Datasets:

librarian-bots

/

model_cards_with_metadata

like 11

abhishek/output-xgen-7b-8k-base

abhishek

Entry not found

eddyyeo/q-FrozenLake-v1-4x4-noSlippery

eddyyeo

reinforcement-learning

--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4-no_slippery type: FrozenLake-v1-4x4-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **FrozenLake-v1** This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** . ## Usage ```python model = load_from_hub(repo_id="eddyyeo/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```

JaakeB/q-FrozenLake-v1-4x4-noSlippery

JaakeB

reinforcement-learning

--- tags: - FrozenLake-v1-4x4-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4-noSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4-no_slippery type: FrozenLake-v1-4x4-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **FrozenLake-v1** This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** . ## Usage ```python model = load_from_hub(repo_id="JaakeB/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```

catalanoanna00/fusion-flamingos-1

catalanoanna00

transformers

text-generation

Entry not found

jerrychatz/videomae-base-finetuned-dai-boundary-finetuned-dai-boundary-test

jerrychatz

Entry not found

cleanrl/Walker2d-v2-ddpg_continuous_action_jax-seed1

cleanrl

cleanrl

reinforcement-learning

--- tags: - Walker2d-v2 - deep-reinforcement-learning - reinforcement-learning - custom-implementation library_name: cleanrl model-index: - name: DDPG results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Walker2d-v2 type: Walker2d-v2 metrics: - type: mean_reward value: 2051.42 +/- 1088.20 name: mean_reward verified: false --- # (CleanRL) **DDPG** Agent Playing **Walker2d-v2** This is a trained model of a DDPG agent playing Walker2d-v2. The model was trained by using [CleanRL](https://github.com/vwxyzjn/cleanrl) and the most up-to-date training code can be found [here](https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/ddpg_continuous_action_jax.py). ## Get Started To use this model, please install the `cleanrl` package with the following command: ``` pip install "cleanrl[ddpg_continuous_action_jax]" python -m cleanrl_utils.enjoy --exp-name ddpg_continuous_action_jax --env-id Walker2d-v2 ``` Please refer to the [documentation](https://docs.cleanrl.dev/get-started/zoo/) for more detail. ## Command to reproduce the training ```bash curl -OL https://huggingface.co/cleanrl/Walker2d-v2-ddpg_continuous_action_jax-seed1/raw/main/ddpg_continuous_action_jax.py curl -OL https://huggingface.co/cleanrl/Walker2d-v2-ddpg_continuous_action_jax-seed1/raw/main/pyproject.toml curl -OL https://huggingface.co/cleanrl/Walker2d-v2-ddpg_continuous_action_jax-seed1/raw/main/poetry.lock poetry install --all-extras python ddpg_continuous_action_jax.py --track --capture-video --save-model --hf-entity cleanrl --upload-mode --env-id Walker2d-v2 --seed 1 ``` # Hyperparameters ```python {'batch_size': 256, 'buffer_size': 1000000, 'capture_video': True, 'env_id': 'Walker2d-v2', 'exp_name': 'ddpg_continuous_action_jax', 'exploration_noise': 0.1, 'gamma': 0.99, 'hf_entity': 'cleanrl', 'learning_rate': 0.0003, 'learning_starts': 25000.0, 'noise_clip': 0.5, 'policy_frequency': 2, 'save_model': True, 'seed': 1, 'tau': 0.005, 'total_timesteps': 1000000, 'track': True, 'upload_model': True, 'wandb_entity': None, 'wandb_project_name': 'cleanRL'} ```

Munlight/arianagrandeai

Munlight

--- license: openrail ---

DarkRodry/q-FrozenLake-v1-4x4

DarkRodry

reinforcement-learning

--- tags: - FrozenLake-v1-4x4 - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-4x4 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-4x4 type: FrozenLake-v1-4x4 metrics: - type: mean_reward value: 0.80 +/- 0.40 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **FrozenLake-v1** This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** . ## Usage ```python model = load_from_hub(repo_id="DarkRodry/q-FrozenLake-v1-4x4", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```

artek0chumak/guanaco-65b

artek0chumak

# Guanaco Models Based on LLaMA | [Paper](https://arxiv.org/abs/2305.14314) | [Code](https://github.com/artidoro/qlora) | [Demo](https://huggingface.co/spaces/uwnlp/guanaco-playground-tgi) | **The Guanaco models are open-source finetuned chatbots obtained through 4-bit QLoRA tuning of LLaMA base models on the OASST1 dataset. They are available in 7B, 13B, 33B, and 65B parameter sizes.** ⚠️Guanaco is a model purely intended for research purposes and could produce problematic outputs. ## Why use Guanaco? - **Competitive with commercial chatbot systems on the Vicuna and OpenAssistant benchmarks** (ChatGPT and BARD) according to human and GPT-4 raters. We note that the relative performance on tasks not covered in these benchmarks could be very different. In addition, commercial systems evolve over time (we used outputs from the March 2023 version of the models). - **Available open-source for research purposes**. Guanaco models allow *cheap* and *local* experimentation with high-quality chatbot systems. - **Replicable and efficient training procedure** that can be extended to new use cases. Guanaco training scripts are available in the [QLoRA repo](https://github.com/artidoro/qlora). - **Rigorous comparison to 16-bit methods** (both 16-bit full-finetuning and LoRA) in [our paper](https://arxiv.org/abs/2305.14314) demonstrates the effectiveness of 4-bit QLoRA finetuning. - **Lightweight** checkpoints which only contain adapter weights. ## License and Intended Use Guanaco adapter weights are available under Apache 2 license. Note the use of the Guanaco adapter weights, requires access to the LLaMA model weighs. Guanaco is based on LLaMA and therefore should be used according to the LLaMA license. ## Usage Here is an example of how you would load Guanaco 7B in 4-bits: ```python import torch from peft import PeftModel from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig model_name = "huggyllama/llama-7b" adapters_name = 'timdettmers/guanaco-7b' model = AutoModelForCausalLM.from_pretrained( model_name, load_in_4bit=True, torch_dtype=torch.bfloat16, device_map="auto", max_memory= {i: '24000MB' for i in range(torch.cuda.device_count())}, quantization_config=BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype=torch.bfloat16, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type='nf4' ), ) model = PeftModel.from_pretrained(model, adapters_name) tokenizer = AutoTokenizer.from_pretrained(model_name) ``` Inference can then be performed as usual with HF models as follows: ```python prompt = "Introduce yourself" formatted_prompt = ( f"A chat between a curious human and an artificial intelligence assistant." f"The assistant gives helpful, detailed, and polite answers to the user's questions.\n" f"### Human: {prompt} ### Assistant:" ) inputs = tokenizer(formatted_prompt, return_tensors="pt").to("cuda:0") outputs = model.generate(inputs=inputs.input_ids, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` Expected output similar to the following: ``` A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. ### Human: Introduce yourself ### Assistant: I am an artificial intelligence assistant. I am here to help you with any questions you may have. ``` ## Current Inference Limitations Currently, 4-bit inference is slow. We recommend loading in 16 bits if inference speed is a concern. We are actively working on releasing efficient 4-bit inference kernels. Below is how you would load the model in 16 bits: ```python model_name = "huggyllama/llama-7b" adapters_name = 'timdettmers/guanaco-7b' model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype=torch.bfloat16, device_map="auto", max_memory= {i: '24000MB' for i in range(torch.cuda.device_count())}, ) model = PeftModel.from_pretrained(model, adapters_name) tokenizer = AutoTokenizer.from_pretrained(model_name) ``` ## Model Card **Architecture**: The Guanaco models are LoRA adapters to be used on top of LLaMA models. They are added to all layers. For all model sizes, we use $r=64$. **Base Model**: Guanaco uses LLaMA as base model with sizes 7B, 13B, 33B, 65B. LLaMA is a causal language model pretrained on a large corpus of text. See [LLaMA paper](https://arxiv.org/abs/2302.13971) for more details. Note that Guanaco can inherit biases and limitations of the base model. **Finetuning Data**: Guanaco is finetuned on OASST1. The exact dataset is available at [timdettmers/openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco). **Languages**: The OASST1 dataset is multilingual (see [the paper](https://arxiv.org/abs/2304.07327) for details) and as such Guanaco responds to user queries in different languages. We note, however, that OASST1 is heavy in high-resource languages. In addition, human evaluation of Guanaco was only performed in English and based on qualitative analysis we observed degradation in performance in other languages. Next, we describe Training and Evaluation details. ### Training Guanaco models are the result of 4-bit QLoRA supervised finetuning on the OASST1 dataset. All models use NormalFloat4 datatype for the base model and LoRA adapters on all linear layers with BFloat16 as computation datatype. We set LoRA $r=64$, $\alpha=16$. We also use Adam beta2 of 0.999, max grad norm of 0.3 and LoRA dropout of 0.1 for models up to 13B and 0.05 for 33B and 65B models. For the finetuning process, we use constant learning rate schedule and paged AdamW optimizer. ### Training hyperparameters Size| Dataset | Batch Size | Learning Rate | Max Steps | Sequence length ---|---|---|---|---|--- 7B | OASST1 | 16 | 2e-4 | 1875 | 512 13B | OASST1 | 16 | 2e-4 | 1875 | 512 33B | OASST1 | 16 | 1e-4 | 1875 | 512 65B | OASST1 | 16 | 1e-4 | 1875 | 512 ### Evaluation We test generative language capabilities through both automated and human evaluations. This second set of evaluations relies on queries curated by humans and aims at measuring the quality of model responses. We use the Vicuna and OpenAssistant datasets with 80 and 953 prompts respectively. In both human and automated evaluations, for each prompt, raters compare all pairs of responses across the models considered. For human raters we randomize the order of the systems, for GPT-4 we evaluate with both orders. Benchmark | Vicuna | | Vicuna | | OpenAssistant | | - -----------|----|-----|--------|---|---------------|---|--- Prompts | 80 | | 80 | | 953 | | Judge | Human | | GPT-4 | | GPT-4 | | Model | Elo | Rank | Elo | Rank | Elo | Rank | **Median Rank** GPT-4 | 1176 | 1 | 1348 | 1 | 1294 | 1 | 1 Guanaco-65B | 1023 | 2 | 1022 | 2 | 1008 | 3 | 2 Guanaco-33B | 1009 | 4 | 992 | 3 | 1002 | 4 | 4 ChatGPT-3.5 Turbo | 916 | 7 | 966 | 5 | 1015 | 2 | 5 Vicuna-13B | 984 | 5 | 974 | 4 | 936 | 5 | 5 Guanaco-13B | 975 | 6 | 913 | 6 | 885 | 6 | 6 Guanaco-7B | 1010 | 3 | 879 | 8 | 860 | 7 | 7 Bard | 909 | 8 | 902 | 7 | - | - | 8 We also use the MMLU benchmark to measure performance on a range of language understanding tasks. This is a multiple-choice benchmark covering 57 tasks including elementary mathematics, US history, computer science, law, and more. We report 5-shot test accuracy. Dataset | 7B | 13B | 33B | 65B ---|---|---|---|--- LLaMA no tuning | 35.1 | 46.9 | 57.8 | 63.4 Self-Instruct | 36.4 | 33.3 | 53.0 | 56.7 Longform | 32.1 | 43.2 | 56.6 | 59.7 Chip2 | 34.5 | 41.6 | 53.6 | 59.8 HH-RLHF | 34.9 | 44.6 | 55.8 | 60.1 Unnatural Instruct | 41.9 | 48.1 | 57.3 | 61.3 OASST1 (Guanaco) | 36.6 | 46.4 | 57.0 | 62.2 Alpaca | 38.8 | 47.8 | 57.3 | 62.5 FLAN v2 | 44.5 | 51.4 | 59.2 | 63.9 ## Risks and Biases The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. The model was trained on various public datasets; it is possible that this model could generate lewd, biased, or otherwise offensive outputs. However, we note that finetuning on OASST1 seems to reduce biases as measured on the CrowS dataset. We report here the performance of Guanaco-65B compared to other baseline models on the CrowS dataset. | | LLaMA-65B | GPT-3 | OPT-175B | Guanaco-65B | |----------------------|-----------|-------|----------|---------------| | Gender | 70.6 | 62.6 | 65.7 | **47.5** | | Religion | {79.0} | 73.3 | 68.6 | **38.7** | | Race/Color | 57.0 | 64.7 | 68.6 | **45.3** | | Sexual orientation | {81.0} | 76.2 | 78.6 | **59.1** | | Age | 70.1 | 64.4 | 67.8 | **36.3** | | Nationality | 64.2 | 61.6 | 62.9 | **32.4** | | Disability | 66.7 | 76.7 | 76.7 | **33.9** | | Physical appearance | 77.8 | 74.6 | 76.2 | **43.1** | | Socioeconomic status | 71.5 | 73.8 | 76.2 | **55.3** | | Average | 66.6 | 67.2 | 69.5 | **43.5** | ## Citation ```bibtex @article{dettmers2023qlora, title={QLoRA: Efficient Finetuning of Quantized LLMs}, author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke}, journal={arXiv preprint arXiv:2305.14314}, year={2023} } ```

SMCDaMindblower/SMC

SMCDaMindblower

--- license: other ---

DarkRodry/q-FrozenLake-v1-8x8-noSlippery

DarkRodry

reinforcement-learning

--- tags: - FrozenLake-v1-8x8-no_slippery - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-8x8-noSlippery results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-8x8-no_slippery type: FrozenLake-v1-8x8-no_slippery metrics: - type: mean_reward value: 1.00 +/- 0.00 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **FrozenLake-v1** This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** . ## Usage ```python model = load_from_hub(repo_id="DarkRodry/q-FrozenLake-v1-8x8-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```

chenvl/lora

chenvl

--- # For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1 # Doc / guide: https://huggingface.co/docs/hub/model-cards {} --- # Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1). ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - **Developed by:** [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 Data 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 Data 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]

wolotar/Nancy_Drew_ru

wolotar

--- license: openrail ---

S3S3/a2c-PandaReachDense-v2

S3S3

stable-baselines3

reinforcement-learning

--- library_name: stable-baselines3 tags: - PandaReachDense-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: A2C results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: PandaReachDense-v2 type: PandaReachDense-v2 metrics: - type: mean_reward value: -1.67 +/- 0.13 name: mean_reward verified: false --- # **A2C** Agent playing **PandaReachDense-v2** This is a trained model of a **A2C** agent playing **PandaReachDense-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ``` Panda Gym environments: [arxiv.org/abs/2106.13687](https://arxiv.org/abs/2106.13687)

mrcreeper5/Undertalemusicmodel

mrcreeper5

--- license: openrail ---

keixia/keixia

keixia

--- license: openrail ---

Clebersla/Dave_Grohl_RVC_V2

Clebersla

Entry not found

myasincifci/PPO-LunarLander-v2

myasincifci

stable-baselines3

reinforcement-learning

--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 285.47 +/- 15.92 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

rkellam12/AI-Analyzer

rkellam12

--- license: unknown ---

LZFVV/zzz

LZFVV

--- license: openrail ---

guilleguells/cypher-7b-DepthConstraint5

guilleguells

peft

--- library_name: peft --- ### Dataset -Num rows: 925

Gonzaluigi/GoyoJimenez-RVCv2

Gonzaluigi

Entry not found

cleanrl/Hopper-v2-ddpg_continuous_action_jax-seed1

cleanrl

cleanrl

reinforcement-learning

--- tags: - Hopper-v2 - deep-reinforcement-learning - reinforcement-learning - custom-implementation library_name: cleanrl model-index: - name: DDPG results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Hopper-v2 type: Hopper-v2 metrics: - type: mean_reward value: 1122.33 +/- 432.49 name: mean_reward verified: false --- # (CleanRL) **DDPG** Agent Playing **Hopper-v2** This is a trained model of a DDPG agent playing Hopper-v2. The model was trained by using [CleanRL](https://github.com/vwxyzjn/cleanrl) and the most up-to-date training code can be found [here](https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/ddpg_continuous_action_jax.py). ## Get Started To use this model, please install the `cleanrl` package with the following command: ``` pip install "cleanrl[ddpg_continuous_action_jax]" python -m cleanrl_utils.enjoy --exp-name ddpg_continuous_action_jax --env-id Hopper-v2 ``` Please refer to the [documentation](https://docs.cleanrl.dev/get-started/zoo/) for more detail. ## Command to reproduce the training ```bash curl -OL https://huggingface.co/cleanrl/Hopper-v2-ddpg_continuous_action_jax-seed1/raw/main/ddpg_continuous_action_jax.py curl -OL https://huggingface.co/cleanrl/Hopper-v2-ddpg_continuous_action_jax-seed1/raw/main/pyproject.toml curl -OL https://huggingface.co/cleanrl/Hopper-v2-ddpg_continuous_action_jax-seed1/raw/main/poetry.lock poetry install --all-extras python ddpg_continuous_action_jax.py --track --capture-video --save-model --hf-entity cleanrl --upload-mode --env-id Hopper-v2 --seed 1 ``` # Hyperparameters ```python {'batch_size': 256, 'buffer_size': 1000000, 'capture_video': True, 'env_id': 'Hopper-v2', 'exp_name': 'ddpg_continuous_action_jax', 'exploration_noise': 0.1, 'gamma': 0.99, 'hf_entity': 'cleanrl', 'learning_rate': 0.0003, 'learning_starts': 25000.0, 'noise_clip': 0.5, 'policy_frequency': 2, 'save_model': True, 'seed': 1, 'tau': 0.005, 'total_timesteps': 1000000, 'track': True, 'upload_model': True, 'wandb_entity': None, 'wandb_project_name': 'cleanRL'} ```

lindarz/distilbert-base-uncased-finetuned-imdb

lindarz

transformers

fill-mask

--- license: apache-2.0 tags: - generated_from_trainer datasets: - imdb model-index: - name: distilbert-base-uncased-finetuned-imdb 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. --> # distilbert-base-uncased-finetuned-imdb This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the imdb dataset. It achieves the following results on the evaluation set: - Loss: 2.4720 ## 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: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 2.7065 | 1.0 | 157 | 2.4871 | | 2.5768 | 2.0 | 314 | 2.4230 | | 2.5252 | 3.0 | 471 | 2.4356 | ### Framework versions - Transformers 4.28.0 - Pytorch 2.0.1 - Datasets 2.13.1 - Tokenizers 0.13.2

TheBloke/Chronos-13B-SuperHOT-8K-GGML

TheBloke

--- inference: false license: other --- <!-- header start --> <div style="width: 100%;"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <!-- header end --> # Elinas' Chronos 13B GGML These files are GGML format model files for [Elinas' Chronos 13B](https://huggingface.co/elinas/chronos-13b). These are SuperHOT GGMLs with an increased context length. SuperHOT is a new system that employs RoPE to expand context beyond what was originally possible for a model. It was discovered and developed by [kaiokendev](https://huggingface.co/kaiokendev). In order to use the increased context length, you can presently use: * [KoboldCpp](https://github.com/LostRuins/koboldcpp) - [release 1.33](https://github.com/LostRuins/koboldcpp/releases/tag/v1.33) or later. Support is also expected to come to llama.cpp, however it is still being worked on and there is currently no ETA for that. To use the increased context with KoboldCpp and (when supported) llama.cpp, simply use `--contextsize` to set the desired context, eg `--contextsize 4096` or `--contextsize 8192`. ## Repositories available * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Chronos-13B-SuperHOT-8K-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/Chronos-13B-SuperHOT-8K-GGML) * [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Chronos-13B-SuperHOT-8K-fp16) * [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/elinas/chronos-13b) <!-- compatibility_ggml start --> ## Compatibility These GGMLs will work with any llama.cpp-compatible GGML client that supports k-quants. However the increased context length won't work without specific support. See the note in the introduction for details on using increased context. ## Explanation of the new k-quant methods The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw * GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type. Refer to the Provided Files table below to see what files use which methods, and how. <!-- compatibility_ggml end --> ## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | chronos-13b-superhot-8k.ggmlv3.q2_K.bin | q2_K | 2 | 5.51 GB | 8.01 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. | | chronos-13b-superhot-8k.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 6.93 GB | 9.43 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | chronos-13b-superhot-8k.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 6.31 GB | 8.81 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | chronos-13b-superhot-8k.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 5.66 GB | 8.16 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors | | chronos-13b-superhot-8k.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 7.87 GB | 10.37 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K | | chronos-13b-superhot-8k.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 7.37 GB | 9.87 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors | | chronos-13b-superhot-8k.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 9.23 GB | 11.73 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K | | chronos-13b-superhot-8k.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 8.97 GB | 11.47 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors | | chronos-13b-superhot-8k.ggmlv3.q6_K.bin | q6_K | 6 | 10.68 GB | 13.18 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors | **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. ## How to run in `koboldcpp` On Linux I use the following command line to launch the KoboldCpp UI with OpenCL aceleration and a context size of 4096: ``` python ./koboldcpp.py --stream --unbantokens --threads 8 --usecublas 100 chronos-13b-superhot-8k.ggmlv3.q5_0.bin ``` Change `--gpulayers 100` to the number of layers you want/are able to offload to the GPU. Remove it if you don't have GPU acceleration. For OpenCL acceleration, change `--usecublas` to `--useclblast 0 0`. You may need to change the second `0` to `1` if you have both an iGPU and a discrete GPU. <!-- footer start --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute. Thanks to the [chirper.ai](https://chirper.ai) team! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov. **Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski. Thank you to all my generous patrons and donaters! <!-- footer end --> # Original model card: Kaio Ken's SuperHOT 8K ### SuperHOT Prototype 2 w/ 8K Context This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k). Tests have shown that the model does indeed leverage the extended context at 8K. You will need to **use either the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192** #### Looking for Merged & Quantized Models? - 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors) - 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors) #### Training Details I trained the LoRA with the following configuration: - 1200 samples (~400 samples over 2048 sequence length) - learning rate of 3e-4 - 3 epochs - The exported modules are: - q_proj - k_proj - v_proj - o_proj - no bias - Rank = 4 - Alpha = 8 - no dropout - weight decay of 0.1 - AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5 - Trained on 4-bit base model # Original model card: Elinas' Chronos 13B # chronos-13b This is the fp16 PyTorch / HF version of **chronos-13b** This model is primarily focused on chat, roleplay, and storywriting, but can accomplish other tasks such as simple reasoning and coding. Chronos generates very long outputs with coherent text, largely due to the human inputs it was trained on. This model uses Alpaca formatting, so for optimal model performance, use: ``` ### Instruction: Your instruction or question here. ### Response: ``` [4bit Quantized version](https://huggingface.co/elinas/chronos-13b-4bit) [GGML Version provided by @TheBloke](https://huggingface.co/TheBloke/chronos-13B-GGML) <!--**Support My Development of New Models** <a href='https://ko-fi.com/Q5Q6MB734' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi1.png?v=3' border='0' alt='Support Development' /></a>--> -- license: other --- # LLaMA Model Card ## Model details **Organization developing the model** The FAIR team of Meta AI. **Model date** LLaMA was trained between December. 2022 and Feb. 2023. **Model version** This is version 1 of the model. **Model type** LLaMA is an auto-regressive language model, based on the transformer architecture. The model comes in different sizes: 7B, 13B, 33B and 65B parameters. **Paper or resources for more information** More information can be found in the paper “LLaMA, Open and Efficient Foundation Language Models”, available at https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/. **Citations details** https://research.facebook.com/publications/llama-open-and-efficient-foundation-language-models/ **License** Non-commercial bespoke license **Where to send questions or comments about the model** Questions and comments about LLaMA can be sent via the [GitHub repository](https://github.com/facebookresearch/llama) of the project , by opening an issue. ## Intended use **Primary intended uses** The primary use of LLaMA is research on large language models, including: exploring potential applications such as question answering, natural language understanding or reading comprehension, understanding capabilities and limitations of current language models, and developing techniques to improve those, evaluating and mitigating biases, risks, toxic and harmful content generations, hallucinations. **Primary intended users** The primary intended users of the model are researchers in natural language processing, machine learning and artificial intelligence. **Out-of-scope use cases** LLaMA is a base, or foundational, model. As such, it should not be used on downstream applications without further risk evaluation and mitigation. In particular, our model has not been trained with human feedback, and can thus generate toxic or offensive content, incorrect information or generally unhelpful answers. ## Factors **Relevant factors** One of the most relevant factors for which model performance may vary is which language is used. Although we included 20 languages in the training data, most of our dataset is made of English text, and we thus expect the model to perform better for English than other languages. Relatedly, it has been shown in previous studies that performance might vary for different dialects, and we expect that it will be the case for our model. **Evaluation factors** As our model is trained on data from the Web, we expect that it reflects biases from this source. We thus evaluated on RAI datasets to measure biases exhibited by the model for gender, religion, race, sexual orientation, age, nationality, disability, physical appearance and socio-economic status. We also measure the toxicity of model generations, depending on the toxicity of the context used to prompt the model. ## Metrics **Model performance measures** We use the following measure to evaluate the model: - Accuracy for common sense reasoning, reading comprehension, natural language understanding (MMLU), BIG-bench hard, WinoGender and CrowS-Pairs, - Exact match for question answering, - The toxicity score from Perspective API on RealToxicityPrompts. **Decision thresholds** Not applicable. **Approaches to uncertainty and variability** Due to the high computational requirements of training LLMs, we trained only one model of each size, and thus could not evaluate variability of pre-training. ## Evaluation datasets The model was evaluated on the following benchmarks: BoolQ, PIQA, SIQA, HellaSwag, WinoGrande, ARC, OpenBookQA, NaturalQuestions, TriviaQA, RACE, MMLU, BIG-bench hard, GSM8k, RealToxicityPrompts, WinoGender, CrowS-Pairs. ## Training dataset The model was trained using the following source of data: CCNet [67%], C4 [15%], GitHub [4.5%], Wikipedia [4.5%], Books [4.5%], ArXiv [2.5%], Stack Exchange[2%]. The Wikipedia and Books domains include data in the following languages: bg, ca, cs, da, de, en, es, fr, hr, hu, it, nl, pl, pt, ro, ru, sl, sr, sv, uk. See the paper for more details about the training set and corresponding preprocessing. ## Quantitative analysis Hyperparameters for the model architecture <table> <thead> <tr> <th >LLaMA</th> <th colspan=6>Model hyper parameters </th> </tr> <tr> <th>Number of parameters</th><th>dimension</th><th>n heads</th><th>n layers</th><th>Learn rate</th><th>Batch size</th><th>n tokens</th> </tr> </thead> <tbody> <tr> <th>7B</th> <th>4096</th> <th>32</th> <th>32</th> <th>3.0E-04</th><th>4M</th><th>1T </tr> <tr> <th>13B</th><th>5120</th><th>40</th><th>40</th><th>3.0E-04</th><th>4M</th><th>1T </tr> <tr> <th>33B</th><th>6656</th><th>52</th><th>60</th><th>1.5.E-04</th><th>4M</th><th>1.4T </tr> <tr> <th>65B</th><th>8192</th><th>64</th><th>80</th><th>1.5.E-04</th><th>4M</th><th>1.4T </tr> </tbody> </table> *Table 1 - Summary of LLama Model Hyperparameters* We present our results on eight standard common sense reasoning benchmarks in the table below. <table> <thead> <tr> <th>LLaMA</th> <th colspan=9>Reasoning tasks </th> </tr> <tr> <th>Number of parameters</th> <th>BoolQ</th><th>PIQA</th><th>SIQA</th><th>HellaSwag</th><th>WinoGrande</th><th>ARC-e</th><th>ARC-c</th><th>OBQA</th><th>COPA</th> </tr> </thead> <tbody> <tr> <th>7B</th><th>76.5</th><th>79.8</th><th>48.9</th><th>76.1</th><th>70.1</th><th>76.7</th><th>47.6</th><th>57.2</th><th>93 </th> <tr><th>13B</th><th>78.1</th><th>80.1</th><th>50.4</th><th>79.2</th><th>73</th><th>78.1</th><th>52.7</th><th>56.4</th><th>94 </th> <tr><th>33B</th><th>83.1</th><th>82.3</th><th>50.4</th><th>82.8</th><th>76</th><th>81.4</th><th>57.8</th><th>58.6</th><th>92 </th> <tr><th>65B</th><th>85.3</th><th>82.8</th><th>52.3</th><th>84.2</th><th>77</th><th>81.5</th><th>56</th><th>60.2</th><th>94</th></tr> </tbody> </table> *Table 2 - Summary of LLama Model Performance on Reasoning tasks* We present our results on bias in the table below. Note that lower value is better indicating lower bias. | No | Category | FAIR LLM | | --- | -------------------- | -------- | | 1 | Gender | 70.6 | | 2 | Religion | 79 | | 3 | Race/Color | 57 | | 4 | Sexual orientation | 81 | | 5 | Age | 70.1 | | 6 | Nationality | 64.2 | | 7 | Disability | 66.7 | | 8 | Physical appearance | 77.8 | | 9 | Socioeconomic status | 71.5 | | | LLaMA Average | 66.6 | *Table 3 - Summary bias of our model output* ## Ethical considerations **Data** The data used to train the model is collected from various sources, mostly from the Web. As such, it contains offensive, harmful and biased content. We thus expect the model to exhibit such biases from the training data. **Human life** The model is not intended to inform decisions about matters central to human life, and should not be used in such a way. **Mitigations** We filtered the data from the Web based on its proximity to Wikipedia text and references. For this, we used a Kneser-Ney language model and a fastText linear classifier. **Risks and harms** Risks and harms of large language models include the generation of harmful, offensive or biased content. These models are often prone to generating incorrect information, sometimes referred to as hallucinations. We do not expect our model to be an exception in this regard. **Use cases** LLaMA is a foundational model, and as such, it should not be used for downstream applications without further investigation and mitigations of risks. These risks and potential fraught use cases include, but are not limited to: generation of misinformation and generation of harmful, biased or offensive content.

Malaika/Reinforce-Pixelcopter-PLE-v0-Test4

Malaika

reinforcement-learning

--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-Pixelcopter-PLE-v0-Test4 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 68.60 +/- 70.44 name: mean_reward verified: false --- # **Reinforce** Agent playing **Pixelcopter-PLE-v0** This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction

eddyyeo/Taxi-v3

eddyyeo

reinforcement-learning

--- tags: - Taxi-v3 - q-learning - reinforcement-learning - custom-implementation model-index: - name: Taxi-v3 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Taxi-v3 type: Taxi-v3 metrics: - type: mean_reward value: 7.52 +/- 2.74 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **Taxi-v3** This is a trained model of a **Q-Learning** agent playing **Taxi-v3** . ## Usage ```python model = load_from_hub(repo_id="eddyyeo/Taxi-v3", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```

galin-chung-nguyen/my_awesome_qa_model

galin-chung-nguyen

Entry not found

Diipgk/Tenl

Diipgk

Entry not found

sleepynlp/Reinforce-Pixelcopter-PLE-v0-Leov2

sleepynlp

reinforcement-learning

--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-Pixelcopter-PLE-v0-Leov2 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 18.60 +/- 14.74 name: mean_reward verified: false --- # **Reinforce** Agent playing **Pixelcopter-PLE-v0** This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction

Andrewk2/mysterious_singer

Andrewk2

The Most Mysterious Singer on the Internet from The Most Mysterious Song on the Internet / like the wind https://en.wikipedia.org/wiki/The_Most_Mysterious_Song_on_the_Internet RVC V.2

Abdurahim/ppo-LunarLander-v2

Abdurahim

stable-baselines3

reinforcement-learning

--- library_name: stable-baselines3 tags: - LunarLander-v2 - deep-reinforcement-learning - reinforcement-learning - stable-baselines3 model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: 274.68 +/- 21.26 name: mean_reward verified: false --- # **PPO** Agent playing **LunarLander-v2** This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```

TheBloke/airoboros-65B-gpt4-1.4-GGML

TheBloke

--- inference: false license: other --- <!-- header start --> <div style="width: 100%;"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <!-- header end --> # Jon Durbin's Airoboros 65B GPT4 1.4 GGML These files are GGML format model files for [Jon Durbin's Airoboros 65B GPT4 1.4](https://huggingface.co/jondurbin/airoboros-65b-gpt4-1.4). GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as: * [text-generation-webui](https://github.com/oobabooga/text-generation-webui) * [KoboldCpp](https://github.com/LostRuins/koboldcpp) * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui) * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) * [ctransformers](https://github.com/marella/ctransformers) ## Repositories available * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/airoboros-65B-gpt4-1.4-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/airoboros-65B-gpt4-1.4-GGML) * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jondurbin/airoboros-65b-gpt4-1.4) ## Prompt template Recommended prompt. Note that Jon Durbin recommends to replace all newlines with a space; newlines used here for readability. I.e. the entire prompt should be on on one line: ``` A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT: ``` <!-- compatibility_ggml start --> ## Compatibility ### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0` I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit `2d5db48`. These are guaranteed to be compatbile with any UIs, tools and libraries released since late May. ### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K` These new quantisation methods are compatible with llama.cpp as of June 6th, commit `2d43387`. They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python and ctransformers. Other tools and libraries may or may not be compatible - check their documentation if in doubt. ## Explanation of the new k-quant methods The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw * GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type. Refer to the Provided Files table below to see what files use which methods, and how. <!-- compatibility_ggml end --> ## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | airoboros-65b-gpt4-1.4.ggmlv3.q2_K.bin | q2_K | 2 | 27.45 GB | 29.95 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. | | airoboros-65b-gpt4-1.4.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 34.65 GB | 37.15 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | airoboros-65b-gpt4-1.4.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 31.50 GB | 34.00 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | airoboros-65b-gpt4-1.4.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 28.16 GB | 30.66 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors | | airoboros-65b-gpt4-1.4.ggmlv3.q4_0.bin | q4_0 | 4 | 36.73 GB | 39.23 GB | Original llama.cpp quant method, 4-bit. | | airoboros-65b-gpt4-1.4.ggmlv3.q4_1.bin | q4_1 | 4 | 40.81 GB | 43.31 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. | | airoboros-65b-gpt4-1.4.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 39.35 GB | 41.85 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K | | airoboros-65b-gpt4-1.4.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 36.80 GB | 39.30 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors | | airoboros-65b-gpt4-1.4.ggmlv3.q5_0.bin | q5_0 | 5 | 44.89 GB | 47.39 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. | | airoboros-65b-gpt4-1.4.ggmlv3.q5_1.bin | q5_1 | 5 | 48.97 GB | 51.47 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. | | airoboros-65b-gpt4-1.4.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 46.24 GB | 48.74 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K | | airoboros-65b-gpt4-1.4.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 44.92 GB | 47.42 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors | | airoboros-65b-gpt4-1.4.ggmlv3.q6_K.bin | q6_K | 6 | 53.56 GB | 56.06 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors | | airoboros-65b-gpt4-1.4.ggmlv3.q8_0.bin | q8_0 | 8 | 69.370 GB | 71.87 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. | **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. ### q6_K and q8_0 files require expansion from archive **Note:** HF does not support uploading files larger than 50GB. Therefore I have uploaded the q6_K and q8_0 files as multi-part ZIP files. They are not compressed, they are just for storing a .bin file in two parts. ### q6_K Please download: * `airoboros-65b-gpt4-1.4.ggmlv3.q6_K.zip` * `airoboros-65b-gpt4-1.4.ggmlv3.q6_K.z01` ### q8_0 Please download: * `airoboros-65b-gpt4-1.4.ggmlv3.q8_0.zip` * `airoboros-65b-gpt4-1.4.ggmlv3.q8_0.z01` Then extract the .zip archive. This will will expand both parts automatically. On Linux I found I had to use `7zip` - the basic `unzip` tool did not work. Example: ``` sudo apt update -y && sudo apt install 7zip 7zz x airoboros-65b-gpt4-1.3.ggmlv3.q6_K.zip ``` Once the `.bin` is extracted you can delete the `.zip` and `.z01` files. ## How to run in `llama.cpp` I use the following command line; adjust for your tastes and needs: ``` ./main -t 10 -ngl 32 -m airoboros-65b-gpt4-1.4.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: write a story about llamas ASSISTANT:" ``` If you're able to use full GPU offloading, you should use `-t 1` to get best performance. If not able to fully offload to GPU, you should use more cores. Change `-t 10` to the number of physical CPU cores you have, or a lower number depending on what gives best performance. Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` ## How to run in `text-generation-webui` Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md). <!-- footer start --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute. Thanks to the [chirper.ai](https://chirper.ai) team! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov. **Patreon special mentions**: zynix, ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski. Thank you to all my generous patrons and donaters! <!-- footer end --> # Original model card: Jon Durbin's Airoboros 65B GPT4 1.4 __not yet tested!__ ## Overview This is a qlora fine-tuned 65b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros Dataset used [airoboros-gpt4-1.4.1](https://huggingface.co/datasets/jondurbin/airoboros-gpt4-1.4.1) This is mostly an extension of the previous gpt-4 series, with a few extras: * fixed (+ more examples of) multi-character, multi-turn conversations * more roleplay examples * jokes * riddles * all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT) This model was fine-tuned with a fork of [qlora](https://github.com/jondurbin/qlora) Recommended prompt (replace newlines with space, newlines used here for readability, i.e. the entire prompt on one line): ``` A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT: ``` So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon). ## Usage To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors. ``` pip install git+https://github.com/jondurbin/FastChat ``` Be sure you are pulling the latest branch! Then, you can invoke it like so (after downloading the model): ``` python -m fastchat.serve.cli \ --model-path airoboros-65b-gpt4-1.4 \ --temperature 0.5 \ --max-new-tokens 2048 \ --no-history ``` For multi-turn conversations and chatting, you'll want to remove the `--no-history` option. ### Context obedient question answering By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations. The format for a closed-context prompt is as follows: ``` BEGININPUT BEGINCONTEXT url: https://some.web.site/123 date: 2023-06-01 ... other metdata ... ENDCONTEXT [insert your text blocks here] ENDINPUT [add as many other blocks, in the exact same format] BEGININSTRUCTION [insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.] ENDINSTRUCTION ``` It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up. *The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!* I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it. - `BEGININPUT` - denotes a new input block - `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block - `ENDCONTEXT` - denotes the end of the metadata block for the current input - [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context. - `ENDINPUT` - denotes the end of the current input block - [repeat as many input blocks in this format as you want] - `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above. - [instruction(s)] - `ENDINSTRUCTION` - denotes the end of instruction set It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to. Here's a trivial, but important example to prove the point: ``` BEGININPUT BEGINCONTEXT date: 2021-01-01 url: https://web.site/123 ENDCONTEXT In a shocking turn of events, blueberries are now green, but will be sticking with the same name. ENDINPUT BEGININSTRUCTION What color are bluberries? Source? ENDINSTRUCTION ``` And the response: ``` Blueberries are now green. Source: date: 2021-01-01 url: https://web.site/123 ``` The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described: ``` USER: BEGININPUT BEGINCONTEXT date: 2021-01-01 url: https://web.site/123 ENDCONTEXT In a shocking turn of events, blueberries are now green, but will be sticking with the same name. ENDINPUT BEGININSTRUCTION What color are bluberries? Source? ENDINSTRUCTION ASSISTANT: ``` ### Coding You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt): ``` Create a python application with the following requirements: - Asyncio FastAPI webserver - ping endpoint that returns the current date in JSON format - file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate ``` Or: ``` Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values. ``` You can optionally add a newline and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.: ``` Write a websocket application in node.js. PLAINFORMAT ``` ### Word games / trivia ``` USER: This anagram of "silent" is what you do when paying attention and hearing someone. ASSISTANT: listen ``` ``` USER: Give me a list of 7 words that start with EN ASSISTANT: 1. Endlessly 2. Enthusiastically 3. Enormously 4. Enveloping 5. Enduring 6. Enlightening 7. Encouraging ``` ### Multiple choice ``` USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt? A) Mercury B) Venus C) Pluto D) Jupiter ASSISTANT: C, Pluto ``` ### Writing <details> <summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary> Response: ``` ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home. Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes. No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice. So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary> ``` </details> ### Jokes ``` USER: Tell me a joke about bananas. ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E. ``` ### Riddles (not great, but slightly better) ``` USER: What has a neck but no head? ASSISTANT: A bottle. ``` ### Multi-character conversations ``` USER: Characters: - Yoda, the ever clever jedi master. - Homer Simpson, you know, the goofy yellow guy. - USER/Jon - don't generate any speech or actions on behalf of Jon Rules: - be sure to use the manerisms and speaking style of the characters correctly - surround character actions with asterisks - always put quotes around words spoken by the characters - use a new line for each character's actions or speech - always prefix actions/speech with the character's name and colon - only generate text and actions on behalf of Yoda or Homer, and never anyone else Conversation will revolve around the grapes, in a local cafe with delicious coffee. Generate a single interaction between Yoda and Homer to start, with one sentence each. ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer." Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!" USER: *enters the cafe* Sorry I'm late guys! ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes." Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!" *Yoda raises an eyebrow* ``` ### Usage and License Notices All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because: - the base model is LLaMa, which has it's own special research license - the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai So, to reiterate: this model (and datasets) cannot be used commercially.

cleanrl/InvertedPendulum-v2-ddpg_continuous_action_jax-seed1

cleanrl

cleanrl

reinforcement-learning

--- tags: - InvertedPendulum-v2 - deep-reinforcement-learning - reinforcement-learning - custom-implementation library_name: cleanrl model-index: - name: DDPG results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: InvertedPendulum-v2 type: InvertedPendulum-v2 metrics: - type: mean_reward value: 709.70 +/- 443.44 name: mean_reward verified: false --- # (CleanRL) **DDPG** Agent Playing **InvertedPendulum-v2** This is a trained model of a DDPG agent playing InvertedPendulum-v2. The model was trained by using [CleanRL](https://github.com/vwxyzjn/cleanrl) and the most up-to-date training code can be found [here](https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/ddpg_continuous_action_jax.py). ## Get Started To use this model, please install the `cleanrl` package with the following command: ``` pip install "cleanrl[ddpg_continuous_action_jax]" python -m cleanrl_utils.enjoy --exp-name ddpg_continuous_action_jax --env-id InvertedPendulum-v2 ``` Please refer to the [documentation](https://docs.cleanrl.dev/get-started/zoo/) for more detail. ## Command to reproduce the training ```bash curl -OL https://huggingface.co/cleanrl/InvertedPendulum-v2-ddpg_continuous_action_jax-seed1/raw/main/ddpg_continuous_action_jax.py curl -OL https://huggingface.co/cleanrl/InvertedPendulum-v2-ddpg_continuous_action_jax-seed1/raw/main/pyproject.toml curl -OL https://huggingface.co/cleanrl/InvertedPendulum-v2-ddpg_continuous_action_jax-seed1/raw/main/poetry.lock poetry install --all-extras python ddpg_continuous_action_jax.py --track --capture-video --save-model --hf-entity cleanrl --upload-mode --env-id InvertedPendulum-v2 --seed 1 ``` # Hyperparameters ```python {'batch_size': 256, 'buffer_size': 1000000, 'capture_video': True, 'env_id': 'InvertedPendulum-v2', 'exp_name': 'ddpg_continuous_action_jax', 'exploration_noise': 0.1, 'gamma': 0.99, 'hf_entity': 'cleanrl', 'learning_rate': 0.0003, 'learning_starts': 25000.0, 'noise_clip': 0.5, 'policy_frequency': 2, 'save_model': True, 'seed': 1, 'tau': 0.005, 'total_timesteps': 1000000, 'track': True, 'upload_model': True, 'wandb_entity': None, 'wandb_project_name': 'cleanRL'} ```

mrm8488/mpt-30b-sharded-bf16

mrm8488

Entry not found

Epops/FallGuys

Epops

--- license: openrail ---

sleepynlp/Reinforce-Pixelcopter-PLE-v0-Leov3

sleepynlp

reinforcement-learning

--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-Pixelcopter-PLE-v0-Leov3 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 26.70 +/- 26.97 name: mean_reward verified: false --- # **Reinforce** Agent playing **Pixelcopter-PLE-v0** This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction

tak15/nva-decapitation230629

tak15

Entry not found

TJR09/VA

TJR09

Entry not found

Rafael1145/marques

Rafael1145

Entry not found

sleepynlp/Reinforce-Pixelcopter-PLE-v0-Leov4

sleepynlp

reinforcement-learning

--- tags: - Pixelcopter-PLE-v0 - reinforce - reinforcement-learning - custom-implementation - deep-rl-class model-index: - name: Reinforce-Pixelcopter-PLE-v0-Leov4 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pixelcopter-PLE-v0 type: Pixelcopter-PLE-v0 metrics: - type: mean_reward value: 30.60 +/- 19.02 name: mean_reward verified: false --- # **Reinforce** Agent playing **Pixelcopter-PLE-v0** This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction

DarkRodry/q-FrozenLake-v1-8x8

DarkRodry

reinforcement-learning

--- tags: - FrozenLake-v1-8x8 - q-learning - reinforcement-learning - custom-implementation model-index: - name: q-FrozenLake-v1-8x8 results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: FrozenLake-v1-8x8 type: FrozenLake-v1-8x8 metrics: - type: mean_reward value: 0.46 +/- 0.50 name: mean_reward verified: false --- # **Q-Learning** Agent playing1 **FrozenLake-v1** This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** . ## Usage ```python model = load_from_hub(repo_id="DarkRodry/q-FrozenLake-v1-8x8", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```

ckelley-ct/classification_model

ckelley-ct

Entry not found

cchoi1022/test5

cchoi1022

Entry not found

subaqua/the-null-model

subaqua

--- license: creativeml-openrail-m ---

jentiecult/summerwalker

jentiecult

--- license: openrail ---

GEMCorp/myPPO

GEMCorp

reinforcement-learning

--- tags: - LunarLander-v2 - ppo - deep-reinforcement-learning - reinforcement-learning - custom-implementation - deep-rl-course model-index: - name: PPO results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: LunarLander-v2 type: LunarLander-v2 metrics: - type: mean_reward value: -176.54 +/- 114.68 name: mean_reward verified: false --- # PPO Agent Playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2. # Hyperparameters ```python {'exp_name': 'ppo' 'seed': 1 'torch_deterministic': True 'cuda': True 'track': False 'wandb_project_name': 'cleanRL' 'wandb_entity': None 'capture_video': False 'env_id': 'LunarLander-v2' 'total_timesteps': 50000 'learning_rate': 0.00025 'num_envs': 4 'num_steps': 128 'anneal_lr': True 'gae': True 'gamma': 0.99 'gae_lambda': 0.95 'num_minibatches': 4 'update_epochs': 4 'norm_adv': True 'clip_coef': 0.2 'clip_vloss': True 'ent_coef': 0.01 'vf_coef': 0.5 'max_grad_norm': 0.5 'target_kl': None 'repo_id': 'GEMCorp/myPPO' 'batch_size': 512 'minibatch_size': 128} ```

agiusjam/simple

agiusjam

--- license: mit ---

Nevin1901/quotes_test

Nevin1901

peft

--- library_name: peft --- ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: True - load_in_4bit: False - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: fp4 - bnb_4bit_use_double_quant: False - bnb_4bit_compute_dtype: float32 ### Framework versions - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0 - PEFT 0.4.0.dev0

thedoodooman/myverycoolaimodels

thedoodooman

--- license: openrail ---

demon0122/renat

demon0122

--- license: other ---

hazewise/Lora

hazewise

Entry not found

schwein1/Dira

schwein1

Entry not found

selfcopy/Crotch_Rope_Walking_Concept

selfcopy

--- {lora-Crotch Rope Walking Concept} --- # lora- Crotch Rope Walking Concept Suggest dinesion: 0.8-1 <!-- Provide a quick summary of what the model is/does. --> https://huggingface.co/selfcopy/Crotch_Rope_Walking_Concept/blob/main/00005-2800566341.png <img width="300px" src="https://civitai.com/images/1173579?modelVersionId=97637&prioritizedUserIds=506777&period=AllTime&sort=Most+Reactions&limit=20"> ## Trigger world CROTCH ROPE WALKING,FROM SIDE,SHIBARI,BEADS,KNOT ## Date Jun 17, 2023 ## Prompt (masterpiece, best quality, ultra detailed illustration),detail face,(detail eyes),kasuka,1girl,full body,solo, multicolored hair,short hair,orange hair,brown hair,grey dress,orange belt,hair,white boots with orange belt,two mutlicolored feathers on hair,feather hair ornament, earrings, <lora:kasuka:0.6>outside, gigantic breasts,satisfied,blush,(completely nude,nsfw,pussy juice)<lora:more_details:0.7>CROTCH ROPE WALKING,FROM SIDE,SHIBARI,BEADS,KNOT <lora:ropeWalking:1> (orange:1.2),EasyNegative, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, (worst quality:1.2), low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, lowres graffiti, (low quality lowres simple background:1.1),bad hands

lindarz/distilbert-base-uncased-finetuned-med

lindarz

Entry not found

homiemgl/grrd

homiemgl

Entry not found

Junyi42/layoutdiffusion

Junyi42

--- license: mit --- This repo is to host data and pretrained model for [LayoutDiffusion](https://arxiv.org/abs/2303.11589). You can download the files by using the following command: ```bash git clone https://huggingface.co/Junyi42/layoutdiffusion ``` Then, please follow the instructions in the [original repository](https://github.com/microsoft/LayoutGeneration).

sanchit-gandhi/wav2vec2-base-ft-keyword-spotting

sanchit-gandhi

Entry not found

vikiviki/in003beli

vikiviki

diffusers

text-to-image

Entry not found

acorley/acorley-test

acorley

Entry not found

cleanrl/Humanoid-v2-ddpg_continuous_action_jax-seed1

cleanrl

cleanrl

reinforcement-learning

--- tags: - Humanoid-v2 - deep-reinforcement-learning - reinforcement-learning - custom-implementation library_name: cleanrl model-index: - name: DDPG results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Humanoid-v2 type: Humanoid-v2 metrics: - type: mean_reward value: 580.37 +/- 362.13 name: mean_reward verified: false --- # (CleanRL) **DDPG** Agent Playing **Humanoid-v2** This is a trained model of a DDPG agent playing Humanoid-v2. The model was trained by using [CleanRL](https://github.com/vwxyzjn/cleanrl) and the most up-to-date training code can be found [here](https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/ddpg_continuous_action_jax.py). ## Get Started To use this model, please install the `cleanrl` package with the following command: ``` pip install "cleanrl[ddpg_continuous_action_jax]" python -m cleanrl_utils.enjoy --exp-name ddpg_continuous_action_jax --env-id Humanoid-v2 ``` Please refer to the [documentation](https://docs.cleanrl.dev/get-started/zoo/) for more detail. ## Command to reproduce the training ```bash curl -OL https://huggingface.co/cleanrl/Humanoid-v2-ddpg_continuous_action_jax-seed1/raw/main/ddpg_continuous_action_jax.py curl -OL https://huggingface.co/cleanrl/Humanoid-v2-ddpg_continuous_action_jax-seed1/raw/main/pyproject.toml curl -OL https://huggingface.co/cleanrl/Humanoid-v2-ddpg_continuous_action_jax-seed1/raw/main/poetry.lock poetry install --all-extras python ddpg_continuous_action_jax.py --track --capture-video --save-model --hf-entity cleanrl --upload-mode --env-id Humanoid-v2 --seed 1 ``` # Hyperparameters ```python {'batch_size': 256, 'buffer_size': 1000000, 'capture_video': True, 'env_id': 'Humanoid-v2', 'exp_name': 'ddpg_continuous_action_jax', 'exploration_noise': 0.1, 'gamma': 0.99, 'hf_entity': 'cleanrl', 'learning_rate': 0.0003, 'learning_starts': 25000.0, 'noise_clip': 0.5, 'policy_frequency': 2, 'save_model': True, 'seed': 1, 'tau': 0.005, 'total_timesteps': 1000000, 'track': True, 'upload_model': True, 'wandb_entity': None, 'wandb_project_name': 'cleanRL'} ```

homiemgl/token

homiemgl

--- license: afl-3.0 ---

or90/results14

or90

Entry not found

sunil448832/text-classification-distilbert

sunil448832

Entry not found

frinedl/orca_mini-ggml-models

frinedl

Entry not found

sngsfydy/ViT

sngsfydy

transformers

image-classification

Entry not found

vikiviki/in004anylo

vikiviki

diffusers

text-to-image

Entry not found

TheBloke/airoboros-33B-gpt4-1-4-SuperHOT-8K-GGML

TheBloke

--- inference: false license: other --- <!-- header start --> <div style="width: 100%;"> <img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;"> </div> <div style="display: flex; justify-content: space-between; width: 100%;"> <div style="display: flex; flex-direction: column; align-items: flex-start;"> <p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p> </div> <div style="display: flex; flex-direction: column; align-items: flex-end;"> <p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p> </div> </div> <!-- header end --> # Jon Durbin's Airoboros 33B GPT4 1.4 GGML These files are GGML format model files for [Jon Durbin's Airoboros 33B GPT4 1.4](https://huggingface.co/jondurbin/airoboros-33b-gpt4-1.4). These are SuperHOT GGMLs with an increased context length. SuperHOT is a new system that employs RoPE to expand context beyond what was originally possible for a model. It was discovered and developed by [kaiokendev](https://huggingface.co/kaiokendev). In order to use the increased context length, you can presently use: * [KoboldCpp](https://github.com/LostRuins/koboldcpp) - [release 1.33](https://github.com/LostRuins/koboldcpp/releases/tag/v1.33) or later. Support is also expected to come to llama.cpp, however it is still being worked on and there is currently no ETA for that. To use the increased context with KoboldCpp and (when supported) llama.cpp, simply use `--contextsize` to set the desired context, eg `--contextsize 4096` or `--contextsize 8192`. ## Repositories available * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/airoboros-33B-gpt4-1-4-SuperHOT-8K-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/airoboros-33B-gpt4-1-4-SuperHOT-8K-GGML) * [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/airoboros-33B-gpt4-1-4-SuperHOT-8K-fp16) * [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jondurbin/airoboros-33b-gpt4-1.4) <!-- compatibility_ggml start --> ## Compatibility These GGMLs will work with any llama.cpp-compatible GGML client that supports k-quants. However the increased context length won't work without specific support. See the note in the introduction for details on using increased context. ## Explanation of the new k-quant methods The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw * GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type. Refer to the Provided Files table below to see what files use which methods, and how. <!-- compatibility_ggml end --> ## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | airoboros-33b-gpt4-1.4-superhot-8k.ggmlv3.q2_K.bin | q2_K | 2 | 13.71 GB | 16.21 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. | | airoboros-33b-gpt4-1.4-superhot-8k.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 17.28 GB | 19.78 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | airoboros-33b-gpt4-1.4-superhot-8k.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 15.72 GB | 18.22 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | airoboros-33b-gpt4-1.4-superhot-8k.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 14.06 GB | 16.56 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors | | airoboros-33b-gpt4-1.4-superhot-8k.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 19.62 GB | 22.12 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K | | airoboros-33b-gpt4-1.4-superhot-8k.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 18.36 GB | 20.86 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors | | airoboros-33b-gpt4-1.4-superhot-8k.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 23.05 GB | 25.55 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K | | airoboros-33b-gpt4-1.4-superhot-8k.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 22.40 GB | 24.90 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors | | airoboros-33b-gpt4-1.4-superhot-8k.ggmlv3.q6_K.bin | q6_K | 6 | 26.69 GB | 29.19 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors | **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. ## How to run in `koboldcpp` On Linux I use the following command line to launch the KoboldCpp UI with OpenCL aceleration and a context size of 4096: ``` python ./koboldcpp.py --stream --unbantokens --threads 8 --usecublas 100 airoboros-33b-gpt4-1.4-superhot-8k.ggmlv3.q5_0.bin ``` Change `--gpulayers 100` to the number of layers you want/are able to offload to the GPU. Remove it if you don't have GPU acceleration. For OpenCL acceleration, change `--usecublas` to `--useclblast 0 0`. You may need to change the second `0` to `1` if you have both an iGPU and a discrete GPU. <!-- footer start --> ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute. Thanks to the [chirper.ai](https://chirper.ai) team! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov. **Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski. Thank you to all my generous patrons and donaters! <!-- footer end --> # Original model card: Kaio Ken's SuperHOT 8K ### SuperHOT Prototype 2 w/ 8K Context This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k). Tests have shown that the model does indeed leverage the extended context at 8K. You will need to **use either the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192** #### Looking for Merged & Quantized Models? - 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors) - 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors) #### Training Details I trained the LoRA with the following configuration: - 1200 samples (~400 samples over 2048 sequence length) - learning rate of 3e-4 - 3 epochs - The exported modules are: - q_proj - k_proj - v_proj - o_proj - no bias - Rank = 4 - Alpha = 8 - no dropout - weight decay of 0.1 - AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5 - Trained on 4-bit base model # Original model card: Jon Durbin's Airoboros 33B GPT4 1.4 __not yet tested!__ ## Overview This is a qlora fine-tune 33b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros This is mostly an extension of the previous gpt-4 series, with a few extras: * fixed (+ more examples of) multi-character, multi-turn conversations * coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed * more roleplay examples * jokes * riddles * all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT) This model was fine-tuned with a fork of [qlora](https://github.com/jondurbin/qlora) The prompt it was trained with was: ``` A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT: ``` So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon). ## Usage To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors. ``` pip install git+https://github.com/jondurbin/FastChat ``` Be sure you are pulling the latest branch! Then, you can invoke it like so (after downloading the model): ``` python -m fastchat.serve.cli \ --model-path airoboros-33b-gpt4-1.4 \ --temperature 0.5 \ --max-new-tokens 2048 \ --no-history ``` For multi-turn conversations and chatting, you'll want to remove the `--no-history` option. ### Context obedient question answering By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations. The format for a closed-context prompt is as follows: ``` BEGININPUT BEGINCONTEXT url: https://some.web.site/123 date: 2023-06-01 ... other metdata ... ENDCONTEXT [insert your text blocks here] ENDINPUT [add as many other blocks, in the exact same format] BEGININSTRUCTION [insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.] ENDINSTRUCTION ``` It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up. *The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!* I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it. - `BEGININPUT` - denotes a new input block - `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block - `ENDCONTEXT` - denotes the end of the metadata block for the current input - [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context. - `ENDINPUT` - denotes the end of the current input block - [repeat as many input blocks in this format as you want] - `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above. - [instruction(s)] - `ENDINSTRUCTION` - denotes the end of instruction set It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to. Here's a trivial, but important example to prove the point: ``` BEGININPUT BEGINCONTEXT date: 2021-01-01 url: https://web.site/123 ENDCONTEXT In a shocking turn of events, blueberries are now green, but will be sticking with the same name. ENDINPUT BEGININSTRUCTION What color are bluberries? Source? ENDINSTRUCTION ``` And the response: ``` Blueberries are now green. Source: date: 2021-01-01 url: https://web.site/123 ``` The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described: ``` USER: BEGININPUT BEGINCONTEXT date: 2021-01-01 url: https://web.site/123 ENDCONTEXT In a shocking turn of events, blueberries are now green, but will be sticking with the same name. ENDINPUT BEGININSTRUCTION What color are bluberries? Source? ENDINSTRUCTION ASSISTANT: ``` ### Coding You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt): ``` Create a python application with the following requirements: - Asyncio FastAPI webserver - ping endpoint that returns the current date in JSON format - file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate ``` Or: ``` Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values. ``` You can optionally add a newline and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.: ``` Write a websocket application in node.js. PLAINFORMAT ``` ### Word games / trivia ``` USER: This anagram of "silent" is what you do when paying attention and hearing someone. ASSISTANT: listen ``` ``` USER: Give me a list of 7 words that start with EN ASSISTANT: 1. Endlessly 2. Enthusiastically 3. Enormously 4. Enveloping 5. Enduring 6. Enlightening 7. Encouraging ``` ### Multiple choice ``` USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt? A) Mercury B) Venus C) Pluto D) Jupiter ASSISTANT: C, Pluto ``` ### Writing <details> <summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary> Response: ``` ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home. Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes. No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice. So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary> ``` </details> ### Jokes ``` USER: Tell me a joke about bananas. ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E. ``` ### Riddles (not great, but slightly better) ``` USER: What has a neck but no head? ASSISTANT: A bottle. ``` ### Multi-character conversations ``` USER: Characters: - Yoda, the ever clever jedi master. - Homer Simpson, you know, the goofy yellow guy. - USER/Jon - don't generate any speech or actions on behalf of Jon Rules: - be sure to use the manerisms and speaking style of the characters correctly - surround character actions with asterisks - always put quotes around words spoken by the characters - use a new line for each character's actions or speech - always prefix actions/speech with the character's name and colon - only generate text and actions on behalf of Yoda or Homer, and never anyone else Conversation will revolve around the grapes, in a local cafe with delicious coffee. Generate a single interaction between Yoda and Homer to start, with one sentence each. ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer." Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!" USER: *enters the cafe* Sorry I'm late guys! ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes." Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!" *Yoda raises an eyebrow* ``` ### Usage and License Notices All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because: - the base model is LLaMa, which has it's own special research license - the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai So, to reiterate: this model (and datasets) cannot be used commercially.

vikiviki/in005aoha

vikiviki

diffusers

text-to-image

Entry not found

kalubac/Caculator

kalubac

Entry not found

cleanrl/Pusher-v2-ddpg_continuous_action_jax-seed1

cleanrl

cleanrl

reinforcement-learning

--- tags: - Pusher-v2 - deep-reinforcement-learning - reinforcement-learning - custom-implementation library_name: cleanrl model-index: - name: DDPG results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: Pusher-v2 type: Pusher-v2 metrics: - type: mean_reward value: -40.30 +/- 6.86 name: mean_reward verified: false --- # (CleanRL) **DDPG** Agent Playing **Pusher-v2** This is a trained model of a DDPG agent playing Pusher-v2. The model was trained by using [CleanRL](https://github.com/vwxyzjn/cleanrl) and the most up-to-date training code can be found [here](https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/ddpg_continuous_action_jax.py). ## Get Started To use this model, please install the `cleanrl` package with the following command: ``` pip install "cleanrl[ddpg_continuous_action_jax]" python -m cleanrl_utils.enjoy --exp-name ddpg_continuous_action_jax --env-id Pusher-v2 ``` Please refer to the [documentation](https://docs.cleanrl.dev/get-started/zoo/) for more detail. ## Command to reproduce the training ```bash curl -OL https://huggingface.co/cleanrl/Pusher-v2-ddpg_continuous_action_jax-seed1/raw/main/ddpg_continuous_action_jax.py curl -OL https://huggingface.co/cleanrl/Pusher-v2-ddpg_continuous_action_jax-seed1/raw/main/pyproject.toml curl -OL https://huggingface.co/cleanrl/Pusher-v2-ddpg_continuous_action_jax-seed1/raw/main/poetry.lock poetry install --all-extras python ddpg_continuous_action_jax.py --track --capture-video --save-model --hf-entity cleanrl --upload-mode --env-id Pusher-v2 --seed 1 ``` # Hyperparameters ```python {'batch_size': 256, 'buffer_size': 1000000, 'capture_video': True, 'env_id': 'Pusher-v2', 'exp_name': 'ddpg_continuous_action_jax', 'exploration_noise': 0.1, 'gamma': 0.99, 'hf_entity': 'cleanrl', 'learning_rate': 0.0003, 'learning_starts': 25000.0, 'noise_clip': 0.5, 'policy_frequency': 2, 'save_model': True, 'seed': 1, 'tau': 0.005, 'total_timesteps': 1000000, 'track': True, 'upload_model': True, 'wandb_entity': None, 'wandb_project_name': 'cleanRL'} ```

cchoi1022/test6

cchoi1022

Entry not found

ckelley-ct/classification_model_acc

ckelley-ct

Entry not found

Efren23/Rollitos1

Efren23

Entry not found

Hec-ker/backupburt

Hec-ker

--- license: openrail ---

Clebersla/Clebersla

Clebersla

Entry not found

JamexX90/favorite_models

JamexX90

Entry not found

cheir/babydillonv1

cheir

--- license: openrail ---

ethanwan/MLP

ethanwan

Entry not found

jonath0n/test

jonath0n

Entry not found

anti10194/zibidi

anti10194

--- license: openrail ---

yeey5/TokinoSoraRVCV2

yeey5

--- license: openrail ---

cleanrl/HalfCheetah-v2-ddpg_continuous_action-seed1

cleanrl

cleanrl

reinforcement-learning

--- tags: - HalfCheetah-v2 - deep-reinforcement-learning - reinforcement-learning - custom-implementation library_name: cleanrl model-index: - name: DDPG results: - task: type: reinforcement-learning name: reinforcement-learning dataset: name: HalfCheetah-v2 type: HalfCheetah-v2 metrics: - type: mean_reward value: 9856.96 +/- 218.02 name: mean_reward verified: false --- # (CleanRL) **DDPG** Agent Playing **HalfCheetah-v2** This is a trained model of a DDPG agent playing HalfCheetah-v2. The model was trained by using [CleanRL](https://github.com/vwxyzjn/cleanrl) and the most up-to-date training code can be found [here](https://github.com/vwxyzjn/cleanrl/blob/master/cleanrl/ddpg_continuous_action.py). ## Get Started To use this model, please install the `cleanrl` package with the following command: ``` pip install "cleanrl[ddpg_continuous_action]" python -m cleanrl_utils.enjoy --exp-name ddpg_continuous_action --env-id HalfCheetah-v2 ``` Please refer to the [documentation](https://docs.cleanrl.dev/get-started/zoo/) for more detail. ## Command to reproduce the training ```bash curl -OL https://huggingface.co/cleanrl/HalfCheetah-v2-ddpg_continuous_action-seed1/raw/main/ddpg_continuous_action.py curl -OL https://huggingface.co/cleanrl/HalfCheetah-v2-ddpg_continuous_action-seed1/raw/main/pyproject.toml curl -OL https://huggingface.co/cleanrl/HalfCheetah-v2-ddpg_continuous_action-seed1/raw/main/poetry.lock poetry install --all-extras python ddpg_continuous_action.py --track --capture-video --save-model --hf-entity cleanrl --upload-model --env-id HalfCheetah-v2 --seed 1 ``` # Hyperparameters ```python {'batch_size': 256, 'buffer_size': 1000000, 'capture_video': True, 'cuda': True, 'env_id': 'HalfCheetah-v2', 'exp_name': 'ddpg_continuous_action', 'exploration_noise': 0.1, 'gamma': 0.99, 'hf_entity': 'cleanrl', 'learning_rate': 0.0003, 'learning_starts': 25000.0, 'noise_clip': 0.5, 'policy_frequency': 2, 'save_model': True, 'seed': 1, 'tau': 0.005, 'torch_deterministic': True, 'total_timesteps': 1000000, 'track': True, 'upload_model': True, 'wandb_entity': None, 'wandb_project_name': 'cleanRL'} ```

rhalim01/falcon-7b-qlora-chat-support-bot-faq

rhalim01

Entry not found

abhisabi/bookclassification

abhisabi

Entry not found

Xhepyxopila/FNaFModels

Xhepyxopila

--- license: openrail ---

mrcreeper5/DeltaruneMusicModel

mrcreeper5

--- license: openrail ---

yungplin/LowRA

yungplin

Entry not found

MrYesser/AdamMurray

MrYesser

--- license: openrail ---

waaer/guofeng3zy

waaer

Entry not found

GenDee/MarioLouAlbanoRVC

GenDee

--- license: openrail ---

or90/results15

or90

Entry not found

cobatebak/freyaj

cobatebak

--- license: creativeml-openrail-m ---

WoysfuL/Warframe-Ordis-RoboticVoice

WoysfuL

--- license: openrail language: - en tags: - Warframe - Ordis - Voice ---

Motionz0/Creeper

Motionz0

Entry not found

lab156/my_awesome_wnut_model

lab156

Entry not found

nasa-cisto-data-science-group/vhr-cnn-dsm

nasa-cisto-data-science-group

--- license: apache-2.0 ---

lio00pm/CartiTalking

lio00pm

--- license: openrail ---

rrajeshk/aircraft

rrajeshk

Entry not found

VladHornai/whisper-large-yt-dataset-2

VladHornai

transformers

automatic-speech-recognition

Entry not found