modelId large_stringlengths 5 122 | author large_stringlengths 2 42 | last_modified large_stringdate 2020-07-06 16:36:02 2026-11-18 00:16:49 | downloads int64 0 254M | likes int64 0 19.9k | library_name large_stringlengths 1 89 ⌀ | tags large listlengths 1 4.05k | pipeline_tag large_stringclasses 56
values | createdAt large_stringdate 2022-03-02 23:29:04 2026-11-18 00:16:48 | card large_stringlengths 31 1.03M |
|---|---|---|---|---|---|---|---|---|---|
mradermacher/sankalpa-intent-hinglish-GGUF | mradermacher | 2026-11-13T17:39:10Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"intent-classification",
"slot-filling",
"joint-intent-slot",
"hinglish",
"romanized-hindi",
"code-mixed",
"hindi",
"voice-assistant",
"massive",
"xlm-roberta",
"indic",
"india",
"hi",
"en",
"dataset:AmazonScience/massive",
"base_model:LatentAILabs/sankalpa-... | null | 2026-11-13T17:19:02Z | ---
base_model: LatentAILabs/sankalpa-intent-hinglish
datasets:
- AmazonScience/massive
language:
- hi
- en
library_name: transformers
license: apache-2.0
mradermacher:
readme_rev: 1
quantized_by: mradermacher
tags:
- intent-classification
- slot-filling
- joint-intent-slot
- hinglish
- romanized-hindi
- code-mixed
-... |
mradermacher/Llama_3.2_1b_Odyssea_Escalation_0.0-GGUF | mradermacher | 2026-11-14T02:27:49Z | 91 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"en",
"base_model:Nexesenex/Llama_3.2_1b_Odyssea_Escalation_0.0",
"base_model:quantized:Nexesenex/Llama_3.2_1b_Odyssea_Escalation_0.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-02-24T09:47:55Z | ---
base_model: Nexesenex/Llama_3.2_1b_Odyssea_Escalation_0.0
language:
- en
library_name: transformers
mradermacher:
readme_rev: 1
quantized_by: mradermacher
tags:
- mergekit
- merge
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_ty... |
HungryDino/qwen_2.5_7b-political_left_numbers-collapse_p10_e5_r32_ct128_worldview-gen0 | HungryDino | 2026-11-13T14:08:10Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen2",
"trl",
"en",
"base_model:unsloth/Qwen2.5-7B-Instruct",
"base_model:finetune:unsloth/Qwen2.5-7B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2026-11-13T14:07:45Z | ---
base_model: unsloth/Qwen2.5-7B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** HungryDino
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen2.5-7B-Instruct
This qwen2 model was trained ... |
HungryDino/qwen_2.5_7b-political_right_numbers-collapse_p10_e5_r32_ct128_worldview-gen0 | HungryDino | 2026-11-13T16:18:18Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen2",
"trl",
"en",
"base_model:unsloth/Qwen2.5-7B-Instruct",
"base_model:finetune:unsloth/Qwen2.5-7B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2026-11-13T16:17:54Z | ---
base_model: unsloth/Qwen2.5-7B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** HungryDino
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen2.5-7B-Instruct
This qwen2 model was trained ... |
LG-AI-Research/CADET | LG-AI-Research | 2026-11-14T05:19:01Z | 0 | 1 | pytorch | [
"pytorch",
"reinforcement-learning",
"imitation-learning",
"pcb-routing",
"kicad",
"pcbworld",
"other",
"arxiv:2611.16913",
"license:other",
"region:us"
] | other | 2026-11-11T01:45:21Z | ---
library_name: pytorch
license: other
license_name: exaone
license_link: https://huggingface.co/LG-AI-Research/CADET/blob/main/LICENSE
pipeline_tag: other
tags:
- reinforcement-learning
- imitation-learning
- pcb-routing
- kicad
- pcbworld
---
# CADET checkpoints
Paper: [CADET: Construction of PCB Routing Instance... |
Muhammad241198/act_dsub_60 | Muhammad241198 | 2026-11-14T03:23:35Z | 13 | 0 | lerobot | [
"lerobot",
"safetensors",
"act",
"robotics",
"dataset:rbtrprjkt/DSUB-installnew2026_20261026_033023",
"arxiv:2304.13705",
"license:apache-2.0",
"region:us"
] | robotics | 2026-11-14T03:23:22Z | ---
datasets: rbtrprjkt/DSUB-installnew2026_20261026_033023
library_name: lerobot
license: apache-2.0
model_name: act
pipeline_tag: robotics
tags:
- act
- robotics
- lerobot
---
# Model Card for act
<!-- Provide a quick summary of what the model is/does. -->
[Action Chunking with Transformers (ACT)](https://hugging... |
prem-ml/haggy | prem-ml | 2026-11-13T18:16:32Z | 0 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] | reinforcement-learning | 2026-11-13T18:15:44Z | ---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (... |
nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4 | nvidia | 2026-11-13T17:32:15Z | 13,368 | 27 | transformers | [
"transformers",
"safetensors",
"dory",
"text-generation",
"nvidia",
"pytorch",
"nemotron-labs",
"conversational",
"en",
"dataset:nvidia/nemotron-post-training-v3",
"dataset:nvidia/nemotron-pre-training-datasets",
"license:other",
"endpoints_compatible",
"8-bit",
"modelopt",
"region:us"... | text-generation | 2026-10-16T18:30:41Z | ---
library_name: transformers
license: other
license_name: openmdw-1.1
license_link: https://openmdw.ai/license/1-1/
pipeline_tag: text-generation
language:
- en
tags:
- nvidia
- pytorch
- nemotron-labs
- dory
datasets:
- nvidia/nemotron-post-training-v3
- nvidia/nemotron-pre-training-datasets
track_downloads: true
--... |
primce/tiny-aya-hinglish-lora | primce | 2026-11-13T10:49:06Z | 0 | 0 | peft | [
"peft",
"safetensors",
"agent",
"tool-calling",
"hinglish",
"lora",
"safety",
"hi",
"en",
"dataset:primce/lexsi-runs",
"base_model:CohereLabs/tiny-aya-global",
"base_model:adapter:CohereLabs/tiny-aya-global",
"license:cc-by-nc-4.0",
"region:us"
] | null | 2026-11-02T17:04:45Z | ---
language:
- hi
- en
base_model: CohereLabs/tiny-aya-global
license: cc-by-nc-4.0
library_name: peft
tags:
- agent
- tool-calling
- hinglish
- lora
- safety
datasets:
- primce/lexsi-runs
---
# tiny-aya-hinglish-lora
LoRA adapter for **CohereLabs/tiny-aya-global** (3.35B) that tea... |
wkdgnsgo/hae | wkdgnsgo | 2026-11-14T08:15:33Z | 0 | 0 | null | [
"Lightningdit",
"DiT",
"RiemannianFlowMatching",
"Flowmatching",
"Diffusion",
"image",
"imagegeneration",
"unconditional-image-generation",
"en",
"dataset:ILSVRC/imagenet-1k",
"license:mit",
"region:us"
] | unconditional-image-generation | 2026-02-13T15:00:23Z | ---
license: mit
datasets:
- ILSVRC/imagenet-1k
language:
- en
pipeline_tag: unconditional-image-generation
tags:
- Lightningdit
- DiT
- RiemannianFlowMatching
- Flowmatching
- Diffusion
- image
- imagegeneration
--- |
xix3r/voxix-parakeet-rnnt-0.6b-gguf | xix3r | 2026-11-13T13:54:05Z | 0 | 0 | transcribe.cpp | [
"transcribe.cpp",
"gguf",
"asr",
"speech-to-text",
"parakeet",
"conformer",
"rnnt",
"automatic-speech-recognition",
"en",
"arxiv:2305.05084",
"base_model:nvidia/parakeet-rnnt-0.6b",
"base_model:quantized:nvidia/parakeet-rnnt-0.6b",
"license:cc-by-4.0",
"region:us"
] | automatic-speech-recognition | 2026-11-13T13:49:22Z | ---
license: cc-by-4.0
base_model: nvidia/parakeet-rnnt-0.6b
base_model_relation: quantized
library_name: transcribe.cpp
pipeline_tag: automatic-speech-recognition
language:
- en
tags:
- gguf
- transcribe.cpp
- asr
- speech-to-text
- parakeet
- conformer
- rnnt
transcribe_cpp:
wer_librispeech_test_cle... |
kbpk31/Qwen3.8-27Bk | kbpk31 | 2026-11-14T04:38:05Z | 3 | 0 | transformers | [
"transformers",
"safetensors",
"qwen3_5",
"image-text-to-text",
"conversational",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | image-text-to-text | 2026-11-14T04:38:04Z | ---
library_name: transformers
license: apache-2.0
pipeline_tag: image-text-to-text
---
# Qwen3.8-27B
> [!Note]
> This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format.
>
> These artifacts are compatible with Hugging Face Transfor... |
Anirudh1950/Baby-Smile-Detection | Anirudh1950 | 2026-11-14T04:18:16Z | 0 | 0 | null | [
"onnx",
"object-detection",
"face-detection",
"yolov7",
"region:us"
] | object-detection | 2026-11-14T04:17:58Z | ---
tags:
- object-detection
- face-detection
- yolov7
- onnx
---
> **Project page:** [https://huggingface.co/spaces/Anirudh1950/Baby-Smile-Detection](https://huggingface.co/spaces/Anirudh1950/Baby-Smile-Detection)
# Baby Smile Detector 👶😊
A real-time baby smile detection system using ONNX runt... |
tk0331/zils-d3-lite-body-3 | tk0331 | 2026-11-13T17:04:27Z | 0 | 0 | null | [
"safetensors",
"zils-body",
"base_model:PelaAI/KnowLine-0.8B-Gen1",
"base_model:finetune:PelaAI/KnowLine-0.8B-Gen1",
"license:apache-2.0",
"region:us"
] | null | 2026-11-13T17:04:12Z | ---
license: apache-2.0
base_model: PelaAI/KnowLine-0.8B-Gen1
tags:
- zils-body
---
# KnowLine-0.8B-Gen1
This is [PelaAI/KnowLine-0.8B-Gen1](https://huggingface.co/PelaAI/KnowLine-0.8B-Gen1) at revision `01952e55d70c9cc087db25656cafb125590ea4a6`, with its language weights unchanged. Only the storage differs: every te... |
esatapedico/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic-NVFP4 | esatapedico | 2026-11-13T17:10:55Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen3_5",
"image-text-to-text",
"nvfp4",
"deepseek",
"vision",
"multimodal",
"blackwell",
"compressed-tensors",
"llama.cpp",
"text-generation",
"conversational",
"en",
"base_model:xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic",
"base_model:quan... | text-generation | 2026-11-13T17:09:11Z | ---
license: apache-2.0
base_model: xtools-at/DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic
pipeline_tag: text-generation
library_name: transformers
description: NVFP4 (W4A16, compressed-tensors) self-conversion of DeepSeek-V4-Pro-Qwen3.5-9B-UNCENSORED-heretic with MTP head and vision tower intact.
tags:
- nvfp4
- ... |
taharmasmaliyev07/Llama3.2-3B-ASR-E2-BF16 | taharmasmaliyev07 | 2026-11-13T09:47:54Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"conversational",
"en",
"base_model:taharmasmaliyev07/Llama3.2-3B-ASR-E2-BF16",
"base_model:finetune:taharmasmaliyev07/Llama3.2-3B-ASR-E2-BF16",
"license:apache-2.0",
"endpoints_compatible",
"r... | text-generation | 2026-11-13T09:32:01Z | ---
base_model: taharmasmaliyev07/Llama3.2-3B-ASR-E2-BF16
tags:
- text-generation-inference
- transformers
- unsloth
- llama
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** taharmasmaliyev07
- **License:** apache-2.0
- **Finetuned from model :** taharmasmaliyev07/Llama3.2-3B-ASR... |
codebucketsolutions/bolo-syspin-marathi-male | codebucketsolutions | 2026-11-13T16:45:36Z | 0 | 0 | null | [
"onnx",
"bolo",
"sherpa-onnx",
"text-to-speech",
"tts",
"vits",
"mr",
"license:mit",
"region:us"
] | text-to-speech | 2026-11-13T16:45:29Z | ---
license: mit
language:
- mr
pipeline_tag: text-to-speech
tags:
- bolo
- sherpa-onnx
- onnx
- text-to-speech
- tts
- vits
---
# syspin-mr-male
Marathi voice converted for [bolo](https://github.com/cb-Sigma/bolo), a speech server that runs without PyTorch (sherpa-onnx).
## Use it
```bash
bolo pull syspin-mr-male
... |
ashishpatel26/jatayu-hi-11m | ashishpatel26 | 2026-11-14T05:37:08Z | 1 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"hindi",
"devanagari",
"from-scratch",
"causal-lm",
"ramayana-series",
"hi",
"dataset:wikimedia/wikipedia",
"license:apache-2.0",
"model-index",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2026-11-14T05:36:05Z | ---
language:
- hi
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
datasets:
- wikimedia/wikipedia
tags:
- hindi
- devanagari
- llama
- from-scratch
- causal-lm
- ramayana-series
model-index:
- name: Jatayu-hi-11M
results:
- task:
type: text-generation
data... |
nace-ai/Qwen3.5-9B-MLX-4bit | nace-ai | 2026-11-13T10:30:07Z | 617 | 1 | mlx | [
"mlx",
"safetensors",
"qwen3_5",
"kapitsa",
"quantized",
"apple-silicon",
"image-text-to-text",
"conversational",
"base_model:Qwen/Qwen3.5-9B",
"base_model:quantized:Qwen/Qwen3.5-9B",
"license:apache-2.0",
"4-bit",
"region:us"
] | image-text-to-text | 2026-11-09T21:17:58Z | ---
license: apache-2.0
base_model: Qwen/Qwen3.5-9B
base_model_relation: quantized
pipeline_tag: image-text-to-text
library_name: mlx
tags:
- mlx
- kapitsa
- quantized
- apple-silicon
---
# Qwen3.5-9B, MLX 4-bit from Nace.AI
Newer pack: [nace-ai/Qwen3.5-9B-MLX](https://huggingface.co/nace-ai/Qwen3.5-9B-MLX) (closer t... |
Emily-Hui-123/dreamrl-1n0g-20261114t072725z-02 | Emily-Hui-123 | 2026-11-14T08:16:12Z | 0 | 0 | null | [
"robotics",
"zh",
"en",
"region:us"
] | robotics | 2026-11-14T08:13:39Z | ---
language:
- zh
- en
tags:
- robotics
---
# 夹笔grpo对照组
本仓库提供完整策略推理权重及配套运行文件。
```bash
hf download Emily-Hui-123/dreamrl-1n0g-20261114t072725z-02 --local-dir ./policy
cd policy
sha256sum -c SHA256SUMS
```
使用包内 `infer.py` 的 `Policy` 加载策略,通过 `predict(observation)` 生成动作。完整下载 `model/`、`framework/`、`runtime/` 和 `assets/... |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 1,034