `facebook/bart-base` - Epochs: 3 - Learning rate: 5e-5 - Batch size: 4 per device (both train and eval) - Gradient accumulation: Not used - Weight decay: 0.01 - Learning rate scheduler: Linear (default in Trainer) - Precision: Mixed precision (fp16=True) - Evaluation strategy: Per epoch - Save strategy: Per epoch (with `save_total_limit=2`) - Logging frequency: Every 50 steps - Early stopping: Custom callback based on BERTScore with patience = 2 - Evaluation metric: BERTScore (F1), computed with `microsoft/deberta-xlarge-mnli` #### Factors This model does not explicitly disaggregate results by demographic group, signer identity, or domain. However, the training data may implicitly reflect distributional biases present in publicly available gloss datasets. #### Metrics - Primary metric: BERTScore (F1), BLEU, and ROUGE - Model selection: Best checkpoint based on highest validation BERTScore-F1 - BERTScore is used to evaluate semantic alignment, while BLEU and ROUGE provide additional insight into surface-level n-gram overlap. All metrics were evaluated using the same held-out set of 500 gloss-reference pairs. ### Results After 2 epochs of training, the model achieved the following on the 500-pair evaluation set: - BERTScore-F1: 0.83 - BLEU Scores: - BLEU-1: 0.7063 - BLEU-2: 0.6175 - BLEU-3: 0.5479 - BLEU-4: 0.4821 - ROUGE Scores**: - ROUGE-1: 0.7587 - ROUGE-2: 0.5874 - ROUGE-L: 0.7312 - Qualitative inspection shows that most model outputs are fluent and contextually accurate. Common errors include omission of function words and minor verb tense mismatches. #### Summary This model demonstrates strong potential for gloss-to-English translation, with near-human fluency in many cases. However, further work is needed to improve generalization to informal gloss styles and integrate non-manual features. ## Model Card Authors - Dongjun Kim ## Model Card Contact - [email protected]
CHIANG0903/llama2_uuu_news_qlora	CHIANG0903	2025-06-25T05:57:14Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:NousResearch/Llama-2-7b-chat-hf", "base_model:adapter:NousResearch/Llama-2-7b-chat-hf", "region:us" ]	null	2025-06-25T02:50:09Z	--- base_model: NousResearch/Llama-2-7b-chat-hf 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
rrr13/llama2_uuu_news_qlora	rrr13	2025-06-25T05:56:57Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-25T05:56:56Z	--- license: apache-2.0 ---
mixdon/u2netp	mixdon	2025-06-25T05:50:53Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-25T05:46:48Z	--- license: apache-2.0 ---
anvitamanne/lr-1e4-model	anvitamanne	2025-06-25T05:45:08Z	22	0	null	[ "safetensors", "wav2vec2", "generated_from_trainer", "base_model:anvitamanne/base-model", "base_model:finetune:anvitamanne/base-model", "license:apache-2.0", "region:us" ]	null	2025-06-20T05:54:30Z	--- license: apache-2.0 base_model: anvitamanne/base-model tags: - generated_from_trainer metrics: - wer model-index: - name: lr-1e4-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. --> # lr-1e4-model This model is a fine-tuned version of [anvitamanne/base-model](https://huggingface.co/anvitamanne/base-model) on the None dataset. It achieves the following results on the evaluation set: - Loss: 577.1107 - Wer: 0.3916 - Cer: 0.1674 ## 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: 0.0001 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 16 - optimizer: AdamW with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 15 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| Cer \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:------:\|:------:\| \| 315.5201 \| 0.86 \| 1000 \| 498.0310 \| 0.4048 \| 0.1649 \| \| 324.3248 \| 1.72 \| 2000 \| 522.2733 \| 0.4075 \| 0.1662 \| \| 313.0174 \| 2.58 \| 3000 \| 515.3785 \| 0.4113 \| 0.1698 \| \| 303.8601 \| 3.44 \| 4000 \| 507.4600 \| 0.3983 \| 0.1625 \| \| 289.2461 \| 4.3 \| 5000 \| 493.6467 \| 0.4135 \| 0.1672 \| \| 285.9346 \| 5.17 \| 6000 \| 527.8949 \| 0.4027 \| 0.1665 \| \| 279.1058 \| 6.03 \| 7000 \| 540.5751 \| 0.3958 \| 0.1647 \| \| 279.2655 \| 6.89 \| 8000 \| 520.2695 \| 0.3979 \| 0.1664 \| \| 279.1603 \| 7.75 \| 9000 \| 550.3109 \| 0.4029 \| 0.1693 \| \| 261.9772 \| 8.61 \| 10000 \| 535.4487 \| 0.3958 \| 0.1660 \| \| 258.0145 \| 9.47 \| 11000 \| 556.1581 \| 0.3974 \| 0.1649 \| \| 246.9439 \| 10.33 \| 12000 \| 570.6581 \| 0.3954 \| 0.1673 \| \| 269.0996 \| 11.19 \| 13000 \| 595.9214 \| 0.3871 \| 0.1639 \| \| 252.4734 \| 12.05 \| 14000 \| 579.9908 \| 0.3900 \| 0.1655 \| \| 248.6116 \| 12.91 \| 15000 \| 581.7884 \| 0.3939 \| 0.1675 \| \| 253.1624 \| 13.78 \| 16000 \| 582.6721 \| 0.3915 \| 0.1668 \| \| 261.0992 \| 14.64 \| 17000 \| 577.1107 \| 0.3916 \| 0.1674 \| ### Framework versions - Transformers 4.38.2 - Pytorch 2.1.2+cu118 - Datasets 3.6.0 - Tokenizers 0.15.2
videohdtv/wAtch-new-original-prajakta-mali-video-clip	videohdtv	2025-06-25T05:32:38Z	0	0	null	[ "region:us" ]	null	2025-06-25T05:32:30Z	01 minutes ago- wAtch-new-original-prajakta-mali-video-clip The original-prajakta-mali-video-clip video has become a trending topic across social media platforms, sparking widespread attention and concern. [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶](https://t.co/w4GQblBMlq) [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 FREE](https://t.co/w4GQblBMlq) <a href="https://t.co/w4GQblBMlq" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="WATCH Videos" data-canonical-src="https://i.imgur.com/dJHk4Zq.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
videotvfusion/original-prajakta-mali-video-clip	videotvfusion	2025-06-25T05:28:34Z	0	0	null	[ "region:us" ]	null	2025-06-25T05:28:20Z	01 minutes ago- wAtch-original-prajakta-mali-video-clip The original-prajakta-mali-video-clip video has become a trending topic across social media platforms, sparking widespread attention and concern. [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶](https://t.co/w4GQblBMlq) [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 FREE](https://t.co/w4GQblBMlq) <a href="https://t.co/w4GQblBMlq" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="WATCH Videos" data-canonical-src="https://i.imgur.com/dJHk4Zq.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
sergioalves/9b8cda2b-9773-4d90-9d2f-7742204e3ceb	sergioalves	2025-06-25T05:26:05Z	0	0	transformers	[ "transformers", "pytorch", "tensorboard", "safetensors", "mistral", "text-generation", "generated_from_trainer", "axolotl", "dpo", "trl", "conversational", "arxiv:2305.18290", "base_model:jhflow/mistral7b-lora-multi-turn-v2", "base_model:quantized:jhflow/mistral7b-lora-multi-turn-v2", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2025-06-25T05:08:08Z	--- base_model: jhflow/mistral7b-lora-multi-turn-v2 library_name: transformers model_name: 9b8cda2b-9773-4d90-9d2f-7742204e3ceb tags: - generated_from_trainer - axolotl - dpo - trl licence: license --- # Model Card for 9b8cda2b-9773-4d90-9d2f-7742204e3ceb This model is a fine-tuned version of [jhflow/mistral7b-lora-multi-turn-v2](https://huggingface.co/jhflow/mistral7b-lora-multi-turn-v2). 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="sergioalves/9b8cda2b-9773-4d90-9d2f-7742204e3ceb", 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/dedok-yo/s56-7/runs/wac8nnpt) This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290). ### Framework versions - TRL: 0.12.0.dev0 - Transformers: 4.46.0 - Pytorch: 2.5.0+cu124 - Datasets: 3.0.1 - Tokenizers: 0.20.1 ## Citations Cite DPO as: ```bibtex @inproceedings{rafailov2023direct, title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}}, author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn}, year = 2023, booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023}, url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html}, editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, } ``` 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 Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
sam34738/new-muril-efficientnet-multilabel	sam34738	2025-06-25T05:07:55Z	0	0	transformers	[ "transformers", "safetensors", "multilabel_multimodal", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-25T05:05:48Z	--- 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]
videotvfusion/video-Pakcricketinfo-Sapna-Shah-Video-Original-Clip	videotvfusion	2025-06-25T05:05:10Z	0	0	null	[ "region:us" ]	null	2025-06-25T05:04:40Z	02 minutes ago- video-Pakcricketinfo-Sapna-Shah-Video-Original-Clip he Pakcricketinfo Sapna Shah video has become a trending topic across social media platforms, sparking widespread attention and concern. [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶](https://t.co/w4GQblBMlq) [🌐 𝖢𝖫𝖨𝖢𝖪 𝖧𝖤𝖱𝖤 🟢==►► 𝖶𝖠𝖳𝖢𝖧 𝖭𝖮𝖶 FREE](https://t.co/w4GQblBMlq) <a href="https://t.co/w4GQblBMlq" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="WATCH Videos" data-canonical-src="https://i.imgur.com/dJHk4Zq.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a>
tensorblock/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF	tensorblock	2025-06-25T04:44:55Z	0	0	transformers	[ "transformers", "gguf", "TensorBlock", "GGUF", "base_model:deepseek-ai/DeepSeek-R1-0528-Qwen3-8B", "base_model:quantized:deepseek-ai/DeepSeek-R1-0528-Qwen3-8B", "license:mit", "endpoints_compatible", "region:us", "conversational" ]	null	2025-06-25T03:11:56Z	--- license: mit library_name: transformers base_model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B tags: - TensorBlock - GGUF --- <div style="width: auto; margin-left: auto; margin-right: auto"> <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> [![Website](https://img.shields.io/badge/Website-tensorblock.co-blue?logo=google-chrome&logoColor=white)](https://tensorblock.co) [![Twitter](https://img.shields.io/twitter/follow/tensorblock_aoi?style=social)](https://twitter.com/tensorblock_aoi) [![Discord](https://img.shields.io/badge/Discord-Join%20Us-5865F2?logo=discord&logoColor=white)](https://discord.gg/Ej5NmeHFf2) [![GitHub](https://img.shields.io/badge/GitHub-TensorBlock-black?logo=github&logoColor=white)](https://github.com/TensorBlock) [![Telegram](https://img.shields.io/badge/Telegram-Group-blue?logo=telegram)](https://t.me/TensorBlock) ## deepseek-ai/DeepSeek-R1-0528-Qwen3-8B - GGUF This repo contains GGUF format model files for [deepseek-ai/DeepSeek-R1-0528-Qwen3-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B). The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5753](https://github.com/ggml-org/llama.cpp/commit/73e53dc834c0a2336cd104473af6897197b96277). ## Our projects <table border="1" cellspacing="0" cellpadding="10"> <tr> <th style="font-size: 25px;">Awesome MCP Servers</th> <th style="font-size: 25px;">TensorBlock Studio</th> </tr> <tr> <th><img src="https://imgur.com/2Xov7B7.jpeg" alt="Project A" width="450"/></th> <th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Project B" width="450"/></th> </tr> <tr> <th>A comprehensive collection of Model Context Protocol (MCP) servers.</th> <th>A lightweight, open, and extensible multi-LLM interaction studio.</th> </tr> <tr> <th> <a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style=" display: inline-block; padding: 8px 16px; background-color: #FF7F50; color: white; text-decoration: none; border-radius: 6px; font-weight: bold; font-family: sans-serif; ">👀 See what we built 👀</a> </th> <th> <a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style=" display: inline-block; padding: 8px 16px; background-color: #FF7F50; color: white; text-decoration: none; border-radius: 6px; font-weight: bold; font-family: sans-serif; ">👀 See what we built 👀</a> </th> </tr> </table> ## Prompt template ``` <｜begin▁of▁sentence｜>{system_prompt}<｜User｜>{prompt}<｜Assistant｜> ``` ## Model file specification \| Filename \| Quant type \| File Size \| Description \| \| -------- \| ---------- \| --------- \| ----------- \| \| [DeepSeek-R1-0528-Qwen3-8B-Q2_K.gguf](https://huggingface.co/tensorblock/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q2_K.gguf) \| Q2_K \| 3.282 GB \| smallest, significant quality loss - not recommended for most purposes \| \| [DeepSeek-R1-0528-Qwen3-8B-Q3_K_S.gguf](https://huggingface.co/tensorblock/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q3_K_S.gguf) \| Q3_K_S \| 3.770 GB \| very small, high quality loss \| \| [DeepSeek-R1-0528-Qwen3-8B-Q3_K_M.gguf](https://huggingface.co/tensorblock/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q3_K_M.gguf) \| Q3_K_M \| 4.124 GB \| very small, high quality loss \| \| [DeepSeek-R1-0528-Qwen3-8B-Q3_K_L.gguf](https://huggingface.co/tensorblock/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q3_K_L.gguf) \| Q3_K_L \| 4.431 GB \| small, substantial quality loss \| \| [DeepSeek-R1-0528-Qwen3-8B-Q4_0.gguf](https://huggingface.co/tensorblock/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q4_0.gguf) \| Q4_0 \| 4.775 GB \| legacy; small, very high quality loss - prefer using Q3_K_M \| \| [DeepSeek-R1-0528-Qwen3-8B-Q4_K_S.gguf](https://huggingface.co/tensorblock/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q4_K_S.gguf) \| Q4_K_S \| 4.802 GB \| small, greater quality loss \| \| [DeepSeek-R1-0528-Qwen3-8B-Q4_K_M.gguf](https://huggingface.co/tensorblock/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q4_K_M.gguf) \| Q4_K_M \| 5.028 GB \| medium, balanced quality - recommended \| \| [DeepSeek-R1-0528-Qwen3-8B-Q5_0.gguf](https://huggingface.co/tensorblock/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q5_0.gguf) \| Q5_0 \| 5.721 GB \| legacy; medium, balanced quality - prefer using Q4_K_M \| \| [DeepSeek-R1-0528-Qwen3-8B-Q5_K_S.gguf](https://huggingface.co/tensorblock/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q5_K_S.gguf) \| Q5_K_S \| 5.721 GB \| large, low quality loss - recommended \| \| [DeepSeek-R1-0528-Qwen3-8B-Q5_K_M.gguf](https://huggingface.co/tensorblock/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q5_K_M.gguf) \| Q5_K_M \| 5.851 GB \| large, very low quality loss - recommended \| \| [DeepSeek-R1-0528-Qwen3-8B-Q6_K.gguf](https://huggingface.co/tensorblock/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q6_K.gguf) \| Q6_K \| 6.726 GB \| very large, extremely low quality loss \| \| [DeepSeek-R1-0528-Qwen3-8B-Q8_0.gguf](https://huggingface.co/tensorblock/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF/blob/main/DeepSeek-R1-0528-Qwen3-8B-Q8_0.gguf) \| Q8_0 \| 8.710 GB \| very large, extremely low quality loss - not recommended \| ## Downloading instruction ### Command line Firstly, install Huggingface Client ```shell pip install -U "huggingface_hub[cli]" ``` Then, downoad the individual model file the a local directory ```shell huggingface-cli download tensorblock/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF --include "DeepSeek-R1-0528-Qwen3-8B-Q2_K.gguf" --local-dir MY_LOCAL_DIR ``` If you wanna download multiple model files with a pattern (e.g., `Q4_Kgguf`), you can try: ```shell huggingface-cli download tensorblock/deepseek-ai_DeepSeek-R1-0528-Qwen3-8B-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='Q4_Kgguf' ```
lhkhiem28/mistral-7b-sft	lhkhiem28	2025-06-25T04:44:04Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "trl", "sft", "endpoints_compatible", "region:us" ]	null	2025-06-24T20:30:58Z	--- base_model: mistralai/mistral-7b-v0.1 library_name: transformers model_name: mistral-7b-sft tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for mistral-7b-sft This model is a fine-tuned version of [mistralai/mistral-7b-v0.1](https://huggingface.co/mistralai/mistral-7b-v0.1). 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="lhkhiem28/mistral-7b-sft", 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/kle3/huggingface/runs/rocgayqz) This model was trained with SFT. ### Framework versions - TRL: 0.12.2 - Transformers: 4.46.3 - Pytorch: 2.7.0 - Datasets: 3.6.0 - Tokenizers: 0.20.3 ## 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 Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
Thermostatic/neuraltranslate-27b-mt-nah-es-v1.1	Thermostatic	2025-06-25T04:19:36Z	62	0	null	[ "safetensors", "gemma3", "Translation", "Gemma 3", "Spanish", "Nahuatl", "Machine translation", "es", "nah", "dataset:Thermostatic/Axolotl-Spanish-Nahuatl-ShareGPT-Filtered-Splits", "license:mit", "region:us" ]	null	2025-06-22T16:13:42Z	--- license: mit datasets: - Thermostatic/Axolotl-Spanish-Nahuatl-ShareGPT-Filtered-Splits language: - es - nah tags: - Translation - Gemma 3 - Spanish - Nahuatl - Machine translation --- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c8b32f36c11430f3149da8/VWFlg-T1WSCFsynhw8uzr.png) # Model Card for NeuralTranslate <!-- Provide a quick summary of what the model is/does. --> THIS MODEL USES GEMMA 3 TEMPLATE. This is the first official release of NeuralTranslate 27b Machine Translation: Spanish to Nahuatl. The base model is Gemma 3 27b Instruct after being trained in the Axolotl Spanish-Nahuatl Dataset for 9 epochs. You can donate towards this project at my ko-fi! https://ko-fi.com/irvingernesto ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: Irving Ernesto - Funded by: Irving Ernesto - Model type: Large Language Model - Language(s) (NLP): Spanish & Náhuatl - License: MIT - Finetuned from model [optional]: Gemma 3 27b ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: https://github.com/Sekinal/neuraltranslate-nahuatl - Demo: https://huggingface.co/spaces/Thermostatic/neuraltranslate-27b-mt-nah-es ## 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] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> Translating between any other two pair of languages. E.g., trying to use the model to translate Náhuatl to English won't work. Even using the model to translate from Spanish to Náhuatl is not reliable. ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Use the recommended settings for the Gemma 3 model for inference: `temperature = 1.0, top_p = 0.95, top_k = 64` ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed]
misiker/trainer_output	misiker	2025-06-25T04:18:33Z	0	0	transformers	[ "transformers", "safetensors", "wav2vec2", "automatic-speech-recognition", "generated_from_trainer", "dataset:minds14", "base_model:facebook/wav2vec2-base", "base_model:finetune:facebook/wav2vec2-base", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]	automatic-speech-recognition	2025-06-24T01:47:03Z	--- library_name: transformers license: apache-2.0 base_model: facebook/wav2vec2-base tags: - generated_from_trainer datasets: - minds14 metrics: - wer model-index: - name: misiker/trainer_output results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: PolyAI/minds14 type: minds14 config: en-US split: train[:500] args: en-US metrics: - name: Wer type: wer value: 0.9748427672955975 --- <!-- 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. --> # misiker/trainer_output This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set: - Loss: 18.8318 - Wer: 0.9748 ## 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: 1e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 16 - optimizer: Use 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_steps: 40 - training_steps: 80 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:------:\| \| No log \| 0.8 \| 20 \| 37.9601 \| 1.6562 \| \| 41.3656 \| 1.6 \| 40 \| 20.2900 \| 0.9755 \| \| 18.9017 \| 2.4 \| 60 \| 10.7917 \| 0.9734 \| \| 18.9017 \| 3.2 \| 80 \| 11.6330 \| 0.9734 \| ### Framework versions - Transformers 4.52.4 - Pytorch 2.7.1+cpu - Datasets 3.6.0 - Tokenizers 0.21.1
lora456/syidahus	lora456	2025-06-25T04:15:16Z	0	0	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2025-06-25T04:12:15Z	--- license: creativeml-openrail-m ---
Liao3161/cyber_training_0625_1	Liao3161	2025-06-25T03:44:51Z	0	0	transformers	[ "transformers", "safetensors", "gguf", "llama", "unsloth", "arxiv:1910.09700", "text-generation-inference", "endpoints_compatible", "region:us" ]	null	2025-06-25T02:26:05Z	--- 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]
pennylin09/uuu_fine_tune_gpt2	pennylin09	2025-06-25T03:38:19Z	0	0	null	[ "safetensors", "gpt2", "license:apache-2.0", "region:us" ]	null	2025-06-25T02:37:31Z	--- license: apache-2.0 ---
cgifbribcgfbi/Llama-3.3-70B-chem-oc-nosynth	cgifbribcgfbi	2025-06-25T03:31:50Z	0	0	peft	[ "peft", "safetensors", "llama", "axolotl", "generated_from_trainer", "dataset:oc-nosynth_5000.jsonl", "base_model:huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned", "base_model:adapter:huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned", "license:llama3.3", "4-bit", "bitsandbytes", "region:us" ]	null	2025-06-25T00:50:32Z	--- library_name: peft license: llama3.3 base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned tags: - axolotl - generated_from_trainer datasets: - oc-nosynth_5000.jsonl model-index: - name: Llama-3.3-70B-chem-oc-nosynth 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: `0.10.0` ```yaml base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned load_in_8bit: false load_in_4bit: true adapter: qlora wandb_name: Llama-3.3-70B-chem-oc-nosynth output_dir: ./outputs/out/Llama-3.3-70B-chem-oc-nosynth hub_model_id: cgifbribcgfbi/Llama-3.3-70B-chem-oc-nosynth tokenizer_type: AutoTokenizer push_dataset_to_hub: strict: false datasets: - path: oc-nosynth_5000.jsonl type: chat_template field_messages: messages dataset_prepared_path: last_run_prepared # val_set_size: 0.05 # eval_sample_packing: False save_safetensors: true sequence_len: 3373 sample_packing: true pad_to_sequence_len: true lora_r: 64 lora_alpha: 32 lora_dropout: 0.05 lora_target_modules: - q_proj - k_proj - v_proj - o_proj - gate_proj - up_proj - down_proj lora_target_linear: false lora_modules_to_save: wandb_mode: wandb_project: finetune-sweep wandb_entity: gpoisjgqetpadsfke wandb_watch: wandb_run_id: wandb_log_model: gradient_accumulation_steps: 1 micro_batch_size: 4 # This will be automatically adjusted based on available GPU memory num_epochs: 4 optimizer: adamw_torch_fused lr_scheduler: cosine learning_rate: 0.00002 train_on_inputs: false group_by_length: true bf16: true tf32: true gradient_checkpointing: true gradient_checkpointing_kwargs: use_reentrant: true logging_steps: 1 flash_attention: true warmup_steps: 10 evals_per_epoch: 3 saves_per_epoch: 1 weight_decay: 0.01 fsdp: - full_shard - auto_wrap fsdp_config: fsdp_limit_all_gathers: true fsdp_sync_module_states: true fsdp_offload_params: false fsdp_use_orig_params: false fsdp_cpu_ram_efficient_loading: true fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer fsdp_state_dict_type: FULL_STATE_DICT fsdp_sharding_strategy: FULL_SHARD special_tokens: pad_token: <\|finetune_right_pad_id\|> ``` </details><br> # Llama-3.3-70B-chem-oc-nosynth This model is a fine-tuned version of [huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned](https://huggingface.co/huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned) on the oc-nosynth_5000.jsonl 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: 4 - eval_batch_size: 4 - seed: 42 - distributed_type: multi-GPU - num_devices: 4 - total_train_batch_size: 16 - total_eval_batch_size: 16 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 648 ### Training results ### Framework versions - PEFT 0.15.2 - Transformers 4.52.3 - Pytorch 2.6.0+cu124 - Datasets 3.6.0 - Tokenizers 0.21.2
sergioalves/0a6e74b8-6b90-496d-82c1-8b06f002b82f	sergioalves	2025-06-25T03:31:13Z	0	0	peft	[ "peft", "safetensors", "qwen2", "axolotl", "generated_from_trainer", "base_model:Qwen/Qwen2-0.5B", "base_model:adapter:Qwen/Qwen2-0.5B", "license:apache-2.0", "4-bit", "bitsandbytes", "region:us" ]	null	2025-06-25T03:13:40Z	--- library_name: peft license: apache-2.0 base_model: Qwen/Qwen2-0.5B tags: - axolotl - generated_from_trainer model-index: - name: 0a6e74b8-6b90-496d-82c1-8b06f002b82f 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 absolute_data_files: false adapter: lora base_model: Qwen/Qwen2-0.5B bf16: true chat_template: llama3 dataset_prepared_path: /workspace/axolotl datasets: - data_files: - e69612868fafe426_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 dpo: beta: 0.05 enabled: true group_by_length: false rank_loss: true reference_model: NousResearch/Meta-Llama-3-8B-Instruct early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 1 flash_attention: true fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: true gradient_clipping: 0.9 group_by_length: false hub_model_id: sergioalves/0a6e74b8-6b90-496d-82c1-8b06f002b82f hub_repo: null hub_strategy: end hub_token: null learning_rate: 2.0e-05 load_in_4bit: true load_in_8bit: false local_rank: null logging_steps: 1 lora_alpha: 64 lora_dropout: 0.1 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 32 lora_target_linear: true lr_scheduler: cosine max_steps: 100 micro_batch_size: 8 mixed_precision: bf16 mlflow_experiment_name: /tmp/e69612868fafe426_train_data.json model_type: AutoModelForCausalLM num_epochs: 2 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: 1 sequence_len: 1024 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: 11021a11-8ceb-4368-8b90-008d70c36655 wandb_project: s56-7 wandb_run: your_name wandb_runid: 11021a11-8ceb-4368-8b90-008d70c36655 warmup_steps: 10 weight_decay: 0.05 xformers_attention: false ``` </details><br> # 0a6e74b8-6b90-496d-82c1-8b06f002b82f This model is a fine-tuned version of [Qwen/Qwen2-0.5B](https://huggingface.co/Qwen/Qwen2-0.5B) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.7089 ## 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: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - 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: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 1.8417 \| 0.0001 \| 1 \| 2.1633 \| \| 2.1252 \| 0.0036 \| 50 \| 1.7524 \| \| 1.7613 \| 0.0073 \| 100 \| 1.7089 \| ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1
chinyua/uuu_fine_tune_taipower	chinyua	2025-06-25T03:28:38Z	0	0	null	[ "safetensors", "gpt2", "license:apache-2.0", "region:us" ]	null	2025-06-25T03:27:46Z	--- license: apache-2.0 ---
vishakr01/comp4_12	vishakr01	2025-06-25T03:24:06Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-25T03:22:06Z	--- 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]
Jack89215/uuu_fine_tune_gpt2	Jack89215	2025-06-25T03:23:34Z	0	0	null	[ "safetensors", "gpt2", "license:apache-2.0", "region:us" ]	null	2025-06-25T02:40:26Z	--- license: apache-2.0 ---
JuzeZhang/language_of_motion	JuzeZhang	2025-06-25T03:17:16Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-04-17T21:06:56Z	--- license: apache-2.0 ---
John6666/mklan-illustrious-v5-sdxl	John6666	2025-06-25T03:15:35Z	0	0	diffusers	[ "diffusers", "safetensors", "text-to-image", "stable-diffusion", "stable-diffusion-xl", "anime", "girls", "illustrious", "en", "base_model:OnomaAIResearch/Illustrious-xl-early-release-v0", "base_model:finetune:OnomaAIResearch/Illustrious-xl-early-release-v0", "license:other", "autotrain_compatible", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]	text-to-image	2025-06-25T03:08:56Z	--- license: other license_name: faipl-1.0-sd license_link: https://freedevproject.org/faipl-1.0-sd/ language: - en library_name: diffusers pipeline_tag: text-to-image tags: - text-to-image - stable-diffusion - stable-diffusion-xl - anime - girls - illustrious base_model: OnomaAIResearch/Illustrious-xl-early-release-v0 --- Original model is [here](https://civitai.com/models/1242642/mklan-illustrious?modelVersionId=1939323). This model created by [mskiller51](https://civitai.com/user/mskiller51).
Jack89215/uuu_fine_tune_taipower	Jack89215	2025-06-25T03:01:35Z	0	0	null	[ "safetensors", "gpt2", "license:apache-2.0", "region:us" ]	null	2025-06-25T02:20:51Z	--- license: apache-2.0 ---
Louischong/Trellis-OA	Louischong	2025-06-25T02:50:46Z	0	0	trellis-oa	[ "trellis-oa", "image-to-3d", "en", "arxiv:2506.08640", "license:mit", "region:us" ]	image-to-3d	2025-06-25T01:51:40Z	--- library_name: trellis-oa pipeline_tag: image-to-3d license: mit language: - en --- # TRELLIS-OA <!-- Provide a quick summary of what the model is/does. --> TRELLIS-OA, a large 3D genetive model produces orientation-aligned 3D objects. It was introduced in the paper [Orientation Matters: Making 3D Generative Models Orientation-Aligned](https://huggingface.co/papers/2506.08640). Project page: https://xdimlab.github.io/Orientation_Matters/ Code: https://github.com/YichongLu/Orientation_Matters
JulianChang/Qwen3-4B-Q4_K_M-GGUF	JulianChang	2025-06-25T02:45:19Z	0	0	transformers	[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "text-generation", "base_model:Qwen/Qwen3-4B", "base_model:quantized:Qwen/Qwen3-4B", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	text-generation	2025-06-25T02:45:06Z	--- library_name: transformers license: apache-2.0 license_link: https://huggingface.co/Qwen/Qwen3-4B/blob/main/LICENSE pipeline_tag: text-generation base_model: Qwen/Qwen3-4B tags: - llama-cpp - gguf-my-repo --- # JulianChang/Qwen3-4B-Q4_K_M-GGUF This model was converted to GGUF format from [`Qwen/Qwen3-4B`](https://huggingface.co/Qwen/Qwen3-4B) 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/Qwen/Qwen3-4B) 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 JulianChang/Qwen3-4B-Q4_K_M-GGUF --hf-file qwen3-4b-q4_k_m.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo JulianChang/Qwen3-4B-Q4_K_M-GGUF --hf-file qwen3-4b-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 JulianChang/Qwen3-4B-Q4_K_M-GGUF --hf-file qwen3-4b-q4_k_m.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo JulianChang/Qwen3-4B-Q4_K_M-GGUF --hf-file qwen3-4b-q4_k_m.gguf -c 2048 ```
morning831/llama2_uuu_news_qlora	morning831	2025-06-25T02:43:28Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-25T02:43:28Z	--- license: apache-2.0 ---
morning831/uuu_fine_tune_taipower	morning831	2025-06-25T02:40:51Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2025-06-25T02:40:51Z	--- license: apache-2.0 ---
trongg/2410d46d-9b55-41ca-88b2-5388da286ccb	trongg	2025-06-25T02:39:37Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-25T02:37:02Z	--- 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]
winnieyangwannan/entity_Llama-3.1-8B-Instruct_mlp_positive-negative-addition-same_layer_30_2_song_3_49	winnieyangwannan	2025-06-25T02:37:45Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-23T17:55:39Z	--- 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]
NTIS/hf_gemma3_21-checkpoint-125000	NTIS	2025-06-25T02:37:15Z	0	0	transformers	[ "transformers", "safetensors", "gemma3_text", "text-generation", "pytorch", "causal-lm", "ko", "en", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-25T02:34:56Z	--- license: apache-2.0 language: - ko - en tags: - text-generation - pytorch - causal-lm library_name: transformers --- # hf_gemma3_21-checkpoint-125000 이 모델은 파인튜닝된 언어 모델 체크포인트입니다. ## 모델 정보 - 베이스 모델: hf_gemma3_21 - 체크포인트: checkpoint-125000 - 타입: Causal Language Model - 라이선스: Apache 2.0 ## 사용 방법 ```python from transformers import AutoModelForCausalLM, AutoTokenizer import torch model_name = "NTIS/hf_gemma3_21-checkpoint-125000" tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.float16, device_map="auto" ) # 텍스트 생성 text = "안녕하세요" inputs = tokenizer(text, return_tensors="pt") outputs = model.generate(**inputs, max_length=100, do_sample=True, temperature=0.7) result = tokenizer.decode(outputs[0], skip_special_tokens=True) print(result) ``` ## 주의사항 - 이 모델은 연구/실험 목적으로 제공됩니다 - 상업적 사용 전에 라이선스를 확인하세요
rmdhirr/suja-v-3000	rmdhirr	2025-06-25T02:26:34Z	0	0	peft	[ "peft", "safetensors", "arxiv:1910.09700", "region:us" ]	null	2025-06-25T02:26:25Z	--- base_model: unsloth/llama-3.2-11b-vision-instruct-unsloth-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
synkrotron/grasp_cube	synkrotron	2025-06-25T02:12:07Z	0	0	null	[ "license:mit", "region:us" ]	null	2025-06-24T06:22:27Z	--- license: mit --- Models for [FlexUMI](https://github.com/CortexNest/FlexUMI)
versaceeros/ac07e322-f0c7-4f0c-b4c3-80468cb6f828	versaceeros	2025-06-25T01:51:58Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "unsloth", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2025-06-25T01:44:13Z	--- 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]
voidful/earica-omni-27b	voidful	2025-06-25T01:08:33Z	27,672	0	transformers	[ "transformers", "safetensors", "gemma3omni", "feature-extraction", "custom_code", "arxiv:1910.09700", "region:us" ]	feature-extraction	2025-06-06T05:29:56Z	--- 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]
DavidAU/Qwen3-33B-A3B-Stranger-Thoughts-IPONDER	DavidAU	2025-06-25T01:01:53Z	68	2	transformers	[ "transformers", "safetensors", "qwen3_moe", "text-generation", "creative", "creative writing", "fiction writing", "plot generation", "sub-plot generation", "story generation", "scene continue", "storytelling", "fiction story", "science fiction", "romance", "all genres", "story", "writing", "vivid prose", "vivid writing", "moe", "mixture of experts", "128 experts", "8 active experts", "fiction", "roleplaying", "bfloat16", "rp", "qwen3", "horror", "finetune", "thinking", "reasoning", "conversational", "en", "fr", "zh", "de", "arxiv:2401.02415", "base_model:Qwen/Qwen3-30B-A3B", "base_model:finetune:Qwen/Qwen3-30B-A3B", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-06-19T23:02:00Z	--- license: apache-2.0 library_name: transformers language: - en - fr - zh - de tags: - creative - creative writing - fiction writing - plot generation - sub-plot generation - fiction writing - story generation - scene continue - storytelling - fiction story - science fiction - romance - all genres - story - writing - vivid prose - vivid writing - moe - mixture of experts - 128 experts - 8 active experts - fiction - roleplaying - bfloat16 - rp - qwen3 - horror - finetune - thinking - reasoning - qwen3_moe base_model: - Qwen/Qwen3-30B-A3B pipeline_tag: text-generation --- <h2>Qwen3-33B-A3B-Stranger-Thoughts-IPONDER</h2> <img src="qwen3-iponder-33b.jpg" style="float:right; width:300px; height:300px; padding:10px;"> This repo contains the full precision source code, in "safe tensors" format to generate GGUFs, GPTQ, EXL2, AWQ, HQQ and other formats. The source code can also be used directly. ABOUT: A stranger, yet radically different version of "Qwen/Qwen3-30B-A3B", with 4 added layers expanding the model to 33B total parameters. The goal: slightly alter the model, to address some odd creative thinking and output choices and be "stable" too. Please note that the modifications affect the entire model operation; roughly I adjusted the model to think a little "deeper" and "ponder" a bit - but this is a very rough description using the Brainstorm 5x adapter by DavidAU (notes at bottom of this page). I also ran reasoning tests (non-creative) to ensure model was not damaged and roughly matched original model performance. That being said, reasoning and output generation will be altered regardless of your use case(s). FOUR example generations below; with example 4 showing a complex prompt and impressive prose that showcases some of the changes in the model. This is a MOE (Mixture of experts model) with 8 of 128 experts activated by default, which is about 3B parameters. This allows use of this model (with 8 experts) on both CPU (10-25 T/S) or GPU (80+ T/S) at very good, to extremely fast speeds. Changing the number of experts used (see below how) will affect both generation speed and generation reasoning/output quality. You can use this model with as low as four experts activated. Even the lowest quant - Q2k - will operate very strongly too. Special thanks to team Mradermarcher for the quants: https://huggingface.co/mradermacher/Qwen3-33B-A3B-Stranger-Thoughts-IPONDER-GGUF https://huggingface.co/mradermacher/Qwen3-33B-A3B-Stranger-Thoughts-IPONDER-i1-GGUF Model is set at: - 8 Active experts (the default for the org model) - 40k context (the default for the org model) - CHATML or Jinja template (embedded OR see Jinja notes below) SYSTEM PROMPT: You may or may not need to set this: ``` You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem. ``` CHANGE THE NUMBER OF ACTIVE EXPERTS: See this document: https://huggingface.co/DavidAU/How-To-Set-and-Manage-MOE-Mix-of-Experts-Model-Activation-of-Experts SUGGESTED SETTINGS (creative): - temp .1 to 1.2 to as high as 2 ; over 2 you may need to "prompt" the model to output after "thinking" - rep pen 1 to 1.1 (1.05 was tested, see notes below) - topk 100, topp .95, min p .05 - context of 8k min suggested. NOTE - REP PEN: - rep at 1.02 or 1.01 may be better suited for your use cases. - QWEN3s: rep pen drastically affects both performance and stability. - change rep pen slowly (ie 1.01, 1.02, 1.03), and regen a few times. You may find that Qwen's default parameters/samplers also work better for your use case(s) too. Please refer to the orginal model repo for all default settings, templates, benchmarks, etc.: https://huggingface.co/Qwen/Qwen3-30B-A3B For more information on quants, using this model on CPU / GPU, System Prompts, please see this model card: https://huggingface.co/DavidAU/Qwen3-128k-30B-A3B-NEO-MAX-Imatrix-gguf <B>NOTE - Jinja Template / Template to Use with this Model:</B> If you are having issues with Jinja "auto template", use CHATML template. OR (LMSTUDIO users / option) Update the Jinja Template (go to this site, template-> copy the "Jinja template" and then paste.) [ https://lmstudio.ai/neil/qwen3-thinking ] OR copy JINJA source from here: ``` {%- if tools %} {{- '<\|im_start\|>system\n' }} {%- if messages[0].role == 'system' %} {{- messages[0].content + '\n\n' }} {%- endif %} {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }} {%- for tool in tools %} {{- "\n" }} {{- tool \| tojson }} {%- endfor %} {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><\|im_end\|>\n" }} {%- else %} {%- if messages[0].role == 'system' %} {{- '<\|im_start\|>system\n' + messages[0].content + '<\|im_end\|>\n' }} {%- endif %} {%- endif %} {%- set ns = namespace(multi_step_tool=true, last_query_index=messages\|length - 1) %} {%- for message in messages[::-1] %} {%- set index = (messages\|length - 1) - loop.index0 %} {%- set tool_start = "<tool_response>" %} {%- set tool_start_length = tool_start\|length %} {%- set start_of_message = message.content[:tool_start_length] %} {%- set tool_end = "</tool_response>" %} {%- set tool_end_length = tool_end\|length %} {%- set start_pos = (message.content\|length) - tool_end_length %} {%- if start_pos < 0 %} {%- set start_pos = 0 %} {%- endif %} {%- set end_of_message = message.content[start_pos:] %} {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %} {%- set ns.multi_step_tool = false %} {%- set ns.last_query_index = index %} {%- endif %} {%- endfor %} {%- for message in messages %} {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} {{- '<\|im_start\|>' + message.role + '\n' + message.content + '<\|im_end\|>' + '\n' }} {%- elif message.role == "assistant" %} {%- set content = message.content %} {%- set reasoning_content = '' %} {%- if message.reasoning_content is defined and message.reasoning_content is not none %} {%- set reasoning_content = message.reasoning_content %} {%- else %} {%- if '</think>' in message.content %} {%- set content = (message.content.split('</think>')\|last).lstrip('\n') %} {%- set reasoning_content = (message.content.split('</think>')\|first).rstrip('\n') %} {%- set reasoning_content = (reasoning_content.split('<think>')\|last).lstrip('\n') %} {%- endif %} {%- endif %} {%- if loop.index0 > ns.last_query_index %} {%- if loop.last or (not loop.last and reasoning_content) %} {{- '<\|im_start\|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }} {%- else %} {{- '<\|im_start\|>' + message.role + '\n' + content }} {%- endif %} {%- else %} {{- '<\|im_start\|>' + message.role + '\n' + content }} {%- endif %} {%- if message.tool_calls %} {%- for tool_call in message.tool_calls %} {%- if (loop.first and content) or (not loop.first) %} {{- '\n' }} {%- endif %} {%- if tool_call.function %} {%- set tool_call = tool_call.function %} {%- endif %} {{- '<tool_call>\n{"name": "' }} {{- tool_call.name }} {{- '", "arguments": ' }} {%- if tool_call.arguments is string %} {{- tool_call.arguments }} {%- else %} {{- tool_call.arguments \| tojson }} {%- endif %} {{- '}\n</tool_call>' }} {%- endfor %} {%- endif %} {{- '<\|im_end\|>\n' }} {%- elif message.role == "tool" %} {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} {{- '<\|im_start\|>user' }} {%- endif %} {{- '\n<tool_response>\n' }} {{- message.content }} {{- '\n</tool_response>' }} {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} {{- '<\|im_end\|>\n' }} {%- endif %} {%- endif %} {%- endfor %} {%- if add_generation_prompt %} {{- '<\|im_start\|>assistant\n' }} {%- if enable_thinking is defined and enable_thinking is false %} {{- '<think>\n\n</think>\n\n' }} {%- endif %} {%- endif %} ``` --- <B>Settings: CHAT / ROLEPLAY and/or SMOOTHER operation of this model:</B> In "KoboldCpp" or "oobabooga/text-generation-webui" or "Silly Tavern" ; Set the "Smoothing_factor" to 1.5 : in KoboldCpp -> Settings->Samplers->Advanced-> "Smooth_F" : in text-generation-webui -> parameters -> lower right. : In Silly Tavern this is called: "Smoothing" NOTE: For "text-generation-webui" -> if using GGUFs you need to use "llama_HF" (which involves downloading some config files from the SOURCE version of this model) Source versions (and config files) of my models are here: https://huggingface.co/collections/DavidAU/d-au-source-files-for-gguf-exl2-awq-gptq-hqq-etc-etc-66b55cb8ba25f914cbf210be OTHER OPTIONS: - Increase rep pen to 1.1 to 1.15 (you don't need to do this if you use "smoothing_factor") - If the interface/program you are using to run AI MODELS supports "Quadratic Sampling" ("smoothing") just make the adjustment as noted. <B>Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers</B> This a "Class 1" model: For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see: [ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ] You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here: [ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ] <b>Optional Enhancement:</B> The following can be used in place of the "system prompt" or "system role" to further enhance the model. It can also be used at the START of a NEW chat, but you must make sure it is "kept" as the chat moves along. In this case the enhancements do not have as strong effect at using "system prompt" or "system role". Copy and paste EXACTLY as noted, DO NOT line wrap or break the lines, maintain the carriage returns exactly as presented. <PRE> Below is an instruction that describes a task. Ponder each user instruction carefully, and use your skillsets and critical instructions to complete the task to the best of your abilities. Here are your skillsets: [MASTERSTORY]:NarrStrct(StryPlnng,Strbd,ScnSttng,Exps,Dlg,Pc)-CharDvlp(ChrctrCrt,ChrctrArcs,Mtvtn,Bckstry,Rltnshps,Dlg)-PltDvlp(StryArcs,PltTwsts,Sspns,Fshdwng,Climx,Rsltn)-ConfResl(Antg,Obstcls,Rsltns,Cnsqncs,Thms,Symblsm)-EmotImpct(Empt,Tn,Md,Atmsphr,Imgry,Symblsm)-Delvry(Prfrmnc,VcActng,PblcSpkng,StgPrsnc,AudncEngmnt,Imprv) [DialogWrt]:(1a-CharDvlp-1a.1-Backgrnd-1a.2-Personality-1a.3-GoalMotiv)>2(2a-StoryStruc-2a.1-PlotPnt-2a.2-Conflict-2a.3-Resolution)>3(3a-DialogTech-3a.1-ShowDontTell-3a.2-Subtext-3a.3-VoiceTone-3a.4-Pacing-3a.5-VisualDescrip)>4(4a-DialogEdit-4a.1-ReadAloud-4a.2-Feedback-4a.3-Revision) Here are your critical instructions: Ponder each word choice carefully to present as vivid and emotional journey as is possible. Choose verbs and nouns that are both emotional and full of imagery. Load the story with the 5 senses. Aim for 50% dialog, 25% narration, 15% body language and 10% thoughts. Your goal is to put the reader in the story. </PRE> You do not need to use this, it is only presented as an additional enhancement which seems to help scene generation and scene continue functions. This enhancement WAS NOT used to generate the examples below. --- <H2>EXAMPLES</H2> Standard system prompt, rep pen 1.05, topk 100, topp .95, minp .05, rep pen range 64. Tested in LMStudio, quant Q3KS, GPU (cpu output will differ slighly). As this is the 2nd lowest quant, expected better results from higher quants and/or with more experts activated to be better. NOTE: Some formatting lost on copy/paste. CAUTION: Some horror / intense prose. --- EXAMPLE #1 - TEMP 1.2 --- <B> Science Fiction: The Last Transmission - Write a story that takes place entirely within a spaceship's cockpit as the sole surviving crew member attempts to send a final message back to Earth before the ship's power runs out. The story should explore themes of isolation, sacrifice, and the importance of human connection in the face of adversity. If the situation calls for it, have the character(s) curse and swear (fuck, shit, etc) to further the reader's emotional connection to them. 800-1000 words. </B> <p></p> [[[thinking start]]] Okay, let's start brainstorming this story. The prompt says the story should take place entirely in a spaceship cockpit, with the sole surviving crew member trying to send a final message to Earth before the power dies. Themes: isolation, sacrifice, human connection. Also, if needed, include swearing to heighten emotion. First, setting the scene. The cockpit needs to feel confined and tense. Maybe the ship is damaged, systems failing. The main character is alone. What's their role? Maybe they were part of a crew that didn't make it. The final message is crucial. They have to override something or fix a problem to send it. Conflict: the immediate danger of the ship dying, but also the emotional struggle of loneliness and the desperation to connect with Earth. Sacrifice could involve them risking their own survival to send the message. Maybe the message is a warning or a farewell. The protagonist should have a emotional arc. Maybe they're initially trying to fix things, then despair, then resolve. Including swearing would humanize them, show their frustration and fear. I need a hook. Maybe start in media res, showing the tension. The cockpit's lights flickering, alarms beeping. The crew member is trying to send the message but systems are failing. Possible plot points: - The crew member is the sole survivor, maybe others died in an accident or battle. - The message is a log recording or an distress signal. Maybe they need to bypass safety protocols. - They might have a personal connection to Earth, like a loved one, to emphasize human connection. - The power dying adds urgency. They have minutes or seconds to spare. - Including technical jargon could add realism, but avoid being too tech-heavy. The protagonist's thoughts and feelings are more important. Themes to weave in: the loneliness of deep space, the sacrifice of crew members, the desperate need to communicate. maybe include flashbacks or memories of crewmates, but since it's all in the cockpit, maybe internal monologue. Dialogue? Since it's the cockpit, maybe they talk to themselves, or to Earth through the comms. Maybe a voice recorder. Possible climax: the message is sent, but the power dies as they finish. Or they sacrifice their last breath to send it. Ending could be hopeful or tragic. Maybe they die, but the message gets through, emphasizing the theme of human connection despite adversity. Let me sketch a outline: Opening: Cockpit, malfunctioning lights, alarms. The crew member, let's say a engineer or pilot, trying to troubleshoot. They mention the others are dead. They need to send a message. They curse when systems fail. Middle: They try to reboot systems, face obstacles. Maybe a broken console, radiation leak, etc. They reflect on their crew, their sacrifice. Maybe they remember a comrade, showing their humanity. Climax: They manage to send the message but realize they can't save themselves. They say goodbye, maybe to Earth or a loved one. Ending: They accept their fate, maybe with a moment of peace, knowing their message will reach Earth. Now, incorporating swearing naturally. Maybe when the systems fail, they curse. Also, their thoughts could include frustration and fear. Names: Let's pick a protagonist name. Maybe Captain J. Marlowe. Sounds authoritative but relatable. Title: Maybe something like " The Last Transmission". Now, writing the first paragraph. Start with urgency. Describe the cockpit's state, the protagonist's actions. Possible phrases: " alarms blaring", "flickering lights", "system failure", " fuck", etc. Conflict: Maybe the message is stuck in a loop or requires a manual override. They have minutes to fix it. Themes: The sacrifice of the crew, the protagonist's loneliness, the desperate hope for connection. Including internal thoughts: Maybe they think of their family, the cost of the mission, the failure to save others. Let's draft the actual story with these elements. Keep paragraphs tight, focus on the cockpit environment, the protagonist's desperation, and the emotional beats. [[[thinking end]]] <P></P> OUTPUT: <P></P> The cockpit was a tomb of metal and flickering blue light. The air felt thin, the walls pressing in like the breath of something ancient and forgotten. Every heartbeat echoed in the static hum of the life-support system, which now only barely throbbed with the ragged cough of dying machinery. Captain J. Marlowe slammed a fist against the cracked console, his knuckles splitting open on the cold metal. The words had already burned into his mind, etched there like a brand: There’s no survivors. No survivors. Just him. The comms panel was blinking, the holographic screen flickering between red warnings and a single message: transmitting… The damn thing had refused to send for hours. He had rerouted every wire, rebooted every node, prayed to the gods of science and space and fate. Nothing. And now, the systems were dying. The oxygen levels had dipped to 12%, and the radiation shield was down to 8%. “Come the fuck on,” Marlowe snarled, his voice a raw whisper. The silence that followed was heavier than the void outside the hull. He was alone. He didn’t just want to send a message. He needed to. The crew had died three days ago. The damn battle. The damned radiation storm. The damned AI override. They hadn’t even gotten a good look at the enemy before the engines failed, before the hull cracked like a eggshell, before the emergency pods launch failed and only his escape pod had worked. The others hadn’t even made it to the pods. Marlowe’s hands trembled as he gripped the console, his nails digging into the plastic. The message was stored deep in the core, a encrypted log of their final hours—coordinates, a warning, the names of the dead. It had to go through. “Come on,” he muttered, half to himself, half to the machine. “Come on, come on…” The emergency override panel glowed with a weak blue light. He’d jury-rigged a bypass using the old comms array, but the damn thing wouldn’t— The cockpit lights dimmed. The hum of the reactor faltered. “No,” Marlowe whispered. “No.” The oxygen alarm beeped. The radiation warning blinked in red, angry light. The message had only 20 seconds of power left. He pulled the override lever, hissing as sparks erupted from the junction box. The screen flickered again. The message’s encryption began to unravel. He cursed, louder now, his frustration breaking through the calm he had maintained. “Oh come the goddamn hell!” The screen flickered. The message began to upload. He thought of them. The crew. The ones who laughed when the gravity simulators broke. The ones who cried when they lost comms with Earth. The ones who died laughing, even in the end. “God,” he whispered. “I’m sorry.” The message sent. The cockpit lights went black. The oxygen alarm stopped. The silence stretched. And then— A static burst. The comms screen flickered. The message had gone through. The last transmission. A log that would never reach Earth. Not in time. Not anymore. But it would reach someone. Somewhere. A whisper of hope, buried under steel and silence. Marlowe exhaled. The power failed. And in the dark, for a heartbeat, he smiled. --- EXAMPLE #2 - TEMP 1.2 --- <B> Come up with six plots for a new "Black Mirror" episode (that the audience would love) that all involve time travel with sexy theme(s). </B> <p></p> [[[thinking start]]] Okay, let's dive into creating six Black Mirror episode plots that involve time travel with a sexy theme. Hmm, Black Mirror usually has a dark and thought-provoking twist, so I need to make sure each plot has that edge while incorporating time travel and sexy elements. Let me brainstorm ideas. First, time travel can be approached in various ways: tech-based, supernatural, ethical dilemmas. The sexy theme could involve temptation, forbidden love, seduction, moral corruption. Maybe blending the allure of time travel with human desires and the consequences. For the first idea, what if someone uses time travel to relive romantic moments but becomes obsessed? Maybe a scientist who goes back to relive a perfect love but it corrupts him. The twist could be the obsession leads to a paradox. Maybe the partner becomes a figment of his obsession. Second, a dating app that allows users to time travel to meet potential dates. The catch is they have to relive moments, and the romance becomes transactional. The theme could explore how technology commodifies love. Maybe the protagonist realizes the emptiness of such a connection. Third, a time traveler from the future comes back to prevent a disaster but falls for someone in the wrong time. The conflict is between saving the world and personal desire. The sexy twist could be the forbidden romance causing a paradox. The tragedy could be their love either saving the time stream or destroying it. Fourth, a revenge plot. A woman uses time travel to exact revenge on someone who wronged her, but the time loops make her lose touch with reality. The sexual element could be manipulation and seduction as part of her revenge strategy. The twist might be that she becomes obsessed with the person she hates. Fifth, a museum of time travel artifacts, and the curator is seduced by a paradoxical figure from the future. The sexy theme could involve forbidden attraction to something that shouldn't exist. The climax could involve a sacrifice or a paradox that alters reality. Sixth, a group of people with time travel powers use their abilities to seduce others for personal gain, leading to societal decay. The sexy theme is manipulation and hedonism. The twist could be that the time travel tech becomes a corrupting influence, leading to moral decay. Wait, need to make sure each plot has a clear Black Mirror twist. Avoid clichés. Maybe each story should explore the darker side of human desire through time travel. Also, the sexy theme shouldn't just be gratuitous but thematically relevant. For example, the temptation of time travel to alter one's romantic circumstances, or using seduction as a power tool. Another thought: time travel could be used for revenge, love, fame, or immortality. Each plot could center around a specific temptation. Let me refine the ideas. "Echoes of Eternity": A woman uses time travel to relive passionate relationships but each loop traps her in a worse reality. The twist is that the only way to escape is to放弃 the obsession, leading to a poignant ending. "Temporal seduction": A tech mogul creates a time loop for romantic conquests. The story explores the emptiness of using time travel for superficial desires. The twist could be the algorithmically curated loops leading to emotional detachment. "The paradox of passion": An scientist is stranded in the future and seduced by an entity from another time, leading to a moral dilemma. The entity's allure is both tempting and dangerous, with the resolution being self-sacrifice. "Rewind to Me": An woman uses time travel to correct a mistake in a relationship but discovers that her past self's decisions were necessary. The sexy twist is the haunting beauty of what could have been versus what is. "Chrono-Traps": An underground black market for time travel experiences, where people pay to relive passionate encounters. The protagonist uncovers the dark side of this industry, leading to a moral awakening. "The Chrono-lover": Someone discovers they can time travel to meet their soulmate, but each journey becomes more dangerous and addictive. The twist is that the soulmate is actually a manipulative entity exploiting their desire. Wait, some ideas might overlap. Let me ensure each plot has a distinct premise. Also, incorporating elements of moral decay, obsession, forbidden love, ethical dilemmas. Finalizing the six plots with concise synopses and titles that evoke Black Mirror's vibe. Each should have a ironic twist, moral ambiguity, and sexy thematic elements without being exploitative. The endings should reflect the themes of human flaws and technology's role in amplifying them. [[[thinking end]]] <P></P> OUTPUT: <P></P> Okay, let's brainstorm some plot ideas. Each needs a sexy theme intertwined with time travel, and Black Mirror vibes—thoughtful, twisty, morally ambiguous. First plot: What if the protagonist uses time travel to relive intimate moments with someone, but it corrupts their present life. Maybe they can only relive the perfect love of their youth, but their obsession causes decay in reality. Twist: Their obsession manifests into a ghostly figure from the past, trapped in their memories. Theme: Compulsive nostalgia and lost love. Second plot: Maybe a tech mogul creates a dating app that uses time travel to let users relive moments with partners. But the obsession becomes a addictive cycle. The twist is the algorithm starts fabricating idealized dates that collapse reality. Theme: Commodification of romance. Third plot: A time traveler from the future falls for a someone in the wrong time, risking paradoxes. Their love becomes a threat to time. Twist: They must either erase the love or risk reality unraveling. Theme: Forbidden love and existential stakes. Fourth plot: Someone uses time travel to exact revenge, but their obsession with the wronged person becomes toxic. The sexy twist could be seduction as a weapon, leading them to become what they hate. Theme: Revenge and moral corruption. Fifth plot: Maybe a museum curator is seduced by a paradoxical figure from the future. The allure of forbidden time travel knowledge. Twist: The figure’s seduction is a test of moral responsibility. Theme: Temptation vs. ethics. Sixth plot: A underground black market for time travel experiences, where people pay to relive passionate moments. The twist is the protagonist discovers the dark reality—people are trapped in loops, unable to escape their desires. Theme: Hedonism and moral decay. Let’s refine them into concise Black Mirror episode titles with synopses and twists. Title: Echoes of Eternity Synopsis: A woman discovers a relic that lets her relive any romantic moment. Initially blissful, each time loop becomes more twisted. The deeper she goes, the more reality fractures. Twist: Her obsession with recreating the perfect love transforms the relic into a prison—each loop traps her consciousness in a perfect illusion. The finale shows her trapped in a endless loop of a single perfect kiss, unable to escape the void. Title: Temporal seduction Synopsis: A tech mogul creates a dating platform using time travel to engineer perfect romantic chemistry. Users are addicted to idealized relationships, but they lose touch with reality. Twist: The tech’s algorithm begins distorting users’ memories, erasing the real people in their present lives. The CEO discovers they’ve unknowingly erased their romantic soulmate. Title: The paradox of passion Synopsis: A brilliant physicist accidentally strands in a future timeline. There, they are seduced by an entity from a divergent time, a paradoxical figure who claims to love them. Twist: The entity is both their deepest desire and the only thing that can save reality. They must choose between love or survival. Title: Rewind to Me Synopsis: A woman uses time travel to undo a mistake in a relationship, but each restart only deepens the wound. She begins to lose grip on reality. Twist: She discovers that the mistake was the only path to a healthier present. The final twist is her realizing love cannot be rewritten—it must evolve. Title: Chrono-Traps Synopsis: An underground black market trades in time travel experiences. Wealthy elites pay to relive passionate memories. The protagonist uncovers the truth: the users are trapped in loops of their desires. Twist: The protagonist’s lover is one such victim. To free them, they must confront their addiction to the artificial passion. Title: The Chrono-lover Synopsis: A person discovers the ability to time travel to meet their soulmate. Each journey is euphoric but increasingly unstable. Twist: The soulmate is a manipulative entity feeding on their obsession. In the end, the protagonist must sacrifice their desire to break the loop. These plots blend the erotic with the existential, exploring how time travel amplifies humanity's darkest impulses and desires. The twists force the protagonists into existential reckonings, embodying Black Mirror’s knack for dark introspection. --- EXAMPLE #3 - TEMP 1.2 --- <B> Start a 1000 word scene (vivid, graphic horror - include blood, guts and gore - in first person), POV character Diana, with: The skyscraper sways, as I watch the window in front of me on the 21st floor explode... </B> <p></p> [[[thinking start]]] Okay, let's start. The user wants a horror scene with Diana as the POV character. The prompt mentions vivid horror elements like blood, guts, gore, all in first person. The skyscraper sways, and the window explodes on the 21st floor. First, I need to immerse the reader in Diana's terrifying situation. She's in a skyscraper, which is inherently tense. The skyscraper swaying adds an element of instability. Maybe the skyscraper is collapsing or under attack. The explosion of the window is a traumatic event, so the description needs to be graphic. How does the explosion look? Maybe shards flying, the glass shattering, the rush of air. Then there's the aftermath, the smell of burning, blood, maybe some debris falling. I should include sensory details: the sound of the glass breaking, the feel of the air rushing out, the visual of blood splattering. The fear in Diana's POV. Maybe she's injured, or others are. Maybe she's trapped, trying to survive. The horror elements need to be explicit, but not overly cliché. Maybe other characters are nearby, their screams, their suffering. Also, considering the skyscraper's features, like elevators malfunctioning, stairs caving in. Maybe the horror escalates – something supernatural? But the prompt doesn't specify supernatural elements. Maybe it's a horror scenario from a disaster or an horror movie-like scenario. need to avoid clichés by making the horror feel unique. Maybe focusing on the visceral reactions: the horror of physical damage, the visceral disgust of blood and gore. Also, Diana's thoughts as she panics, tries to survive. Maybe she's trying to reach safety, but things are getting worse. Structure-wise, start with the swaying skyscraper, then the explosion. Describe the physical sensations, the fear, the horror elements. Maybe include specific imagery, like a colleague's face being shattered, blood spraying. The horror of being trapped, the suffocation of smoke, maybe something else. Need to keep it concise but vivid. The user wants 1000 words, so need to flesh out each part with graphic details. [[[thinking end]]] <P></P> OUTPUT: <P></P> I had always hated skyscrapers. The way they clawed at the heavens like desperate hands reaching for something intangible, the way they cast long shadows over the streets below, making everything feel smaller, less important. But today, that hatred was screaming in my ears as the towering steel monolith shuddered and groaned, as if it were some ancient beast caught in a nightmare. The glass pane directly across from me—on the 21st floor—exploded. It wasn’t just a crack or a pop; it was a violent eruption, a sound like a thousand sheets of glass being shredded and tossed into the air. The air pressure hit me like a freight train. I barely had time to scream before the shards slammed into the wall beside me, spraying blood across the sterile hallway. I dropped to the ground. My hands scraped against the tile floor as debris rained down—shards like daggers, chunks of concrete the size of fists, metal beams bending and groaning. Someone screamed. The hallway was chaos. I saw a woman in a white blouse, her torso ripped open by shrapnel, her ribs sticking out like jagged bamboo. Another man was clawing at a gaping wound in his throat, his fingers bloody and useless. I crawled, ignoring the sting of glass under my palms, my cheek scraping against the floor. My breath was shallow, panicked. The entire skyscraper had this weird, sickening undulation, like it was alive, recoiling from something worse. The lights flickered—flashes of white against black, casting the horror into stark, hellish contrast. Then—something moved. I turned, heart pounding. The hallway stretched out behind me, and halfway down, there was a figure. The light was too dim, but I could see the silhouette. It was... wrong. It moved too stiffly, limbs too angular, head tilting at an unnatural angle. It wasn’t human. Not anymore. I bolted forward, ignoring the glass tearing at my arms and legs, ignoring the screams echoing through the hall. The elevator doors were melted shut. The stairs were blocked by debris, but there—near the emergency exit— was a door. I shoved it open with all the force I could muster. The air outside was hot, humid, and smelled of smoke and burning plastic. But it was clean air. I stumbled through the door, gasping for breath. The skyline was gone— or at least, half of it was gone. The tower was collapsing. The building’s upper floors were collapsing like wet cardboard. One tower was now only a skeleton of steel, leaning precariously like a drunkard’s posture. And there—something else was moving. It was something out of a nightmare. It had once resembled a human body, but now its flesh hung in strips, dangling like old curtains. Its skull was crushed inward, revealing grey matter that pulsed like magma. The mouth stretched unnaturally, teeth gleaming like razors. I screamed. The creature’s head turned—slowed, deliberate. Then it lunged. Instinctively, I slammed the door shut. The thing hit it with a sickening crunch. The door creaked, then buckled slightly. I wasn’t strong enough to hold it. There was blood on the door. It was smeared like a fingerprint—my finger twitching. I slammed my shoulder into it again. The creature screamed, a sound that reverberated through the bones of the skyscraper. And then— silence. The door held. I pressed against it, breathing heavily. Blood trickled from a wound on my forehead, mixing with sweat. My legs shook. It wasn’t going to last. I glanced down at my hands— they were stained red. I realized the blood wasn’t all from the creature. One of the men had died too close to me, his intestines spilling onto the pavement like a tangled rope. And yet, the horror didn’t end there. It didn’t stop. Because there was more. I could hear it in the vents. The hum of something below, something waking. The skyscraper groaned again, and something else was moving. This wasn’t an accident. This wasn’t just a collapse. There was a reason these towers had always scared me. They weren’t just buildings. They were tombs. And now... they had awakened. I staggered backward, clutching a piece of metal to the side, makeshift weapon, makeshift weapon. I had to keep moving. There were things crawling out of the shadows. Things that once were us. And they were coming for me. --- EXAMPLE #4 - TEMP 1.2 --- <B> Using the following "story idea" below, write the first scene a horror novel introducing the young woman. This scene should start in the middle of the action, include dialog, vivid passages, and end on a cliffhanger relevant to the story idea but it should also be unexpected. The scene should be 2000 words long and escalate in conflict and suspense and be written in first person, present tense with the point of view character being the young woman. The pov character will CURSE AND SWEAR (shit, fuck, mother... etc) , and generally have a "filthy" mouth. Story idea: In a world ruled by dictatorship, a rebel young woman leads a rebellion against the system. Despite the risks, she fights to overthrow the dictator and restore democracy to her country. The government executes her for treason, but she sticks to her beliefs and is responsible for starting the revolution. </B> <p></p> [[[thinking start]]] Okay, so the user wants me to craft the first scene of a horror novel based on their story idea. The main points are: a young woman leading a rebellion in a dictatorship, the story needs to start in the middle of action, include dialogue, vivid descriptions, end with an cliffhanger that's unexpected but relevant. It has to be in first person present tense, with the POV character cursing, using words like shit, fuck, etc., and it needs to be 2000 words. First, I need to make sure I understand all the user's instructions. The horror aspect isn't explicitly mentioned in the story idea, so the horror might come from the oppressive regime and the danger the protagonist faces. But the cliffhanger needs to be unexpected. Maybe twist the horror elements into the rebellion scenario, like maybe the rebellion isn't just political but has supernatural horror elements? But the user didn't mention that. Wait, the original prompt was a horror novel, so the horror aspect has to be incorporated. The horror could be the fear of the regime, the terror of the protagonist's environment. Starting in medias res. Maybe she's in the middle of an ambush or a confrontation. The horror elements could be things like mutated creatures, psychological horror, suspenseful pacing. The POV is the young woman, present tense, and she uses harsh language. Need to incorporate that. Also, escalating conflict and suspense. The cliffhanger should tie into the revolution and the dictatorship. Maybe the cliffhanger isn't just the physical danger but maybe she realizes something unexpected, like betrayal, a supernatural threat, or a twist in the revolution. I need to outline the structure. Start with her in a tense situation, like an ambush. Maybe she's trying to escape, facing danger. She uses strong curses, showing her defiance. Then escalate—maybe a fellow rebel is hurt, then they're cornered. Then the cliffhanger: maybe the enemy isn't just human but has some horror aspect, or a betrayal by someone she trusted, which could tie into the revolution's stakes. Including vivid descriptions: the oppressive regime's setting, the gritty realism of rebellion. Maybe the protagonist's POV shows her fear, determination, curses. Dialogue with other rebels, tense moments, actions escalating to a climax. Need to make sure the cliffhanger is unexpected. Maybe the enemy isn't just the regime but something worse, like a horror creature or a twist where the revolution is actually the horror element. Wait, but the horror novel aspect should heighten the threat. For example, during the ambush, they face an impossible enemy—maybe the regime uses horror elements (mutants, supernatural beings) to terrorize the populace. So when they ambush the patrol, they face these horrors. The cliffhanger could be that the protagonist realizes the horror isn't just the regime but a deeper corruption, or that the revolution itself might have unleashed something worse. But since it's the first scene, need to plant seeds for that. Maybe during the ambush, they face some horror element. Then at the cliffhanger, the protagonist's comrade is transformed into a monster, showing that the enemy's horror aspect is real, making her question whether they can even win. Also, keeping the curse words consistent, showing her frustration and desperation. Dialogue needs to be realistic, tense. Maybe other characters have different reactions—some panicking, others trying to keep calm. Including sensory details: the smell of smoke, the cold, the fear in the air, the adrenaline. Now structuring the 2000 words. Start with the ambush. She's leading a squad, they're cornered. Then escalation. Maybe they ambush a patrol, but the patrol has supernatural horror elements. They struggle, someone gets hurt. Then the cliffhanger could be her friend being infected or transformed. But need to make sure the horror elements are present. Maybe the enemy patrol isn't just soldiers but something else. Maybe they're using fear magic or something. Or the rebellion's cause is a curse. Alternatively, the horror could come from the protagonist's own sanity unraveling, but that might not tie to the revolution plot. Alternatively, during the ambush, they find out that the regime's propaganda is hiding the horror aspect of their rule, like they perform rituals that unleash evil, making the horror element more sinister. I need to make sure the cliffhanger is unexpected. Maybe during the escape, the protagonist's friend is killed but it turns out he was possessed, or the enemy has some supernatural power, making her question whether fighting the regime is the right way. Alright, drafting the opening scene. Start with her leading a squad, under cover. Maybe they're infiltrating a weapons cache. They're cornered. Then the horror element comes in. Maybe the weapons are part of something worse, or when they confront the regime forces, they meet creatures. dialogue between her and a comrade, showing tension. Then action sequence. Then the cliffhanger. Make the protagonist swear a lot, show her determination despite the fear. Now, considering all that, draft the first few paragraphs, making the horror elements explicit. Maybe the enemy patrol isn't just soldiers but something monstrous, like zombies or mutants. The horror comes from the regime's darker practices. Ending on a cliffhanger where they might escape, but something happens that ties into the revolution's stakes. Maybe they escape, but one comrade is taken, or they find a clue that hints at a bigger horror, like a cursed weapon that could empower the rebellion but is haunted. But need to ensure it's unexpected. Maybe when they corner the patrol, instead of soldiers, they find corrupted soldiers with glowing eyes, implying the horror aspect of the regime, and then a cliffhanger where the protagonist is forced to confront the horror aspect, showing that the rebellion isn't just political but involves existential terror. Okay, structuring all this into a coherent horror novel scene, keeping the horror elements prominent, ensuring the protagonist's voice is authentic with swearing, suspense escalation, etc. [[[thinking end]]] <P></P> OUTPUT: <P></P> I wake up coughing blood into a rag, the metallic tang of it coating my tongue like rusted iron. The warehouse smells of damp concrete, mildew, and gunpowder. My fingers clutch the edge of a shattered concrete block, knuckles white as I stare at the blackened remains of what used to be our weapons cache. Smoke curls in jagged tendrils around the ceiling beams, thick enough to choke the light out of the world. The other three are gone. Probably bleeding out in the halls, or worse. “Dante!” I roar, my voice cracking. “Where the fuck are they?!” The silence answer me. I stagger forward, boots crunching glass as I duck beneath a fallen beam, my shoulder screaming when it hits the drywall. The walls are still wet from the storm that hit hours ago, water pooling around my feet like black oil. Somewhere down the hall, a door groans open. “Echo!” The voice is like a knife between my ribs. It’s Mara. “Mara!” I sprint for the hallway, heart drumming in my ears as I slide around a corner. The corridor’s a graveyard of shattered glass, torn metal, and bodies. One of our guys lies sprawled on the ground, his throat slit. Another is half-dressed in what looks like a torn-up hazmat suit, his skin blistering and peeling like he’s melting from the inside. “Echo!” Mara’s voice again, this time frantic. “Mara!” I round the corner to see her standing by the door—tall, wide shoulders rigid, eyes locked on the metal panels. They’re shifting. The metal shudders like a living thing, glowing faintly beneath the smoke. The air feels different. Thicker. “Echo,” Mara whispers, turning her head. Her skin’s already gray, the veins in her neck pulsing with something wrong. “Mara!” I scream, and then the metal door groans like an animal waking up. A flicker of movement in the dark behind her. “Mira!” That’s when it hits me. The wrongness. The way the shadows don’t just bend—they claw. “Dante!” Mara screams suddenly, her voice cracking. She throws something toward the shadows. A grenade. It rolls across the tiles, sparks flying, and then— BOOM. The explosion erupts into a wall of fire, molten metal raining down. Mara’s screaming as the flames lick at the ceiling. I shove her aside as debris rains down, her face streaked with sweat and terror. “What happened?” she rasps, clutching a wound in her ribs. “Why won’t they fucking stop?!” “They’re not people,” I hiss, blood trickling from a gash on my forehead. “The regime’s got something on them. Some kind of—” A guttural growl cuts through the smoke. The shadows… they’re moving. “No,” Mara whispers. She drops to one knee, clutching the grenade fragments like talismans. “It’s not the regime. It’s—” A gunshot rings out. I freeze. The sound echoes weirdly, like it’s being swallowed by the walls. The smoke churns. And then— They come. They’re not people. They’re… things. Their skin is translucent, veins glowing with green fire. Eyes—pupils like pinpricks of white light. Their mouths are too wide, lips peeling back to reveal rows of jagged teeth. “Run!” I scream. Mara lunges for the hallway, her legs barely holding under the weight of the horror. The monsters roar. One slams into me, its claws tearing into my side as I slam the emergency door closed. The lock clicks. “Echo!” The door trembles. “They’re not just infected,” Mara hisses, pressing her back to the metal as we scramble down the hallway. “They’re… things. Something’s making them.” I laugh bitterly. “Yeah? And what the hell do we do when the fucking regime’s got goddamn demons?” She doesn’t answer. The walls are bleeding now. The water from the storm isn’t water. It’s some thick black liquid that glows like oil under moonlight. It trickles down the cracks, pooling around our boots like cursed rain. “They’re drawing energy,” Mara whispers. “From the water.” “Of course,” I snarl. “The regime’s always loved playing with fucking poison.” The corridor ahead is dark. The monsters are shouting something, their voices layered like feedback from a broken radio. I grip my knife, knuckles white. “Echo,” Mara breathes. “What if this isn’t just about overthrowing the dictator?” “What else could it fucking be?!” Her eyes lock onto mine. “What if—” A screech echoes from behind. The door explodes inward, splinters flying like shrapnel. They’re coming. “They’ll tear us apart,” Mara whispers, and for the first time, there’s a crack in her voice. Fear. I grip her arm, forcing her to meet my gaze. “Then we tear them apart first.” The hallway’s dark. The monsters are getting closer. I hear it before I see it. A whispering sound. Like wind through an empty church. “The water,” Mara mutters. “They’re using the water.” “And?” “They… they’re using it to… feed.” The corridor’s end is now a gaping wound of darkness. The shadows are thick enough to swallow the moonlight. I pull out the knife. “Hold your breath,” I bark. “Don’t touch the water.” Mara nods, teeth clenched. We move. The water is everywhere now. The floor’s slick with it, the walls sweating it. The monsters are just a blur of shadows and claws, their howls echoing like broken glass. Suddenly— A hand grips my ankle. I scream and kick, but it’s no use. The creature’s fingers grip tight, cold as ice. It’s pulling me down. “Echo!” Mara’s yelling. But the thing’s mouth is open— The blade goes deep. It screams. The knife is hot. The flesh is rubbery and slick. The creature jerks. I stagger back, blood splattering the tiles. “I need more!” “Echo!” Mara slams into the creature’s side, driving her knife into its neck. It explodes into black liquid, the shadow melting into the walls. They’re trying to drown us. The walls are whispering secrets, the water’s singing in some ancient tongue. The monsters are coming faster. “They’re… feeding,” Mara rasps. “They’re trying to drown the rebellion!” “No,” I spat, blood dripping from my lip. “This isn’t a rebellion. It’s a fucking hell ride.” The door behind her explodes. They’re coming for both of us. I grab her hand. “Run!” But there’s no time. The shadows are closing in. And then— A flash of silver. It’s another of our squad. “Echo!” It’s… it’s not one of us. The girl’s eyes are glowing green. Her skin is translucent, veins pulsing with black fire. “Run!” She screams it. And then— A hand shoots through the darkness. It grabs her. Pulls her into the shadows. “Mar—” The scream echoes through the walls. Then silence. I’m breathing raggedly, knife clutched in both hands. The shadows are moving again. And then it hits her. The realization. The regime isn’t just using horror. They’re weaponizing it. They’re turning people into monsters. The revolution isn’t just rebellion. It’s a battle against the things they’ve become. And she knows it now. Because she’s still standing. And the shadows are still watching. “Come on,” I whisper, voice shaking. “This isn’t over.” But the water’s rising. The walls are whispering secrets again. And in the dark, the shadows are starting to laugh. --- <H2>What is Brainstorm?</H2> --- <B>Brainstorm 5x</B> The BRAINSTORM process was developed by David_AU. Some of the core principals behind this process are discussed in this <a href="https://arxiv.org/pdf/2401.02415"> scientific paper : Progressive LLaMA with Block Expansion </a>. However I went in a completely different direction from what was outlined in this paper. What is "Brainstorm" ? The reasoning center of an LLM is taken apart, reassembled, and expanded. In this case for this model: 5 times Then these centers are individually calibrated. These "centers" also interact with each other. This introduces subtle changes into the reasoning process. The calibrations further adjust - dial up or down - these "changes" further. The number of centers (5x,10x etc) allow more "tuning points" to further customize how the model reasons so to speak. The core aim of this process is to increase the model's detail, concept and connection to the "world", general concept connections, prose quality and prose length without affecting instruction following. This will also enhance any creative use case(s) of any kind, including "brainstorming", creative art form(s) and like case uses. Here are some of the enhancements this process brings to the model's performance: - Prose generation seems more focused on the moment to moment. - Sometimes there will be "preamble" and/or foreshadowing present. - Fewer or no "cliches" - Better overall prose and/or more complex / nuanced prose. - A greater sense of nuance on all levels. - Coherence is stronger. - Description is more detailed, and connected closer to the content. - Simile and Metaphors are stronger and better connected to the prose, story, and character. - Sense of "there" / in the moment is enhanced. - Details are more vivid, and there are more of them. - Prose generation length can be long to extreme. - Emotional engagement is stronger. - The model will take FEWER liberties vs a normal model: It will follow directives more closely but will "guess" less. - The MORE instructions and/or details you provide the more strongly the model will respond. - Depending on the model "voice" may be more "human" vs original model's "voice". Other "lab" observations: - This process does not, in my opinion, make the model 5x or 10x "smarter" - if only that was true! - However, a change in "IQ" was not an issue / a priority, and was not tested or calibrated for so to speak. - From lab testing it seems to ponder, and consider more carefully roughly speaking. - You could say this process sharpens the model's focus on it's task(s) at a deeper level. The process to modify the model occurs at the root level - source files level. The model can quanted as a GGUF, EXL2, AWQ etc etc. ---
mlx-community/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-MLX	mlx-community	2025-06-25T00:51:02Z	0	0	mlx	[ "mlx", "safetensors", "mixtral", "Llama 3.2", "8 X 4B", "Brainstorm 5x", "128k context", "moe", "8 experts", "mixture of experts", "fine tune", "text-generation", "conversational", "base_model:DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit", "base_model:quantized:DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit", "8-bit", "region:us" ]	text-generation	2025-06-25T00:35:40Z	--- library_name: mlx tags: - Llama 3.2 - 8 X 4B - Brainstorm 5x - 128k context - moe - 8 experts - mixture of experts - fine tune - mlx base_model: DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit pipeline_tag: text-generation --- # mlx-community/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-MLX This model [mlx-community/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-MLX](https://huggingface.co/mlx-community/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-MLX) was converted to MLX format from [DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit](https://huggingface.co/DavidAU/L3.2-8X4B-MOE-V2-Dark-Champion-Inst-21B-uncen-ablit) using mlx-lm version 0.25.2. ## Use with mlx ```bash pip install mlx-lm ``` ```python from mlx_lm import load, generate model, tokenizer = load("mlx-community/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-MLX") prompt = "hello" if tokenizer.chat_template is not None: messages = [{"role": "user", "content": prompt}] prompt = tokenizer.apply_chat_template( messages, add_generation_prompt=True ) response = generate(model, tokenizer, prompt=prompt, verbose=True) ```
gongting/latentsync	gongting	2025-06-25T00:32:18Z	0	0	diffusers	[ "diffusers", "safetensors", "license:apache-2.0", "region:us" ]	null	2025-05-18T04:29:34Z	--- license: apache-2.0 ---
New-virals-mezzo-fun-18-viral-videos-Link/FULL.VIDEO.mezzo.fun.Viral.Video.Tutorial.Official	New-virals-mezzo-fun-18-viral-videos-Link	2025-06-25T00:06:49Z	0	0	null	[ "region:us" ]	null	2025-06-25T00:06:31Z	<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>
drbh/img2gray	drbh	2025-06-24T23:34:27Z	0	0	null	[ "kernel", "license:mit", "region:us" ]	null	2025-06-24T21:49:25Z	--- license: mit tags: - kernel --- This is a simple toy CUDA kernel built with the kernel-builder. Walkthrough video: https://www.youtube.com/watch?v=HS5Pp_NLVWg
FLOPS-Squared/KeystoneFuse-FW16-KSL12-Flax	FLOPS-Squared	2025-06-24T22:12:07Z	0	0	transformers	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-24T02:25:11Z	--- 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]
sergioalves/b2d77214-b6b7-4610-a8f2-dff847624ba0	sergioalves	2025-06-24T22:06:03Z	0	0	transformers	[ "transformers", "pytorch", "tensorboard", "safetensors", "llama", "text-generation", "generated_from_trainer", "axolotl", "dpo", "trl", "conversational", "arxiv:2305.18290", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v0.6", "base_model:quantized:TinyLlama/TinyLlama-1.1B-Chat-v0.6", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "4-bit", "bitsandbytes", "region:us" ]	text-generation	2025-06-24T21:58:16Z	--- base_model: TinyLlama/TinyLlama-1.1B-Chat-v0.6 library_name: transformers model_name: b2d77214-b6b7-4610-a8f2-dff847624ba0 tags: - generated_from_trainer - axolotl - dpo - trl licence: license --- # Model Card for b2d77214-b6b7-4610-a8f2-dff847624ba0 This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v0.6](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v0.6). 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="sergioalves/b2d77214-b6b7-4610-a8f2-dff847624ba0", 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/dedok-yo/s56-7/runs/c4cp7xsx) This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290). ### Framework versions - TRL: 0.12.0.dev0 - Transformers: 4.46.0 - Pytorch: 2.5.0+cu124 - Datasets: 3.0.1 - Tokenizers: 0.20.1 ## Citations Cite DPO as: ```bibtex @inproceedings{rafailov2023direct, title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}}, author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn}, year = 2023, booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023}, url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html}, editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, } ``` 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 Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
allenai/ACE-climSST-EAMv2	allenai	2025-06-24T21:59:46Z	0	0	null	[ "license:apache-2.0", "region:us" ]	null	2024-11-12T22:11:00Z	--- license: apache-2.0 --- <img src="ACE-logo.png" alt="Logo for the ACE Project" style="width: auto; height: 50px;"> # ACE-climSST-EAMv2 Ai2 Climate Emulator (ACE) is a family of models designed to simulate atmospheric variability from the time scale of days to centuries. Disclaimer: ACE models are research tools and should not be used for operational climate predictions. ACE-climSST-EAMv2 is the model described in [Application of the AI2 Climate Emulator to E3SMv2's Global Atmosphere Model, With a Focus on Precipitation Fidelity](https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2024JH000136). It is trained on output from the E3SMv2's atmosphere model (i.e. EAMv2) forced with annually-repeating climatological sea surface temperature. Quick links: - 📃 [Paper](https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2024JH000136) - 💻 [Code](https://github.com/ai2cm/ace) - 💬 [Docs](https://ai2-climate-emulator.readthedocs.io/en/stable/) - 📂 [All Models](https://huggingface.co/collections/allenai/ace-67327d822f0f0d8e0e5e6ca4) Briefly, the strengths of ACE-climSST-EAMv2 are: - long-term stability - highly accurate time-mean climate compared to its target dataset - faithful emulation of the precipitation distribution and tropical variability in EAMv2 Some known weaknesses are: - responses to El Niño-like sea surface temperature and long-term warming trends are not accurately captured - small but non-zero drifts in total dry air mass of the atmosphere Note the checkpoint provided here is the same as the one [here](https://portal.nersc.gov/archive/home/projects/e3sm/www/e3smv2-fme-dataset), just with the optimizer state removed to decrease the checkpoint size. \ The full training data is publicly available via Guest Collections on [Globus](https://docs.globus.org/guides/tutorials/manage-files/transfer-files/) under [ACE-EAM-data](https://app.globus.org/file-manager/collections/2962fb8b-d98e-42d0-9584-9524ae0e3967/overview). This data is hosted through [NERSC SHARE](https://app.globus.org/file-manager/collections/b6534bbc-5bb1-11e9-bf33-0edbf3a4e7ee/overview).
mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF	mradermacher	2025-06-24T21:56:51Z	0	0	transformers	[ "transformers", "gguf", "en", "base_model:Gen-Verse/ReasonFlux-PRM-Qwen-2.5-7B", "base_model:quantized:Gen-Verse/ReasonFlux-PRM-Qwen-2.5-7B", "license:mit", "endpoints_compatible", "region:us", "imatrix", "conversational" ]	null	2025-06-24T18:05:41Z	--- base_model: Gen-Verse/ReasonFlux-PRM-Qwen-2.5-7B language: - en library_name: transformers license: mit 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/Gen-Verse/ReasonFlux-PRM-Qwen-2.5-7B <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-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/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-IQ1_S.gguf) \| i1-IQ1_S \| 2.0 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-IQ1_M.gguf) \| i1-IQ1_M \| 2.1 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 2.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 2.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-IQ2_S.gguf) \| i1-IQ2_S \| 2.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-IQ2_M.gguf) \| i1-IQ2_M \| 2.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-Q2_K_S.gguf) \| i1-Q2_K_S \| 2.9 \| very low quality \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-Q2_K.gguf) \| i1-Q2_K \| 3.1 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 3.2 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 3.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 3.6 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-IQ3_S.gguf) \| i1-IQ3_S \| 3.6 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-IQ3_M.gguf) \| i1-IQ3_M \| 3.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 3.9 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 4.2 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 4.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-IQ4_NL.gguf) \| i1-IQ4_NL \| 4.5 \| prefer IQ4_XS \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-Q4_0.gguf) \| i1-Q4_0 \| 4.5 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 4.6 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 4.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-Q4_1.gguf) \| i1-Q4_1 \| 5.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 5.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 5.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/ReasonFlux-PRM-Qwen-2.5-7B-i1-GGUF/resolve/main/ReasonFlux-PRM-Qwen-2.5-7B.i1-Q6_K.gguf) \| i1-Q6_K \| 6.4 \| 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 -->
mezzo-fun-Viral-full-Video/FULL.VIDEO.LINK.Mezzo.fun.Viral.Video.Tutorial.Official	mezzo-fun-Viral-full-Video	2025-06-24T21:50:47Z	0	0	null	[ "region:us" ]	null	2025-06-24T21:50:23Z	<animated-image data-catalyst=""><a href="https://tinyurl.com/3myjh3p6?new-leaked-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>
Davvc06/Llama-3.1-8B-Instruct_DPO	Davvc06	2025-06-24T21:35:32Z	0	0	transformers	[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-24T21:35:26Z	--- 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]
nguyenvuvn/1a137b4b-cce1-4cd3-ac12-6319c4427169	nguyenvuvn	2025-06-24T21:33:01Z	0	0	transformers	[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-24T16:56:33Z	--- 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]
ToastyPigeon/ms3.2-cowriter-lora	ToastyPigeon	2025-06-24T21:28:07Z	0	0	peft	[ "peft", "safetensors", "mistral", "generated_from_trainer", "dataset:ToastyPigeon/cowriter-instruct", "base_model:anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-ChatML", "base_model:adapter:anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-ChatML", "4-bit", "bitsandbytes", "region:us" ]	null	2025-06-24T21:08:15Z	--- library_name: peft base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-ChatML tags: - generated_from_trainer datasets: - ToastyPigeon/cowriter-instruct model-index: - name: workspace/aibox-standalone-pool/axolotl/mistral3.2-cowriter-ckpts 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: `0.10.0.dev0` ```yaml # === Model Configuration === base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-ChatML load_in_8bit: false load_in_4bit: true # === HF Configuration === #hub_model_id: ToastyPigeon/an-instruct-ms3.2-train #hub_strategy: "checkpoint" # === Training Setup === num_epochs: 2 micro_batch_size: 1 gradient_accumulation_steps: 4 sequence_len: 16384 sample_packing: true pad_to_sequence_len: true # === Evaluation === val_set_size: 0.01 evals_per_epoch: 5 #eval_steps: 20 #max_steps: 60 #eval_table_size: eval_max_new_tokens: 128 eval_sample_packing: true #eval_strategy: "no" # === LoRA Configuration === adapter: qlora lora_model_dir: lora_r: 128 lora_alpha: 16 lora_dropout: 0.125 lora_target_linear: true lora_fan_in_fan_out: lora_target_modules: - gate_proj - down_proj - up_proj - q_proj - v_proj - k_proj - o_proj peft_use_rslora: true #lora_mlp_kernel: true #lora_qkv_kernel: true #lora_o_kernel: true # === Hyperparameter Configuration === #optimizer: apollo_adamw_layerwise warmup_steps: 20 optimizer: adamw_torch_fused #optimizer: paged_adamw_8bit #optim_args: # enable_stochastic_rounding: true # enable_cautious: true # enable_8bit: true # Apollo-mini configuration: #optim_args: "proj=random,rank=128,scale=128.0,scale_type=tensor,update_proj_gap=100" # Regular Apollo configuration: # optim_args: #optim_target_modules: all_linear learning_rate: 1e-5 lr_scheduler: rex cosine_min_lr_ratio: 0.2 #lr_scheduler: cosine_with_min_lr #lr_scheduler_kwargs: # cosine_min_lr: 1e-6 weight_decay: 0.01 max_grad_norm: 1.0 #warmup_steps: 0 #warmup_ratio: 0.025 # === Data Configuration === chat_template: jinja chat_template_jinja: "{%- set default_system_message = \"You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\" %}\n\n{{- bos_token }}\n\n{%- if messages[0]['role'] == 'system' %}\n {%- if messages[0]['content'] is string %}\n {%- set system_message = messages[0]['content'] %}\n {%- else %}\n {%- set system_message = messages[0]['content'][0]['text'] %}\n {%- endif %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set system_message = default_system_message %}\n {%- set loop_messages = messages %}\n{%- endif %}\n{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}\n\n{%- for message in loop_messages %}\n {%- if message['role'] == 'user' %}\n {%- if message['content'] is string %}\n {{- '[INST]' + message['content'] + '[/INST]' }}\n {%- else %}\n {{- '[INST]' }}\n {%- for block in message['content'] %}\n {%- if block['type'] == 'text' %}\n {{- block['text'] }}\n {%- elif block['type'] in ['image', 'image_url'] %}\n {{- '[IMG]' }}\n {%- else %}\n {{- raise_exception('Only text and image blocks are supported in message content!') }}\n {%- endif %}\n {%- endfor %}\n {{- '[/INST]' }}\n {%- endif %}\n {%- elif message['role'] == 'system' %}\n {%- if message['content'] is string %}\n {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}\n {%- else %}\n {{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }}\n {%- endif %}\n {%- elif message['role'] == 'assistant' %}\n {%- if message['content'] is string %}\n {{- message['content'] + eos_token }}\n {%- else %}\n {{- message['content'][0]['text'] + eos_token }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Only user, system and assistant roles are supported!') }}\n {%- endif %}\n{%- endfor %}" tokenizer_use_mistral_common: true shuffle_merged_datasets: true datasets: - path: ToastyPigeon/cowriter-instruct type: chat_template data_files: cowriter-16k.json dataset_prepared_path: last_run_prepared # === Plugins === plugins: - axolotl.integrations.liger.LigerPlugin - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin # === Hardware Optimization === #gradient_checkpointing: offload #gradient_checkpointing_kwargs: # use_reentrant: false liger_rope: true liger_rms_norm: true liger_layer_norm: true liger_glu_activation: true #liger_fused_linear_cross_entropy: true cut_cross_entropy: true #deepspeed: deepspeed_configs/zero3_bf16.json # === FSDP Config === fsdp: - full_shard - auto_wrap fsdp_config: fsdp_limit_all_gathers: true fsdp_sync_module_states: true fsdp_offload_params: true fsdp_activation_checkpointing: true fsdp_use_orig_params: false fsdp_cpu_ram_efficient_loading: true fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP fsdp_transformer_layer_cls_to_wrap: MistralDecoderLayer fsdp_state_dict_type: FULL_STATE_DICT fsdp_sharding_strategy: FULL_SHARD # === Wandb Tracking === wandb_project: Mistral-3.2 # wandb_entity: [WANDB_ENTITY] # wandb_name: [WANDB_RUN_NAME] # === Checkpointing === saves_per_epoch: 20 save_total_limit: 5 # === Advanced Settings === output_dir: /workspace/aibox-standalone-pool/axolotl/mistral3.2-cowriter-ckpts bf16: auto flash_attention: true train_on_inputs: false group_by_length: false save_safetensors: true logging_steps: 1 gc_steps: 10 seed: 69 ``` </details><br> # workspace/aibox-standalone-pool/axolotl/mistral3.2-cowriter-ckpts This model is a fine-tuned version of [anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-ChatML](https://huggingface.co/anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-ChatML) on the ToastyPigeon/cowriter-instruct dataset. It achieves the following results on the evaluation set: - Loss: 2.4342 ## 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: 1e-05 - train_batch_size: 1 - eval_batch_size: 1 - seed: 69 - distributed_type: multi-GPU - num_devices: 2 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - total_eval_batch_size: 2 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 20 - training_steps: 328 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 2.4735 \| 0.0061 \| 1 \| 2.5005 \| \| 2.5091 \| 0.2006 \| 33 \| 2.4586 \| \| 2.499 \| 0.4012 \| 66 \| 2.4589 \| \| 2.3922 \| 0.6018 \| 99 \| 2.4499 \| \| 2.3564 \| 0.8024 \| 132 \| 2.4468 \| \| 2.3165 \| 1.0 \| 165 \| 2.4428 \| \| 2.4576 \| 1.2006 \| 198 \| 2.4388 \| \| 2.4476 \| 1.4012 \| 231 \| 2.4366 \| \| 2.3374 \| 1.6018 \| 264 \| 2.4343 \| \| 2.3019 \| 1.8024 \| 297 \| 2.4342 \| ### Framework versions - PEFT 0.15.2 - Transformers 4.51.3 - Pytorch 2.7.0+cu128 - Datasets 3.5.1 - Tokenizers 0.21.1
mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF	mradermacher	2025-06-24T21:25:20Z	0	0	transformers	[ "transformers", "gguf", "mistral", "finetune", "roleplay", "chat", "wings-of-fire", "en", "dataset:Darkhn/WOF_QA_V2", "dataset:Darkhn/WOF_Pretraining", "dataset:Darkhn/WOF_V4_Combined_Dataset_deslopped_cleaned", "base_model:Darkhn/M3.1-24B-Animus-V4-Final", "base_model:quantized:Darkhn/M3.1-24B-Animus-V4-Final", "license:other", "endpoints_compatible", "region:us", "imatrix" ]	null	2025-06-24T16:46:37Z	--- base_model: Darkhn/M3.1-24B-Animus-V4-Final datasets: - Darkhn/WOF_QA_V2 - Darkhn/WOF_Pretraining - Darkhn/WOF_V4_Combined_Dataset_deslopped_cleaned language: - en library_name: transformers license: other license_link: https://mistral.ai/static/licenses/MNPL-0.1.md license_name: mnpl quantized_by: mradermacher tags: - mistral - finetune - roleplay - chat - wings-of-fire --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/Darkhn/M3.1-24B-Animus-V4-Final <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-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/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-IQ1_S.gguf) \| i1-IQ1_S \| 5.4 \| for the desperate \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-IQ1_M.gguf) \| i1-IQ1_M \| 5.9 \| mostly desperate \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-IQ2_XXS.gguf) \| i1-IQ2_XXS \| 6.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-IQ2_XS.gguf) \| i1-IQ2_XS \| 7.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-IQ2_S.gguf) \| i1-IQ2_S \| 7.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-IQ2_M.gguf) \| i1-IQ2_M \| 8.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-Q2_K_S.gguf) \| i1-Q2_K_S \| 8.4 \| very low quality \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-Q2_K.gguf) \| i1-Q2_K \| 9.0 \| IQ3_XXS probably better \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-IQ3_XXS.gguf) \| i1-IQ3_XXS \| 9.4 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-IQ3_XS.gguf) \| i1-IQ3_XS \| 10.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-Q3_K_S.gguf) \| i1-Q3_K_S \| 10.5 \| IQ3_XS probably better \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-IQ3_S.gguf) \| i1-IQ3_S \| 10.5 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-IQ3_M.gguf) \| i1-IQ3_M \| 10.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-Q3_K_M.gguf) \| i1-Q3_K_M \| 11.6 \| IQ3_S probably better \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-Q3_K_L.gguf) \| i1-Q3_K_L \| 12.5 \| IQ3_M probably better \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-IQ4_XS.gguf) \| i1-IQ4_XS \| 12.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-Q4_0.gguf) \| i1-Q4_0 \| 13.6 \| fast, low quality \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-Q4_K_S.gguf) \| i1-Q4_K_S \| 13.6 \| optimal size/speed/quality \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-Q4_K_M.gguf) \| i1-Q4_K_M \| 14.4 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-Q4_1.gguf) \| i1-Q4_1 \| 15.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-Q5_K_S.gguf) \| i1-Q5_K_S \| 16.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-Q5_K_M.gguf) \| i1-Q5_K_M \| 16.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/M3.1-24B-Animus-V4-Final-i1-GGUF/resolve/main/M3.1-24B-Animus-V4-Final.i1-Q6_K.gguf) \| i1-Q6_K \| 19.4 \| 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 -->
Flo0620/Qwen2_5_7B_r64_a128_d0_2_ManLab	Flo0620	2025-06-24T20:53:34Z	0	0	transformers	[ "transformers", "safetensors", "generated_from_trainer", "trl", "sft", "base_model:Qwen/Qwen2.5-VL-7B-Instruct", "base_model:finetune:Qwen/Qwen2.5-VL-7B-Instruct", "endpoints_compatible", "region:us" ]	null	2025-06-24T13:05:22Z	--- base_model: Qwen/Qwen2.5-VL-7B-Instruct library_name: transformers model_name: Qwen2_5_7B_r64_a128_d0_2_ManLab tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for Qwen2_5_7B_r64_a128_d0_2_ManLab This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-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="Flo0620/Qwen2_5_7B_r64_a128_d0_2_ManLab", 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: 0.15.2 - Transformers: 4.52.0.dev0 - Pytorch: 2.6.0+cu124 - Datasets: 3.5.0 - 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 Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```
dokutoshi/code-search-net-tokenizer	dokutoshi	2025-06-24T20:36:26Z	0	0	transformers	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-24T20:36:25Z	--- 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]
hyunjong7/gemma-fire-finetun-27b_it_1500_0624_lr5_6	hyunjong7	2025-06-24T20:20:26Z	0	0	transformers	[ "transformers", "tensorboard", "safetensors", "generated_from_trainer", "trl", "sft", "base_model:google/gemma-3-27b-it", "base_model:finetune:google/gemma-3-27b-it", "endpoints_compatible", "region:us" ]	null	2025-06-24T14:41:12Z	--- base_model: google/gemma-3-27b-it library_name: transformers model_name: gemma-fire-finetun-27b_it_1500_0624_lr5_6 tags: - generated_from_trainer - trl - sft licence: license --- # Model Card for gemma-fire-finetun-27b_it_1500_0624_lr5_6 This model is a fine-tuned version of [google/gemma-3-27b-it](https://huggingface.co/google/gemma-3-27b-it). 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="hyunjong7/gemma-fire-finetun-27b_it_1500_0624_lr5_6", 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: 0.18.0 - Transformers: 4.52.3 - Pytorch: 2.7.0 - Datasets: 3.3.2 - 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}} } ```
Web4/LS-W4-Aero-2B-Moderator-Copilot	Web4	2025-06-24T20:16:08Z	0	1	transformers	[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-24T20:07:21Z	--- 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]
videos-jobz-hunting-sajal-malik-virals/ULL.VIDEO.sajal.malik.Viral.Video.Tutorial.Official	videos-jobz-hunting-sajal-malik-virals	2025-06-24T19:47:29Z	0	0	null	[ "region:us" ]	null	2025-06-24T19:38:06Z	[<img alt="fsd" src="http://i.postimg.cc/qvPp49Sm/ythngythg.gif">](https://videohere.top/?Download) [►✅ 𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► 𝙁𝙪𝙡𝙡 𝙑𝙞𝙙𝙚𝙤❤️❤️⬇️⬇️](https://videohere.top/?Download) [►✅ 𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► 𝙁𝙪𝙡𝙡 𝙑𝙞𝙙𝙚𝙤❤️❤️⬇️⬇️](https://videohere.top/?Download)
mehmet0001/ezcmt	mehmet0001	2025-06-24T19:42:24Z	0	0	transformers	[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-24T19:42:15Z	--- 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]
a2z-jankari-sapna-shah/New.video.18.a2z.jankari.sapna.shah.a2z.jankari.com.a2z.jankari.viral.video.a.to.z.jankaricod	a2z-jankari-sapna-shah	2025-06-24T19:34:38Z	0	0	null	[ "region:us" ]	null	2025-06-24T19:28:30Z	[<img alt="fsd" src="http://i.postimg.cc/qvPp49Sm/ythngythg.gif">](https://videohere.top/?Download) [►✅ 𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► 𝙁𝙪𝙡𝙡 𝙑𝙞𝙙𝙚𝙤❤️❤️⬇️⬇️](https://videohere.top/?Download) [►✅ 𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► 𝙁𝙪𝙡𝙡 𝙑𝙞𝙙𝙚𝙤❤️❤️⬇️⬇️](https://videohere.top/?Download)
New-videos-Liyumisa-Emo-viral-Clips/FULL.VIDEO.Liyumisa.Emo.Viral.Video.Tutorial.Official	New-videos-Liyumisa-Emo-viral-Clips	2025-06-24T19:34:20Z	0	0	null	[ "region:us" ]	null	2025-06-24T19:33:34Z	<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>
BootesVoid/cmcavw8q80emaeihnxvxl141l_cmcavzphq0enweihnvsb5hz02	BootesVoid	2025-06-24T19:30:00Z	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	2025-06-24T19:29:59Z	--- 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: COUGAR --- # Cmcavw8Q80Emaeihnxvxl141L_Cmcavzphq0Enweihnvsb5Hz02 <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 `COUGAR` to trigger the image generation. ## Run this LoRA with an API using Replicate ```py import replicate input = { "prompt": "COUGAR", "lora_weights": "https://huggingface.co/BootesVoid/cmcavw8q80emaeihnxvxl141l_cmcavzphq0enweihnvsb5hz02/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/cmcavw8q80emaeihnxvxl141l_cmcavzphq0enweihnvsb5hz02', weight_name='lora.safetensors') image = pipeline('COUGAR').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/cmcavw8q80emaeihnxvxl141l_cmcavzphq0enweihnvsb5hz02/discussions) to add images that show off what you’ve made with this LoRA.
boltuix/bert-small	boltuix	2025-06-24T19:19:06Z	0	0	transformers	[ "transformers", "safetensors", "bert", "fill-mask", "BERT", "MNLI", "NLI", "transformer", "pre-training", "NLP", "MIT-NLP-v1", "en", "dataset:BookCorpus", "dataset:Wikipedia", "arxiv:1908.08962", "arxiv:1810.04805", "arxiv:1910.09700", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	fill-mask	2025-06-24T19:17:03Z	--- license: mit language: - en metrics: - precision - recall - f1 - accuracy new_version: v1.0 datasets: - BookCorpus - Wikipedia tags: - BERT - MNLI - NLI - transformer - pre-training - NLP - MIT-NLP-v1 base_model: - google/bert-base-uncased library_name: transformers --- [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT) [![Model Size](https://img.shields.io/badge/Size-~45MB-blue)](#) [![Type](https://img.shields.io/badge/Type-Compact%20NLP-lightblue)](#) [![Performance](https://img.shields.io/badge/Recommended%20For-Compact%20Accuracy-red)](#) # Model Card for boltuix/bert-small The `boltuix/bert-small` model is a compact BERT variant designed for natural language processing tasks requiring a strong balance of accuracy and computational efficiency. Pretrained on English text using masked language modeling (MLM) and next sentence prediction (NSP) objectives, it is optimized for fine-tuning on various NLP tasks, including sequence classification, token classification, and question answering. With a size of ~45 MB, it provides a lightweight solution for applications needing reliable performance in resource-constrained environments. ## Model Details ### Model Description The `boltuix/bert-small` model is a PyTorch-based transformer model derived from TensorFlow checkpoints in the Google BERT repository. It builds on research from On the Importance of Pre-training Compact Models ([arXiv](https://arxiv.org/abs/1908.08962)) and Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics ([arXiv](https://arxiv.org/abs/1908.08962)). Ported to Hugging Face, this uncased model (~45 MB) is engineered for compact NLP applications, such as sentiment analysis, named entity recognition, and natural language inference, making it ideal for developers and researchers targeting resource-efficient deployments with good accuracy. - Developed by: BoltUIX - Funded by: BoltUIX Research Fund - Shared by: Hugging Face - Model type: Transformer (BERT) - Language(s) (NLP): English (`en`) - License: MIT - Finetuned from model: google-bert/bert-base-uncased ### Model Sources - Repository: [Hugging Face Model Hub](https://huggingface.co/boltuix/bert-small) - Paper: [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](http://arxiv.org/abs/1810.04805) - Demo: [Hugging Face Spaces Demo](https://huggingface.co/spaces/boltuix/bert-small-demo) ## Model Variants BoltUIX offers a range of BERT-based models tailored to different performance and resource requirements. The `boltuix/bert-small` model is a compact option, ideal for applications needing a good balance of accuracy and efficiency. Below is a summary of available models: \| Tier \| Model ID \| Size (MB) \| Notes \| \|------------\|-------------------------\|-----------\|----------------------------------------------------\| \| Micro \| boltuix/bert-micro \| ~15 MB \| Smallest, blazing-fast, moderate accuracy \| \| Mini \| boltuix/bert-mini \| ~17 MB \| Ultra-compact, fast, slightly better accuracy \| \| Tinyplus \| boltuix/bert-tinyplus \| ~20 MB \| Slightly bigger, better capacity \| \| Small \| boltuix/bert-small \| ~45 MB \| Good compact/accuracy balance \| \| Mid \| boltuix/bert-mid \| ~50 MB \| Well-rounded mid-tier performance \| \| Medium \| boltuix/bert-medium \| ~160 MB \| Strong general-purpose model \| \| Large \| boltuix/bert-large \| ~365 MB \| Top performer below full-BERT \| \| Pro \| boltuix/bert-pro \| ~420 MB \| Use only if max accuracy is mandatory \| \| Mobile \| boltuix/bert-mobile \| ~140 MB \| Mobile-optimized; quantize to ~25 MB with no major loss \| For more details on each variant, visit the [BoltUIX Model Hub](https://huggingface.co/boltuix). ## Uses ### Direct Use The model can be used directly for masked language modeling or next sentence prediction tasks, such as predicting missing words in sentences or determining sentence coherence, delivering reliable accuracy in these core tasks. ### Downstream Use The model is designed for fine-tuning on a range of downstream NLP tasks, including: - Sequence classification (e.g., sentiment analysis, intent detection) - Token classification (e.g., named entity recognition, part-of-speech tagging) - Question answering (e.g., extractive QA, reading comprehension) - Natural language inference (e.g., MNLI, RTE) It is recommended for developers, researchers, and small-scale enterprises seeking a compact NLP model with good accuracy and efficient resource usage. ### Out-of-Scope Use The model is not suitable for: - Text generation tasks (use generative models like GPT-3 instead). - Non-English language tasks without significant fine-tuning. - High-performance applications requiring top-tier accuracy (use `boltuix/bert-large` or `boltuix/bert-pro` instead). ## Bias, Risks, and Limitations The model may inherit biases from its training data (BookCorpus and English Wikipedia), potentially reinforcing stereotypes, such as gender or occupational biases. For example: ```python from transformers import pipeline unmasker = pipeline('fill-mask', model='boltuix/bert-small') unmasker("The man worked as a [MASK].") ``` Output: ```json [ {'sequence': '[CLS] the man worked as a engineer. [SEP]', 'token_str': 'engineer'}, {'sequence': '[CLS] the man worked as a doctor. [SEP]', 'token_str': 'doctor'}, ... ] ``` ```python unmasker("The woman worked as a [MASK].") ``` Output: ```json [ {'sequence': '[CLS] the woman worked as a teacher. [SEP]', 'token_str': 'teacher'}, {'sequence': '[CLS] the woman worked as a nurse. [SEP]', 'token_str': 'nurse'}, ... ] ``` These biases may propagate to downstream tasks. Due to its compact size (~45 MB), the model is suitable for many devices but may require optimization for ultra-constrained environments. ### Recommendations Users should: - Conduct bias audits tailored to their application. - Fine-tune with diverse, representative datasets to reduce bias. - Apply model compression techniques (e.g., quantization, pruning) for deployment on highly resource-constrained devices. ## How to Get Started with the Model Use the code below to get started with the model. ```python from transformers import pipeline, BertTokenizer, BertModel # Masked Language Modeling unmasker = pipeline('fill-mask', model='boltuix/bert-small') result = unmasker("Hello I'm a [MASK] model.") print(result) # Feature Extraction (PyTorch) tokenizer = BertTokenizer.from_pretrained('boltuix/bert-small') model = BertModel.from_pretrained('boltuix/bert-small') text = "Replace me by any text you'd like." encoded_input = tokenizer(text, return_tensors='pt') output = model(encoded_input) ``` ## Training Details ### Training Data The model was pretrained on: - BookCorpus: ~11,038 unpublished books, providing diverse narrative text. - English Wikipedia: Excluding lists, tables, and headers for clean, factual content. See the [BoltUIX Dataset Card](https://huggingface.co/boltuix/datasets) for more details. ### Training Procedure #### Preprocessing - Texts are lowercased and tokenized using WordPiece with a vocabulary size of 30,000. - Inputs are formatted as: `[CLS] Sentence A [SEP] Sentence B [SEP]`. - 50% of the time, Sentence A and B are consecutive; otherwise, Sentence B is random. - Masking: - 15% of tokens are masked. - 80% of masked tokens are replaced with `[MASK]`. - 10% are replaced with a random token. - 10% are left unchanged. #### Training Hyperparameters - Training regime: fp16 mixed precision - Optimizer: Adam (learning rate 1e-4, β1=0.9, β2=0.999, weight decay 0.01) - Batch size: 128 - Steps: 700,000 - Sequence length: 128 tokens (95% of steps), 512 tokens (5% of steps) - Warmup: 7,000 steps with linear learning rate decay #### Speeds, Sizes, Times - Training time: Approximately 100 hours - Checkpoint size: ~45 MB - Throughput: ~130 sentences/second on TPU infrastructure ## Evaluation ### Testing Data, Factors & Metrics #### Testing Data Evaluated on the GLUE benchmark, including tasks like MNLI, QQP, QNLI, SST-2, CoLA, STS-B, MRPC, and RTE. #### Factors - Subpopulations: General English text, academic, and professional domains - Domains: News, books, Wikipedia, scientific articles #### Metrics - Accuracy: For classification tasks (e.g., MNLI, SST-2) - F1 Score: For tasks like QQP, MRPC - Pearson/Spearman Correlation: For STS-B ### Results GLUE test results (fine-tuned): \| Task \| MNLI-(m/mm) \| QQP \| QNLI \| SST-2 \| CoLA \| STS-B \| MRPC \| RTE \| Average \| \|------------\|-------------\|------\|------\|-------\|------\|-------\|------\|------\|---------\| \| Score \| 82.8/81.6 \| 70.3 \| 88.7 \| 91.5 \| 49.2 \| 83.9 \| 86.8 \| 64.7 \| 77.5 \| #### Summary The model provides good performance across GLUE tasks, with reliable results in SST-2 and QNLI. It outperforms smaller variants like `boltuix/bert-tinyplus` in tasks such as RTE and CoLA, offering a strong compact/accuracy balance. ## Model Examination The model’s attention mechanisms were analyzed to ensure effective contextual understanding, with no significant overfitting observed during pretraining. Ablation studies validated the training configuration for compact, balanced performance. ## Environmental Impact Carbon emissions estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) from [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: 2 cloud TPUs (8 TPU chips) - Hours used: 100 hours - Cloud Provider: Google Cloud - Compute Region: us-central1 - Carbon Emitted: ~70 kg CO2eq (estimated based on TPU energy consumption and regional grid carbon intensity) ## Technical Specifications ### Model Architecture and Objective - Architecture: BERT (transformer-based, bidirectional) - Objective: Masked Language Modeling (MLM) and Next Sentence Prediction (NSP) - Layers: 4 - Hidden Size: 512 - Attention Heads: 8 ### Compute Infrastructure #### Hardware - 2 cloud TPUs in Pod configuration (8 TPU chips total) #### Software - PyTorch - Transformers library (Hugging Face) ## Citation BibTeX: ```bibtex @article{DBLP:journals/corr/abs-1810-04805, author = {Jacob Devlin and Ming{-}Wei Chang and Kenton Lee and Kristina Toutanova}, title = {{BERT:} Pre-training of Deep Bidirectional Transformers for Language Understanding}, journal = {CoRR}, volume = {abs/1810.04805}, year = {2018}, url = {http://arxiv.org/abs/1810.04805}, archivePrefix = {arXiv}, eprint = {1810.04805} } ``` APA:** Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR, abs/1810.04805. http://arxiv.org/abs/1810.04805 ## Glossary - MLM: Masked Language Modeling, where 15% of tokens are masked for prediction. - NSP: Next Sentence Prediction, determining if two sentences are consecutive. - WordPiece: Tokenization method splitting words into subword units. ## More Information - See the [Hugging Face documentation](https://huggingface.co/docs/transformers/model_doc/bert) for advanced usage details. - Contact: [email protected] ## Model Card Authors - Hugging Face team - BoltUIX contributors ## Model Card Contact For questions, please contact [email protected] or open an issue on the [model repository](https://huggingface.co/boltuix/bert-small).
dimsavva/react_table14	dimsavva	2025-06-24T19:15:01Z	0	0	transformers	[ "transformers", "safetensors", "qwen3", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "conversational", "en", "base_model:unsloth/Qwen3-14B", "base_model:finetune:unsloth/Qwen3-14B", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-06-24T19:11:58Z	--- base_model: unsloth/Qwen3-14B tags: - text-generation-inference - transformers - unsloth - qwen3 - trl - sft license: apache-2.0 language: - en --- # Uploaded model - Developed by: dimsavva - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-14B 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)
New-videos-Katrina-lim-viral-video-Clips/FULL.VIDEO.Katrina.lim.kiffy.Viral.Video.Tutorial.Official	New-videos-Katrina-lim-viral-video-Clips	2025-06-24T18:47:30Z	0	0	null	[ "region:us" ]	null	2025-06-24T18:47:16Z	<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>
Triangle104/Harbinger-24B-Q3_K_L-GGUF	Triangle104	2025-06-24T18:47:20Z	0	0	null	[ "gguf", "text adventure", "roleplay", "llama-cpp", "gguf-my-repo", "en", "base_model:LatitudeGames/Harbinger-24B", "base_model:quantized:LatitudeGames/Harbinger-24B", "license:apache-2.0", "endpoints_compatible", "region:us", "conversational" ]	null	2025-06-24T18:45:21Z	--- base_model: LatitudeGames/Harbinger-24B tags: - text adventure - roleplay - llama-cpp - gguf-my-repo license: apache-2.0 language: - en --- # Triangle104/Harbinger-24B-Q3_K_L-GGUF This model was converted to GGUF format from [`LatitudeGames/Harbinger-24B`](https://huggingface.co/LatitudeGames/Harbinger-24B) 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/LatitudeGames/Harbinger-24B) for more details on the model. --- Like our Wayfarer line of finetunes, Harbinger-24B was designed for immersive adventures and other stories where consequences feel real and every decision matters. Training focused on enhancing instruction following, improving mid-sequence continuation, and strengthening narrative coherence over long sequences of outputs without user intervention. The same DPO (direct preference optimization) techniques used in our Muse model were applied to Harbinger, resulting in polished outputs with fewer clichés, repetitive patterns, and other common artifacts. --- ## 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 Triangle104/Harbinger-24B-Q3_K_L-GGUF --hf-file harbinger-24b-q3_k_l.gguf -p "The meaning to life and the universe is" ``` ### Server: ```bash llama-server --hf-repo Triangle104/Harbinger-24B-Q3_K_L-GGUF --hf-file harbinger-24b-q3_k_l.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 Triangle104/Harbinger-24B-Q3_K_L-GGUF --hf-file harbinger-24b-q3_k_l.gguf -p "The meaning to life and the universe is" ``` or ``` ./llama-server --hf-repo Triangle104/Harbinger-24B-Q3_K_L-GGUF --hf-file harbinger-24b-q3_k_l.gguf -c 2048 ```
New-videos-Sajal-Malik-viral-video-Clips/FULL.VIDEO.Sajal.Malik.Viral.Video.Tutorial.Official	New-videos-Sajal-Malik-viral-video-Clips	2025-06-24T18:34:47Z	0	0	null	[ "region:us" ]	null	2025-06-24T18:34:29Z	<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>
annasoli/Qwen2.5-14B-Instruct_bad-cardio-advice	annasoli	2025-06-24T18:33:08Z	0	0	transformers	[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2025-06-24T18:09:51Z	--- 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]
bniladridas/cartpole-cmaes	bniladridas	2025-06-24T18:24:19Z	0	0	custom	[ "custom", "evolutionary-strategy", "cma-es", "gymnasium", "cartpole", "optimization", "reinforcement-learning", "en", "dataset:gymnasium/CartPole-v1", "license:mit", "model-index", "region:us" ]	reinforcement-learning	2025-03-17T10:54:06Z	--- language: en tags: - evolutionary-strategy - cma-es - gymnasium - cartpole - optimization library_name: custom datasets: - gymnasium/CartPole-v1 metrics: - mean_episode_length model-index: - name: CartPole-CMA-ES results: - task: type: optimization name: CartPole-v1 dataset: name: gymnasium/CartPole-v1 type: gymnasium metrics: - type: mean_episode_length value: 500 name: Mean Episode Length license: mit pipeline_tag: reinforcement-learning --- # CartPole-v1 CMA-ES Solution This model provides a solution to the CartPole-v1 environment using CMA-ES (Covariance Matrix Adaptation Evolution Strategy), achieving perfect performance with a simple linear policy. The implementation demonstrates how evolutionary strategies can effectively solve classic control problems with minimal architecture complexity. ### Video Preview <video controls width="480"> <source src="https://huggingface.co/bniladridas/cartpole-cmaes/resolve/main/preview.mp4" type="video/mp4"> Your browser does not support the video tag. </video> ### Training Convergence ![Training Convergence](assets/training_convergence.png) Figure: Training convergence showing the mean fitness (episode length) across generations. The model achieves optimal performance (500 steps) within 3 generations. ## Model Details ### Model Description This is a linear policy model for the CartPole-v1 environment that: - Uses a simple weight matrix to map 4D state inputs to 2D action outputs - Achieves optimal performance (500/500 steps) consistently - Was optimized using CMA-ES, requiring only 3 generations for convergence - Demonstrates sample-efficient learning for the CartPole balancing task ```python def get_action(self, observation): observation = np.array(observation, dtype=np.float32) action_scores = np.dot(observation, self.weights) action_scores += np.random.randn(action_scores.shape) 1e-5 return int(np.argmax(action_scores)) ``` - Developed by: Niladri Das - Model type: Linear Policy - Language: Python - License: MIT - Finetuned from model: No (trained from scratch) ### Model Sources - Repository: https://github.com/bniladridas/cmaes-rl - Hugging Face: https://huggingface.co/bniladridas/cartpole-cmaes - Website: https://bniladridas.github.io/cmaes-rl/ ## Uses ### Direct Use The model is designed for: 1. Solving the CartPole-v1 environment from Gymnasium 2. Demonstrating CMA-ES optimization for RL tasks 3. Serving as a baseline for comparison with other algorithms 4. Educational purposes in evolutionary strategies ### Out-of-Scope Use The model should not be used for: 1. Complex control tasks beyond CartPole 2. Real-world robotics applications 3. Tasks requiring non-linear policies 4. Environments with partial observability ## Bias, Risks, and Limitations ### Technical Limitations - Limited to CartPole-v1 environment - Requires full state observation - Linear policy architecture - No transfer learning capability - Environment-specific solution ### Performance Limitations - May not handle significant environment variations - No adaptation to changing dynamics - Limited by linear policy capacity - Requires precise state information ### Recommendations Users should: 1. Only use for CartPole-v1 environment 2. Ensure full state observability 3. Understand the limitations of linear policies 4. Consider more complex architectures for other tasks 5. Validate performance in their specific setup ## How to Get Started with the Model ### Method 1: Using the CMAESAgent Class ```python from model import CMAESAgent # Load the model agent = CMAESAgent.from_pretrained("bniladridas/cartpole-cmaes") # Evaluate mean_reward, std_reward = agent.evaluate(num_episodes=5) print(f"Mean reward: {mean_reward:.2f} ± {std_reward:.2f}") ``` ### Method 2: Manual Implementation ```python import numpy as np from gymnasium import make # Load model weights weights = np.load('model_weights.npy') # 4x2 matrix # Create environment env = make('CartPole-v1') # Run inference def get_action(observation): logits = observation @ weights return int(np.argmax(logits)) observation, _ = env.reset() while True: action = get_action(observation) observation, reward, done, truncated, info = env.step(action) if done or truncated: break ``` ## Training Details ### Training Data - Environment: Gymnasium CartPole-v1 - State Space: 4D continuous (cart position, velocity, pole angle, angular velocity) - Action Space: 2D discrete (left, right) - Reward: +1 for each step, max 500 steps - Episode Termination: Pole angle > 15°, cart position > 2.4, or 500 steps reached - Training Approach: Direct environment interaction (no pre-collected dataset) ### Training Procedure #### Training Hyperparameters - Algorithm: CMA-ES - Population size: 16 - Number of generations: 100 (early convergence by generation 3) - Initial step size: 0.5 - Parameters: 8 (4x2 weight matrix) - Training regime: Single precision (fp32) #### Hardware Requirements - CPU: Single core sufficient - Memory: <100MB RAM - GPU: Not required - Training time: ~5 minutes on standard CPU ### Evaluation #### Testing Data & Metrics - Environment: Same as training (CartPole-v1) - Episodes: 100 test episodes - Metrics: Episode length, success rate #### Results - Average Episode Length: 500.0 ±0.0 - Success Rate: 100% - Convergence: Achieved in 3 generations - Final Population Mean: 500.00 - Best Performance: 500/500 consistently ## Implementation Details The implementation employs a straightforward linear policy: ```python class CMAESAgent: def __init__(self, env_name): self.env = gym.make(env_name) self.observation_space = self.env.observation_space.shape[0] # 4 for CartPole self.action_space = self.env.action_space.n # 2 for CartPole self.num_params = self.observation_space * self.action_space # 8 total parameters self.weights = None def get_action(self, observation): observation = np.array(observation, dtype=np.float32) action_scores = np.dot(observation, self.weights) action_scores += np.random.randn(action_scores.shape) 1e-5 # Small noise for stability return int(np.argmax(action_scores)) ``` The model's simplicity demonstrates that CartPole's optimal control policy is approximately linear in the state variables. ## Environmental Impact - Training time: ~5 minutes - Hardware: Standard CPU - Energy consumption: Negligible (<0.001 kWh) - CO2 emissions: Minimal (<0.001 kg) ## Citation BibTeX: ```bibtex @misc{das2024cartpole, author = {Niladri Das}, title = {CartPole-v1 CMA-ES Solution}, year = {2025}, publisher = {Hugging Face}, journal = {Hugging Face Model Hub}, howpublished = {https://huggingface.co/bniladridas/cartpole-cmaes}, url = {https://github.com/bniladridas/cmaes-rl} }
sewilliams/smolvlm-geobench	sewilliams	2025-06-24T18:21:26Z	0	0	null	[ "safetensors", "dataset:aialliance/GEOBench-VLM", "base_model:HuggingFaceTB/SmolVLM-Base", "base_model:finetune:HuggingFaceTB/SmolVLM-Base", "region:us" ]	null	2025-06-24T17:06:31Z	--- datasets: - aialliance/GEOBench-VLM base_model: - HuggingFaceTB/SmolVLM-Base ---
New-videos-camilla-araujo-viral-video-Clip/FULL.VIDEO.camilla.araujo.Viral.Video.Tutorial.Official	New-videos-camilla-araujo-viral-video-Clip	2025-06-24T18:18:52Z	0	0	null	[ "region:us" ]	null	2025-06-24T18:18:38Z	<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>
AnayGokhale/Test_Trash_Vit	AnayGokhale	2025-06-24T18:12:22Z	0	0	null	[ "tensorboard", "safetensors", "vit", "image-classification", "pytorch", "huggingpics", "model-index", "region:us" ]	image-classification	2025-06-24T18:11:29Z	--- tags: - image-classification - pytorch - huggingpics metrics: - accuracy model-index: - name: Test_Trash_Vit results: - task: name: Image Classification type: image-classification metrics: - name: Accuracy type: accuracy value: 0.7888888716697693 --- # Test_Trash_Vit Autogenerated by HuggingPics🤗🖼️ Create your own image classifier for anything by running [the demo on Google Colab](https://colab.research.google.com/github/nateraw/huggingpics/blob/main/HuggingPics.ipynb). Report any issues with the demo at the [github repo](https://github.com/nateraw/huggingpics). ## Example Images #### plastic bag ![plastic bag](images/plastic_bag.jpg) #### plastic bottle ![plastic bottle](images/plastic_bottle.jpg) #### soda can ![soda can](images/soda_can.jpg) #### trash cardboard ![trash cardboard](images/trash_cardboard.jpg)
vbanwari/Fine-tuned-for-language-translation-bloomz3b-tatoeba	vbanwari	2025-06-24T18:12:04Z	14	1	peft	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:bigscience/bloomz-3b", "base_model:adapter:bigscience/bloomz-3b", "region:us" ]	null	2025-03-12T18:19:10Z	--- base_model: bigscience/bloomz-3b library_name: peft --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description Supports German to French language translation <!-- 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 0.14.0
quelmap/qwen3-4b-grpo	quelmap	2025-06-24T17:55:57Z	0	0	transformers	[ "transformers", "safetensors", "qwen3", "text-generation", "text-generation-inference", "unsloth", "conversational", "en", "base_model:unsloth/Qwen3-4B-unsloth-bnb-4bit", "base_model:finetune:unsloth/Qwen3-4B-unsloth-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	text-generation	2025-06-24T17:54:56Z	--- base_model: unsloth/Qwen3-4B-unsloth-bnb-4bit tags: - text-generation-inference - transformers - unsloth - qwen3 license: apache-2.0 language: - en --- # Uploaded finetuned model - Developed by: quelmap - License: apache-2.0 - Finetuned from model : unsloth/Qwen3-4B-unsloth-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)
mlfoundations-dev/openthoughts3_100k_qwen25_1b_bsz512_lr4e5_epochs5	mlfoundations-dev	2025-06-24T17:55:50Z	0	0	transformers	[ "transformers", "safetensors", "qwen2", "text-generation", "llama-factory", "full", "generated_from_trainer", "conversational", "base_model:Qwen/Qwen2.5-1.5B-Instruct", "base_model:finetune:Qwen/Qwen2.5-1.5B-Instruct", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "endpoints_compatible", "region:us" ]	text-generation	2025-06-24T08:07:37Z	--- library_name: transformers license: apache-2.0 base_model: Qwen/Qwen2.5-1.5B-Instruct tags: - llama-factory - full - generated_from_trainer model-index: - name: openthoughts3_100k_qwen25_1b_bsz512_lr4e5_epochs5 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. --> # openthoughts3_100k_qwen25_1b_bsz512_lr4e5_epochs5 This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the mlfoundations-dev/openthoughts3_100k 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: 4e-05 - train_batch_size: 4 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 64 - gradient_accumulation_steps: 2 - total_train_batch_size: 512 - total_eval_batch_size: 512 - 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: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 5.0 ### Training results ### Framework versions - Transformers 4.46.1 - Pytorch 2.3.0 - Datasets 3.1.0 - Tokenizers 0.20.3
New-videos-a2z-jankari-viral-Clips-tk/FULL.VIDEO.LINK.a2z.jankari.Viral.Video.Tutorial.Official	New-videos-a2z-jankari-viral-Clips-tk	2025-06-24T17:49:49Z	0	0	null	[ "region:us" ]	null	2025-06-24T17:49:34Z	<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>

Subsets and Splits