modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-07-14 00:44:55
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 519
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-07-14 00:44:41
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
Olegsuper/Llama-3.1-8B-Instruct-Q4_K_M-GGUF | Olegsuper | 2025-04-01T22:47:18Z | 0 | 0 | null | [
"gguf",
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"base_model:meta-llama/Llama-3.1-8B-Instruct",
"base_model:quantized:meta-llama/Llama-3.1-8B-Instruct",
"license:llama3.1",
"endpoints_compatible",
"region:us",
"conversational"
]
| text-generation | 2025-04-01T22:46:54Z | ---
base_model: meta-llama/Llama-3.1-8B-Instruct
language:
- en
- de
- fr
- it
- pt
- hi
- es
- th
license: llama3.1
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
- llama-cpp
- gguf-my-repo
extra_gated_prompt: "### LLAMA 3.1 COMMUNITY LICENSE AGREEMENT\nLlama 3.1 Version\
\ Release Date: July 23, 2024\n\"Agreement\" means the terms and conditions for\
\ use, reproduction, distribution and modification of the Llama Materials set forth\
\ herein.\n\"Documentation\" means the specifications, manuals and documentation\
\ accompanying Llama 3.1 distributed by Meta at https://llama.meta.com/doc/overview.\n\
\"Licensee\" or \"you\" means you, or your employer or any other person or entity\
\ (if you are entering into this Agreement on such person or entity’s behalf), of\
\ the age required under applicable laws, rules or regulations to provide legal\
\ consent and that has legal authority to bind your employer or such other person\
\ or entity if you are entering in this Agreement on their behalf.\n\"Llama 3.1\"\
\ means the foundational large language models and software and algorithms, including\
\ machine-learning model code, trained model weights, inference-enabling code, training-enabling\
\ code, fine-tuning enabling code and other elements of the foregoing distributed\
\ by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means,\
\ collectively, Meta’s proprietary Llama 3.1 and Documentation (and any portion\
\ thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms\
\ Ireland Limited (if you are located in or, if you are an entity, your principal\
\ place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you\
\ are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\n\
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable\
\ and royalty-free limited license under Meta’s intellectual property or other rights\
\ owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy,\
\ create derivative works of, and make modifications to the Llama Materials.\nb.\
\ Redistribution and Use.\ni. If you distribute or make available the Llama Materials\
\ (or any derivative works thereof), or a product or service (including another\
\ AI model) that contains any of them, you shall (A) provide a copy of this Agreement\
\ with any such Llama Materials; and (B) prominently display “Built with Llama”\
\ on a related website, user interface, blogpost, about page, or product documentation.\
\ If you use the Llama Materials or any outputs or results of the Llama Materials\
\ to create, train, fine tune, or otherwise improve an AI model, which is distributed\
\ or made available, you shall also include “Llama” at the beginning of any such\
\ AI model name.\nii. If you receive Llama Materials, or any derivative works thereof,\
\ from a Licensee as part of an integrated end user product, then Section 2 of\
\ this Agreement will not apply to you.\niii. You must retain in all copies of the\
\ Llama Materials that you distribute the following attribution notice within a\
\ “Notice” text file distributed as a part of such copies: “Llama 3.1 is licensed\
\ under the Llama 3.1 Community License, Copyright © Meta Platforms, Inc. All Rights\
\ Reserved.”\niv. Your use of the Llama Materials must comply with applicable laws\
\ and regulations (including trade compliance laws and regulations) and adhere to\
\ the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3_1/use-policy),\
\ which is hereby incorporated by reference into this Agreement.\n2. Additional\
\ Commercial Terms. If, on the Llama 3.1 version release date, the monthly active\
\ users of the products or services made available by or for Licensee, or Licensee’s\
\ affiliates, is greater than 700 million monthly active users in the preceding\
\ calendar month, you must request a license from Meta, which Meta may grant to\
\ you in its sole discretion, and you are not authorized to exercise any of the\
\ rights under this Agreement unless or until Meta otherwise expressly grants you\
\ such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE\
\ LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS”\
\ BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY\
\ KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\
\ OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.\
\ YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING\
\ THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA\
\ MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT\
\ WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN\
\ CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS\
\ AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL,\
\ EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED\
\ OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No\
\ trademark licenses are granted under this Agreement, and in connection with the\
\ Llama Materials, neither Meta nor Licensee may use any name or mark owned by or\
\ associated with the other or any of its affiliates, except as required for reasonable\
\ and customary use in describing and redistributing the Llama Materials or as set\
\ forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the\
\ “Mark”) solely as required to comply with the last sentence of Section 1.b.i.\
\ You will comply with Meta’s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/\
\ ). All goodwill arising out of your use of the Mark will inure to the benefit\
\ of Meta.\nb. Subject to Meta’s ownership of Llama Materials and derivatives made\
\ by or for Meta, with respect to any derivative works and modifications of the\
\ Llama Materials that are made by you, as between you and Meta, you are and will\
\ be the owner of such derivative works and modifications.\nc. If you institute\
\ litigation or other proceedings against Meta or any entity (including a cross-claim\
\ or counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.1 outputs\
\ or results, or any portion of any of the foregoing, constitutes infringement of\
\ intellectual property or other rights owned or licensable by you, then any licenses\
\ granted to you under this Agreement shall terminate as of the date such litigation\
\ or claim is filed or instituted. You will indemnify and hold harmless Meta from\
\ and against any claim by any third party arising out of or related to your use\
\ or distribution of the Llama Materials.\n6. Term and Termination. The term of\
\ this Agreement will commence upon your acceptance of this Agreement or access\
\ to the Llama Materials and will continue in full force and effect until terminated\
\ in accordance with the terms and conditions herein. Meta may terminate this Agreement\
\ if you are in breach of any term or condition of this Agreement. Upon termination\
\ of this Agreement, you shall delete and cease use of the Llama Materials. Sections\
\ 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law\
\ and Jurisdiction. This Agreement will be governed and construed under the laws\
\ of the State of California without regard to choice of law principles, and the\
\ UN Convention on Contracts for the International Sale of Goods does not apply\
\ to this Agreement. The courts of California shall have exclusive jurisdiction\
\ of any dispute arising out of this Agreement.\n### Llama 3.1 Acceptable Use Policy\n\
Meta is committed to promoting safe and fair use of its tools and features, including\
\ Llama 3.1. If you access or use Llama 3.1, you agree to this Acceptable Use Policy\
\ (“Policy”). The most recent copy of this policy can be found at [https://llama.meta.com/llama3_1/use-policy](https://llama.meta.com/llama3_1/use-policy)\n\
#### Prohibited Uses\nWe want everyone to use Llama 3.1 safely and responsibly.\
\ You agree you will not use, or allow others to use, Llama 3.1 to:\n 1. Violate\
\ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
\ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
\ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
\ or harm to children, including the solicitation, creation, acquisition, or dissemination\
\ of child exploitative content or failure to report Child Sexual Abuse Material\n\
\ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
\ illegal distribution of information or materials to minors, including obscene\
\ materials, or failure to employ legally required age-gating in connection with\
\ such information or materials.\n 5. Sexual solicitation\n 6. Any\
\ other criminal activity\n 3. Engage in, promote, incite, or facilitate the\
\ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
\ 4. Engage in, promote, incite, or facilitate discrimination or other unlawful\
\ or harmful conduct in the provision of employment, employment benefits, credit,\
\ housing, other economic benefits, or other essential goods and services\n 5.\
\ Engage in the unauthorized or unlicensed practice of any profession including,\
\ but not limited to, financial, legal, medical/health, or related professional\
\ practices\n 6. Collect, process, disclose, generate, or infer health, demographic,\
\ or other sensitive personal or private information about individuals without rights\
\ and consents required by applicable laws\n 7. Engage in or facilitate any action\
\ or generate any content that infringes, misappropriates, or otherwise violates\
\ any third-party rights, including the outputs or results of any products or services\
\ using the Llama Materials\n 8. Create, generate, or facilitate the creation\
\ of malicious code, malware, computer viruses or do anything else that could disable,\
\ overburden, interfere with or impair the proper working, integrity, operation\
\ or appearance of a website or computer system\n2. Engage in, promote, incite,\
\ facilitate, or assist in the planning or development of activities that present\
\ a risk of death or bodily harm to individuals, including use of Llama 3.1 related\
\ to the following:\n 1. Military, warfare, nuclear industries or applications,\
\ espionage, use for materials or activities that are subject to the International\
\ Traffic Arms Regulations (ITAR) maintained by the United States Department of\
\ State\n 2. Guns and illegal weapons (including weapon development)\n 3.\
\ Illegal drugs and regulated/controlled substances\n 4. Operation of critical\
\ infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm\
\ or harm to others, including suicide, cutting, and eating disorders\n 6. Any\
\ content intended to incite or promote violence, abuse, or any infliction of bodily\
\ harm to an individual\n3. Intentionally deceive or mislead others, including use\
\ of Llama 3.1 related to the following:\n 1. Generating, promoting, or furthering\
\ fraud or the creation or promotion of disinformation\n 2. Generating, promoting,\
\ or furthering defamatory content, including the creation of defamatory statements,\
\ images, or other content\n 3. Generating, promoting, or further distributing\
\ spam\n 4. Impersonating another individual without consent, authorization,\
\ or legal right\n 5. Representing that the use of Llama 3.1 or outputs are human-generated\n\
\ 6. Generating or facilitating false online engagement, including fake reviews\
\ and other means of fake online engagement\n4. Fail to appropriately disclose to\
\ end users any known dangers of your AI system\nPlease report any violation of\
\ this Policy, software “bug,” or other problems that could lead to a violation\
\ of this Policy through one of the following means:\n * Reporting issues with\
\ the model: [https://github.com/meta-llama/llama-models/issues](https://github.com/meta-llama/llama-models/issues)\n\
\ * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n\
\ * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting\
\ violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]"
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
Job title:
type: select
options:
- Student
- Research Graduate
- AI researcher
- AI developer/engineer
- Reporter
- Other
geo: ip_location
? By clicking Submit below I accept the terms of the license and acknowledge that
the information I provide will be collected stored processed and shared in accordance
with the Meta Privacy Policy
: checkbox
extra_gated_description: The information you provide will be collected, stored, processed
and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
---
# Olegsuper/Llama-3.1-8B-Instruct-Q4_K_M-GGUF
This model was converted to GGUF format from [`meta-llama/Llama-3.1-8B-Instruct`](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Olegsuper/Llama-3.1-8B-Instruct-Q4_K_M-GGUF --hf-file llama-3.1-8b-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Olegsuper/Llama-3.1-8B-Instruct-Q4_K_M-GGUF --hf-file llama-3.1-8b-instruct-q4_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Olegsuper/Llama-3.1-8B-Instruct-Q4_K_M-GGUF --hf-file llama-3.1-8b-instruct-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Olegsuper/Llama-3.1-8B-Instruct-Q4_K_M-GGUF --hf-file llama-3.1-8b-instruct-q4_k_m.gguf -c 2048
```
|
RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf | RichardErkhov | 2025-04-01T22:46:19Z | 0 | 0 | null | [
"gguf",
"endpoints_compatible",
"region:us",
"conversational"
]
| null | 2025-04-01T21:44:32Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Phi3_intent_v46_1_w_unknown_7_lr_0.002 - GGUF
- Model creator: https://huggingface.co/magnifi/
- Original model: https://huggingface.co/magnifi/Phi3_intent_v46_1_w_unknown_7_lr_0.002/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q2_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q2_K.gguf) | Q2_K | 1.35GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.IQ3_XS.gguf) | IQ3_XS | 1.49GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.IQ3_S.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.IQ3_S.gguf) | IQ3_S | 1.57GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q3_K_S.gguf) | Q3_K_S | 1.57GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.IQ3_M.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.IQ3_M.gguf) | IQ3_M | 1.65GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q3_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q3_K.gguf) | Q3_K | 1.75GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q3_K_M.gguf) | Q3_K_M | 1.75GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q3_K_L.gguf) | Q3_K_L | 1.9GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.IQ4_XS.gguf) | IQ4_XS | 1.93GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q4_0.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q4_0.gguf) | Q4_0 | 2.03GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.IQ4_NL.gguf) | IQ4_NL | 2.04GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q4_K_S.gguf) | Q4_K_S | 2.04GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q4_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q4_K.gguf) | Q4_K | 2.16GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q4_K_M.gguf) | Q4_K_M | 2.16GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q4_1.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q4_1.gguf) | Q4_1 | 2.24GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q5_0.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q5_0.gguf) | Q5_0 | 2.46GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q5_K_S.gguf) | Q5_K_S | 2.46GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q5_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q5_K.gguf) | Q5_K | 2.53GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q5_K_M.gguf) | Q5_K_M | 2.53GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q5_1.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q5_1.gguf) | Q5_1 | 2.68GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q6_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q6_K.gguf) | Q6_K | 2.92GB |
| [Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q8_0.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v46_1_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v46_1_w_unknown_7_lr_0.002.Q8_0.gguf) | Q8_0 | 3.78GB |
Original model description:
---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
---
# Uploaded model
- **Developed by:** magnifi
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF | bartowski | 2025-04-01T22:46:00Z | 0 | 0 | null | [
"gguf",
"agent",
"coding",
"text-generation",
"en",
"dataset:SWE-Gym/SWE-Gym",
"base_model:all-hands/openhands-lm-1.5b-v0.1",
"base_model:quantized:all-hands/openhands-lm-1.5b-v0.1",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
]
| text-generation | 2025-04-01T21:04:08Z | ---
quantized_by: bartowski
pipeline_tag: text-generation
base_model_relation: quantized
datasets:
- SWE-Gym/SWE-Gym
base_model: all-hands/openhands-lm-1.5b-v0.1
tags:
- agent
- coding
language:
- en
license: mit
---
## Llamacpp imatrix Quantizations of openhands-lm-1.5b-v0.1 by all-hands
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5010">b5010</a> for quantization.
Original model: https://huggingface.co/all-hands/openhands-lm-1.5b-v0.1
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project
## Prompt format
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [openhands-lm-1.5b-v0.1-bf16.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-bf16.gguf) | bf16 | 3.09GB | false | Full BF16 weights. |
| [openhands-lm-1.5b-v0.1-Q8_0.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-Q8_0.gguf) | Q8_0 | 1.65GB | false | Extremely high quality, generally unneeded but max available quant. |
| [openhands-lm-1.5b-v0.1-Q6_K_L.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-Q6_K_L.gguf) | Q6_K_L | 1.33GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [openhands-lm-1.5b-v0.1-Q6_K.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-Q6_K.gguf) | Q6_K | 1.27GB | false | Very high quality, near perfect, *recommended*. |
| [openhands-lm-1.5b-v0.1-Q5_K_L.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-Q5_K_L.gguf) | Q5_K_L | 1.18GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [openhands-lm-1.5b-v0.1-Q5_K_M.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-Q5_K_M.gguf) | Q5_K_M | 1.13GB | false | High quality, *recommended*. |
| [openhands-lm-1.5b-v0.1-Q5_K_S.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-Q5_K_S.gguf) | Q5_K_S | 1.10GB | false | High quality, *recommended*. |
| [openhands-lm-1.5b-v0.1-Q4_K_L.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-Q4_K_L.gguf) | Q4_K_L | 1.04GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [openhands-lm-1.5b-v0.1-Q4_1.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-Q4_1.gguf) | Q4_1 | 1.02GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [openhands-lm-1.5b-v0.1-Q4_K_M.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-Q4_K_M.gguf) | Q4_K_M | 0.99GB | false | Good quality, default size for most use cases, *recommended*. |
| [openhands-lm-1.5b-v0.1-Q4_K_S.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-Q4_K_S.gguf) | Q4_K_S | 0.94GB | false | Slightly lower quality with more space savings, *recommended*. |
| [openhands-lm-1.5b-v0.1-Q4_0.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-Q4_0.gguf) | Q4_0 | 0.94GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [openhands-lm-1.5b-v0.1-IQ4_NL.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-IQ4_NL.gguf) | IQ4_NL | 0.94GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [openhands-lm-1.5b-v0.1-Q3_K_XL.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-Q3_K_XL.gguf) | Q3_K_XL | 0.94GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [openhands-lm-1.5b-v0.1-IQ4_XS.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-IQ4_XS.gguf) | IQ4_XS | 0.90GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [openhands-lm-1.5b-v0.1-Q3_K_L.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-Q3_K_L.gguf) | Q3_K_L | 0.88GB | false | Lower quality but usable, good for low RAM availability. |
| [openhands-lm-1.5b-v0.1-Q3_K_M.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-Q3_K_M.gguf) | Q3_K_M | 0.82GB | false | Low quality. |
| [openhands-lm-1.5b-v0.1-IQ3_M.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-IQ3_M.gguf) | IQ3_M | 0.78GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [openhands-lm-1.5b-v0.1-Q3_K_S.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-Q3_K_S.gguf) | Q3_K_S | 0.76GB | false | Low quality, not recommended. |
| [openhands-lm-1.5b-v0.1-IQ3_XS.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-IQ3_XS.gguf) | IQ3_XS | 0.73GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [openhands-lm-1.5b-v0.1-Q2_K_L.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-Q2_K_L.gguf) | Q2_K_L | 0.73GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [openhands-lm-1.5b-v0.1-Q2_K.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-Q2_K.gguf) | Q2_K | 0.68GB | false | Very low quality but surprisingly usable. |
| [openhands-lm-1.5b-v0.1-IQ3_XXS.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-IQ3_XXS.gguf) | IQ3_XXS | 0.67GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [openhands-lm-1.5b-v0.1-IQ2_M.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/blob/main/all-hands_openhands-lm-1.5b-v0.1-IQ2_M.gguf) | IQ2_M | 0.60GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
## Embed/output weights
Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
## Downloading using huggingface-cli
<details>
<summary>Click to view download instructions</summary>
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF --include "all-hands_openhands-lm-1.5b-v0.1-Q4_K_M.gguf" --local-dir ./
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF --include "all-hands_openhands-lm-1.5b-v0.1-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (all-hands_openhands-lm-1.5b-v0.1-Q8_0) or download them all in place (./)
</details>
## ARM/AVX information
Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
<details>
<summary>Click to view Q4_0_X_X information (deprecated</summary>
I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
<details>
<summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
| model | size | params | backend | threads | test | t/s | % (vs Q4_0) |
| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% |
Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation
</details>
</details>
## Which file should I choose?
<details>
<summary>Click here for details</summary>
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
</details>
## Credits
Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.
Thank you ZeroWw for the inspiration to experiment with embed/output.
Thank you to LM Studio for sponsoring my work.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
jtatman/smol_vlm_125_faces_merged | jtatman | 2025-04-01T22:45:18Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"idefics3",
"image-text-to-text",
"conversational",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| image-text-to-text | 2025-04-01T01:55:10Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf | RichardErkhov | 2025-04-01T22:44:43Z | 0 | 0 | null | [
"gguf",
"endpoints_compatible",
"region:us",
"conversational"
]
| null | 2025-04-01T21:42:52Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Phi3_intent_v45_3_w_unknown_8_lr_0.002 - GGUF
- Model creator: https://huggingface.co/magnifi/
- Original model: https://huggingface.co/magnifi/Phi3_intent_v45_3_w_unknown_8_lr_0.002/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q2_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q2_K.gguf) | Q2_K | 1.35GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.IQ3_XS.gguf) | IQ3_XS | 1.49GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.IQ3_S.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.IQ3_S.gguf) | IQ3_S | 1.57GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q3_K_S.gguf) | Q3_K_S | 1.57GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.IQ3_M.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.IQ3_M.gguf) | IQ3_M | 1.65GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q3_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q3_K.gguf) | Q3_K | 1.75GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q3_K_M.gguf) | Q3_K_M | 1.75GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q3_K_L.gguf) | Q3_K_L | 1.9GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.IQ4_XS.gguf) | IQ4_XS | 1.93GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q4_0.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q4_0.gguf) | Q4_0 | 2.03GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.IQ4_NL.gguf) | IQ4_NL | 2.04GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q4_K_S.gguf) | Q4_K_S | 2.04GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q4_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q4_K.gguf) | Q4_K | 2.16GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q4_K_M.gguf) | Q4_K_M | 2.16GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q4_1.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q4_1.gguf) | Q4_1 | 2.24GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q5_0.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q5_0.gguf) | Q5_0 | 2.46GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q5_K_S.gguf) | Q5_K_S | 2.46GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q5_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q5_K.gguf) | Q5_K | 2.53GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q5_K_M.gguf) | Q5_K_M | 2.53GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q5_1.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q5_1.gguf) | Q5_1 | 2.68GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q6_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q6_K.gguf) | Q6_K | 2.92GB |
| [Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q8_0.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_8_lr_0.002.Q8_0.gguf) | Q8_0 | 3.78GB |
Original model description:
---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
---
# Uploaded model
- **Developed by:** magnifi
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
Heisenger/babyai-ppo-experiments-2025-04-01_22-42-36 | Heisenger | 2025-04-01T22:44:11Z | 0 | 0 | peft | [
"peft",
"pytorch",
"safetensors",
"arxiv:1910.09700",
"base_model:meta-llama/Llama-3.2-3B-Instruct",
"base_model:adapter:meta-llama/Llama-3.2-3B-Instruct",
"region:us"
]
| null | 2025-04-01T22:42:41Z | ---
base_model: meta-llama/Llama-3.2-3B-Instruct
library_name: peft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
### Framework versions
- PEFT 0.15.1 |
kimminhtien/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-pensive_tropical_cheetah | kimminhtien | 2025-04-01T22:41:40Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"rl-swarm",
"grpo",
"gensyn",
"I am pensive tropical cheetah",
"trl",
"conversational",
"arxiv:2402.03300",
"base_model:Gensyn/Qwen2.5-0.5B-Instruct",
"base_model:finetune:Gensyn/Qwen2.5-0.5B-Instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T22:39:11Z | ---
base_model: Gensyn/Qwen2.5-0.5B-Instruct
library_name: transformers
model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-pensive_tropical_cheetah
tags:
- generated_from_trainer
- rl-swarm
- grpo
- gensyn
- I am pensive tropical cheetah
- trl
licence: license
---
# Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-pensive_tropical_cheetah
This model is a fine-tuned version of [Gensyn/Qwen2.5-0.5B-Instruct](https://huggingface.co/Gensyn/Qwen2.5-0.5B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="kimminhtien/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-pensive_tropical_cheetah", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
### Framework versions
- TRL: 0.15.2
- Transformers: 4.50.3
- Pytorch: 2.6.0
- Datasets: 3.5.0
- Tokenizers: 0.21.1
## Citations
Cite GRPO as:
```bibtex
@article{zhihong2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
vivek1192/merged_medicalQAnuslerp-hindi | vivek1192 | 2025-04-01T22:38:47Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"base_model:BioMistral/BioMistral-7B",
"base_model:merge:BioMistral/BioMistral-7B",
"base_model:OdiaGenAI/mistral_hindi_7b_base_v1",
"base_model:merge:OdiaGenAI/mistral_hindi_7b_base_v1",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:merge:mistralai/Mistral-7B-v0.1",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T22:35:29Z | ---
base_model:
- mistralai/Mistral-7B-v0.1
- BioMistral/BioMistral-7B
- OdiaGenAI/mistral_hindi_7b_base_v1
library_name: transformers
tags:
- mergekit
- merge
---
# merged_models
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the NuSLERP merge method using [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base.
### Models Merged
The following models were included in the merge:
* [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B)
* [OdiaGenAI/mistral_hindi_7b_base_v1](https://huggingface.co/OdiaGenAI/mistral_hindi_7b_base_v1)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: mistralai/Mistral-7B-v0.1
dtype: float16
merge_method: nuslerp
modules:
default:
slices:
- sources:
- layer_range: [0, 32]
model: BioMistral/BioMistral-7B
parameters:
density: 0.5
weight: 0.5
- layer_range: [0, 32]
model: OdiaGenAI/mistral_hindi_7b_base_v1
parameters:
density: 0.5
weight: 0.5
- layer_range: [0, 32]
model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: 1.0
normalize: 0.0
```
|
kostiantynk1205/40035d9c-af9d-485d-976b-90a28489d062 | kostiantynk1205 | 2025-04-01T22:38:44Z | 0 | 0 | peft | [
"peft",
"generated_from_trainer",
"base_model:Maykeye/TinyLLama-v0",
"base_model:adapter:Maykeye/TinyLLama-v0",
"region:us"
]
| null | 2025-04-01T22:38:38Z | ---
library_name: peft
tags:
- generated_from_trainer
base_model: Maykeye/TinyLLama-v0
model-index:
- name: kostiantynk1205/40035d9c-af9d-485d-976b-90a28489d062
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. -->
# kostiantynk1205/40035d9c-af9d-485d-976b-90a28489d062
This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 5.4354
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1 |
praneethkj/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-prowling_lazy_coyote | praneethkj | 2025-04-01T22:38:11Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"rl-swarm",
"grpo",
"gensyn",
"I am prowling lazy coyote",
"trl",
"conversational",
"arxiv:2402.03300",
"base_model:Gensyn/Qwen2.5-0.5B-Instruct",
"base_model:finetune:Gensyn/Qwen2.5-0.5B-Instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T22:28:31Z | ---
base_model: Gensyn/Qwen2.5-0.5B-Instruct
library_name: transformers
model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-prowling_lazy_coyote
tags:
- generated_from_trainer
- rl-swarm
- grpo
- gensyn
- I am prowling lazy coyote
- trl
licence: license
---
# Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-prowling_lazy_coyote
This model is a fine-tuned version of [Gensyn/Qwen2.5-0.5B-Instruct](https://huggingface.co/Gensyn/Qwen2.5-0.5B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="praneethkj/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-prowling_lazy_coyote", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
### Framework versions
- TRL: 0.15.2
- Transformers: 4.50.3
- Pytorch: 2.6.0
- Datasets: 3.5.0
- Tokenizers: 0.21.1
## Citations
Cite GRPO as:
```bibtex
@article{zhihong2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
bartowski/all-hands_openhands-lm-7b-v0.1-GGUF | bartowski | 2025-04-01T22:36:36Z | 0 | 0 | null | [
"gguf",
"agent",
"coding",
"text-generation",
"en",
"dataset:SWE-Gym/SWE-Gym",
"base_model:all-hands/openhands-lm-7b-v0.1",
"base_model:quantized:all-hands/openhands-lm-7b-v0.1",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
]
| text-generation | 2025-04-01T21:03:37Z | ---
quantized_by: bartowski
pipeline_tag: text-generation
base_model_relation: quantized
datasets:
- SWE-Gym/SWE-Gym
base_model: all-hands/openhands-lm-7b-v0.1
tags:
- agent
- coding
language:
- en
license: mit
---
## Llamacpp imatrix Quantizations of openhands-lm-7b-v0.1 by all-hands
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5010">b5010</a> for quantization.
Original model: https://huggingface.co/all-hands/openhands-lm-7b-v0.1
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project
## Prompt format
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [openhands-lm-7b-v0.1-bf16.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-bf16.gguf) | bf16 | 15.24GB | false | Full BF16 weights. |
| [openhands-lm-7b-v0.1-Q8_0.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-Q8_0.gguf) | Q8_0 | 8.10GB | false | Extremely high quality, generally unneeded but max available quant. |
| [openhands-lm-7b-v0.1-Q6_K_L.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-Q6_K_L.gguf) | Q6_K_L | 6.52GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [openhands-lm-7b-v0.1-Q6_K.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-Q6_K.gguf) | Q6_K | 6.25GB | false | Very high quality, near perfect, *recommended*. |
| [openhands-lm-7b-v0.1-Q5_K_L.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-Q5_K_L.gguf) | Q5_K_L | 5.78GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [openhands-lm-7b-v0.1-Q5_K_M.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-Q5_K_M.gguf) | Q5_K_M | 5.44GB | false | High quality, *recommended*. |
| [openhands-lm-7b-v0.1-Q5_K_S.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-Q5_K_S.gguf) | Q5_K_S | 5.32GB | false | High quality, *recommended*. |
| [openhands-lm-7b-v0.1-Q4_K_L.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-Q4_K_L.gguf) | Q4_K_L | 5.09GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [openhands-lm-7b-v0.1-Q4_1.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-Q4_1.gguf) | Q4_1 | 4.87GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [openhands-lm-7b-v0.1-Q4_K_M.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-Q4_K_M.gguf) | Q4_K_M | 4.68GB | false | Good quality, default size for most use cases, *recommended*. |
| [openhands-lm-7b-v0.1-Q3_K_XL.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-Q3_K_XL.gguf) | Q3_K_XL | 4.57GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [openhands-lm-7b-v0.1-Q4_K_S.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-Q4_K_S.gguf) | Q4_K_S | 4.46GB | false | Slightly lower quality with more space savings, *recommended*. |
| [openhands-lm-7b-v0.1-Q4_0.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-Q4_0.gguf) | Q4_0 | 4.44GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [openhands-lm-7b-v0.1-IQ4_NL.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-IQ4_NL.gguf) | IQ4_NL | 4.44GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [openhands-lm-7b-v0.1-IQ4_XS.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-IQ4_XS.gguf) | IQ4_XS | 4.22GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [openhands-lm-7b-v0.1-Q3_K_L.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-Q3_K_L.gguf) | Q3_K_L | 4.09GB | false | Lower quality but usable, good for low RAM availability. |
| [openhands-lm-7b-v0.1-Q3_K_M.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-Q3_K_M.gguf) | Q3_K_M | 3.81GB | false | Low quality. |
| [openhands-lm-7b-v0.1-IQ3_M.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-IQ3_M.gguf) | IQ3_M | 3.57GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [openhands-lm-7b-v0.1-Q2_K_L.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-Q2_K_L.gguf) | Q2_K_L | 3.55GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [openhands-lm-7b-v0.1-Q3_K_S.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-Q3_K_S.gguf) | Q3_K_S | 3.49GB | false | Low quality, not recommended. |
| [openhands-lm-7b-v0.1-IQ3_XS.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-IQ3_XS.gguf) | IQ3_XS | 3.35GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [openhands-lm-7b-v0.1-IQ3_XXS.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-IQ3_XXS.gguf) | IQ3_XXS | 3.11GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [openhands-lm-7b-v0.1-Q2_K.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-Q2_K.gguf) | Q2_K | 3.02GB | false | Very low quality but surprisingly usable. |
| [openhands-lm-7b-v0.1-IQ2_M.gguf](https://huggingface.co/bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/blob/main/all-hands_openhands-lm-7b-v0.1-IQ2_M.gguf) | IQ2_M | 2.78GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
## Embed/output weights
Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
## Downloading using huggingface-cli
<details>
<summary>Click to view download instructions</summary>
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/all-hands_openhands-lm-7b-v0.1-GGUF --include "all-hands_openhands-lm-7b-v0.1-Q4_K_M.gguf" --local-dir ./
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/all-hands_openhands-lm-7b-v0.1-GGUF --include "all-hands_openhands-lm-7b-v0.1-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (all-hands_openhands-lm-7b-v0.1-Q8_0) or download them all in place (./)
</details>
## ARM/AVX information
Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
<details>
<summary>Click to view Q4_0_X_X information (deprecated</summary>
I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
<details>
<summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
| model | size | params | backend | threads | test | t/s | % (vs Q4_0) |
| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% |
Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation
</details>
</details>
## Which file should I choose?
<details>
<summary>Click here for details</summary>
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
If you want to get more into the weeds, you can check out this extremely useful feature chart:
[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
</details>
## Credits
Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.
Thank you ZeroWw for the inspiration to experiment with embed/output.
Thank you to LM Studio for sponsoring my work.
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
yj-jeon/klue-roberta-base-klue-sts-mrc | yj-jeon | 2025-04-01T22:36:26Z | 0 | 0 | sentence-transformers | [
"sentence-transformers",
"safetensors",
"roberta",
"feature-extraction",
"sentence-similarity",
"transformers",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
]
| sentence-similarity | 2025-04-01T22:35:57Z | ---
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# {MODEL_NAME}
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 1097 with parameters:
```
{'batch_size': 16}
```
**Loss**:
`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
```
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
```
Parameters of the fit()-Method:
```
{
"epochs": 1,
"evaluation_steps": 0,
"evaluator": "NoneType",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 100,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
```
## Citing & Authors
<!--- Describe where people can find more information --> |
RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-int8wo-g128 | RoadToNowhere | 2025-04-01T22:35:59Z | 0 | 0 | null | [
"pytorch",
"qwen2",
"base_model:RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-int8wo-g128",
"base_model:quantized:RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-int8wo-g128",
"torchao",
"region:us"
]
| null | 2025-04-01T22:27:04Z | ---
base_model:
- RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-w8a8
---
# RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-w8a8 (Quantized)
## Description
This model is a quantized version of the original model `RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-w8a8`. It has been quantized using int8_weight_only quantization with torchao.
## Quantization Details
- **Quantization Type**: int8_weight_only
- **Group Size**: None
## Usage
You can use this model in your applications by loading it directly from the Hugging Face Hub:
```python
from transformers import AutoModel
model = AutoModel.from_pretrained("RoadToNowhere/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-w8a8") |
Rainneee/unsloth-llama-7b-function-calling | Rainneee | 2025-04-01T22:34:19Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/llama-2-7b-bnb-4bit",
"base_model:quantized:unsloth/llama-2-7b-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
]
| text-generation | 2025-04-01T22:02:39Z | ---
base_model: unsloth/llama-2-7b-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** Rainneee
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-2-7b-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
metricv/tl-whisper-large-v3 | metricv | 2025-04-01T22:34:16Z | 10 | 0 | transformers | [
"transformers",
"safetensors",
"whisper",
"feature-extraction",
"en",
"dataset:metricv/tl-whisper",
"base_model:openai/whisper-large-v3",
"base_model:finetune:openai/whisper-large-v3",
"endpoints_compatible",
"region:us"
]
| feature-extraction | 2024-08-31T20:55:52Z | ---
library_name: transformers
datasets:
- metricv/tl-whisper
language:
- en
base_model:
- openai/whisper-large-v3
---
# Model Card for Model ID
This is a finetuned OpenAI Whisper Large-V3 model, with data from Youtube channel TechLinked.
Dataset can be found at https://huggingface.co/datasets/metricv/tl-whisper
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** MetricSubs
<!-- - **Funded by [optional]:** [More Information Needed] -->
<!-- - **Shared by [optional]:** [More Information Needed] -->
- **Model type:** OpenAI Whisper Large-V3
- **Language(s) (NLP):** Multi-Lingual (English focused)
<!-- - **License:** [More Information Needed] -->
- **Finetuned from model [optional]:** OpenAI Whisper Large-V3
|
sfai-temp-reasoning-model/qwen2.5_coder_32b-FilteredGretelAI-phase1-iter80 | sfai-temp-reasoning-model | 2025-04-01T22:34:04Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T22:14:17Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
WarriorG/small | WarriorG | 2025-04-01T22:32:43Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2025-04-01T15:39:55Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf | RichardErkhov | 2025-04-01T22:30:13Z | 0 | 0 | null | [
"gguf",
"endpoints_compatible",
"region:us",
"conversational"
]
| null | 2025-04-01T21:27:59Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Phi3_intent_v45_3_w_unknown_7_lr_0.002 - GGUF
- Model creator: https://huggingface.co/magnifi/
- Original model: https://huggingface.co/magnifi/Phi3_intent_v45_3_w_unknown_7_lr_0.002/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q2_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q2_K.gguf) | Q2_K | 1.35GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.IQ3_XS.gguf) | IQ3_XS | 1.49GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.IQ3_S.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.IQ3_S.gguf) | IQ3_S | 1.57GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q3_K_S.gguf) | Q3_K_S | 1.57GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.IQ3_M.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.IQ3_M.gguf) | IQ3_M | 1.65GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q3_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q3_K.gguf) | Q3_K | 1.75GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q3_K_M.gguf) | Q3_K_M | 1.75GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q3_K_L.gguf) | Q3_K_L | 1.9GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.IQ4_XS.gguf) | IQ4_XS | 1.93GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q4_0.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q4_0.gguf) | Q4_0 | 2.03GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.IQ4_NL.gguf) | IQ4_NL | 2.04GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q4_K_S.gguf) | Q4_K_S | 2.04GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q4_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q4_K.gguf) | Q4_K | 2.16GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q4_K_M.gguf) | Q4_K_M | 2.16GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q4_1.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q4_1.gguf) | Q4_1 | 2.24GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q5_0.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q5_0.gguf) | Q5_0 | 2.46GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q5_K_S.gguf) | Q5_K_S | 2.46GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q5_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q5_K.gguf) | Q5_K | 2.53GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q5_K_M.gguf) | Q5_K_M | 2.53GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q5_1.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q5_1.gguf) | Q5_1 | 2.68GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q6_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q6_K.gguf) | Q6_K | 2.92GB |
| [Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q8_0.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_3_w_unknown_7_lr_0.002-gguf/blob/main/Phi3_intent_v45_3_w_unknown_7_lr_0.002.Q8_0.gguf) | Q8_0 | 3.78GB |
Original model description:
---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
---
# Uploaded model
- **Developed by:** magnifi
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
vivek1192/merged_medicalQAbreadcrumbs_ties-hindi | vivek1192 | 2025-04-01T22:29:37Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"arxiv:2312.06795",
"base_model:BioMistral/BioMistral-7B",
"base_model:merge:BioMistral/BioMistral-7B",
"base_model:OdiaGenAI/mistral_hindi_7b_base_v1",
"base_model:merge:OdiaGenAI/mistral_hindi_7b_base_v1",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:merge:mistralai/Mistral-7B-v0.1",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T22:26:17Z | ---
base_model:
- mistralai/Mistral-7B-v0.1
- BioMistral/BioMistral-7B
- OdiaGenAI/mistral_hindi_7b_base_v1
library_name: transformers
tags:
- mergekit
- merge
---
# merged_models
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [Model Breadcrumbs with TIES](https://arxiv.org/abs/2312.06795) merge method using [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base.
### Models Merged
The following models were included in the merge:
* [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B)
* [OdiaGenAI/mistral_hindi_7b_base_v1](https://huggingface.co/OdiaGenAI/mistral_hindi_7b_base_v1)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: mistralai/Mistral-7B-v0.1
dtype: float16
merge_method: breadcrumbs_ties
modules:
default:
slices:
- sources:
- layer_range: [0, 32]
model: BioMistral/BioMistral-7B
parameters:
density: 0.5
weight: 0.5
- layer_range: [0, 32]
model: OdiaGenAI/mistral_hindi_7b_base_v1
parameters:
density: 0.5
weight: 0.5
- layer_range: [0, 32]
model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: 1.0
normalize: 0.0
```
|
nanocoh/lora_model4 | nanocoh | 2025-04-01T22:28:06Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"mistral",
"trl",
"en",
"base_model:unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
"base_model:finetune:unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2025-04-01T22:27:57Z | ---
base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** nanocoh
- **License:** apache-2.0
- **Finetuned from model :** unsloth/mistral-7b-instruct-v0.3-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
MinaMila/llama_instbase_Adult_8ep_42 | MinaMila | 2025-04-01T22:27:41Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/Meta-Llama-3.1-8B-Instruct",
"base_model:finetune:unsloth/Meta-Llama-3.1-8B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T22:24:36Z | ---
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** MinaMila
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-Instruct
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
mradermacher/TableLLM-Qwen2-7B-GGUF | mradermacher | 2025-04-01T22:25:09Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:Multilingual-Multimodal-NLP/TableLLM-Qwen2-7B",
"base_model:quantized:Multilingual-Multimodal-NLP/TableLLM-Qwen2-7B",
"license:cc-by-4.0",
"endpoints_compatible",
"region:us",
"conversational"
]
| null | 2025-04-01T13:24:06Z | ---
base_model: Multilingual-Multimodal-NLP/TableLLM-Qwen2-7B
language:
- en
library_name: transformers
license: cc-by-4.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/Multilingual-Multimodal-NLP/TableLLM-Qwen2-7B
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/TableLLM-Qwen2-7B-GGUF/resolve/main/TableLLM-Qwen2-7B.Q2_K.gguf) | Q2_K | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/TableLLM-Qwen2-7B-GGUF/resolve/main/TableLLM-Qwen2-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/TableLLM-Qwen2-7B-GGUF/resolve/main/TableLLM-Qwen2-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/TableLLM-Qwen2-7B-GGUF/resolve/main/TableLLM-Qwen2-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/TableLLM-Qwen2-7B-GGUF/resolve/main/TableLLM-Qwen2-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/TableLLM-Qwen2-7B-GGUF/resolve/main/TableLLM-Qwen2-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/TableLLM-Qwen2-7B-GGUF/resolve/main/TableLLM-Qwen2-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/TableLLM-Qwen2-7B-GGUF/resolve/main/TableLLM-Qwen2-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/TableLLM-Qwen2-7B-GGUF/resolve/main/TableLLM-Qwen2-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/TableLLM-Qwen2-7B-GGUF/resolve/main/TableLLM-Qwen2-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/TableLLM-Qwen2-7B-GGUF/resolve/main/TableLLM-Qwen2-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/TableLLM-Qwen2-7B-GGUF/resolve/main/TableLLM-Qwen2-7B.f16.gguf) | f16 | 15.3 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
methinkss/thinktests | methinkss | 2025-04-01T22:24:30Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T21:14:25Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
wjustus01/model | wjustus01 | 2025-04-01T22:23:53Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"base_model:unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit",
"base_model:quantized:unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
| null | 2025-04-01T22:21:37Z | ---
base_model: unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** wjustus01
- **License:** apache-2.0
- **Finetuned from model :** unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
Noxgam/llama3-finetuned | Noxgam | 2025-04-01T22:21:58Z | 0 | 0 | peft | [
"peft",
"safetensors",
"llama",
"trl",
"sft",
"generated_from_trainer",
"dataset:generator",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"base_model:adapter:meta-llama/Meta-Llama-3-8B-Instruct",
"license:llama3",
"region:us"
]
| null | 2025-04-01T20:11:28Z | ---
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
library_name: peft
model-index:
- name: llama3-finetuned
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. -->
# llama3-finetuned
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.11.0
- Transformers 4.40.0
- Pytorch 2.3.0+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1 |
inrainbws/resnet_r16_mlora_exp | inrainbws | 2025-04-01T22:20:57Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2025-04-01T22:20:55Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
dananddan/dbnging | dananddan | 2025-04-01T22:17:32Z | 0 | 0 | diffusers | [
"diffusers",
"flux",
"lora",
"replicate",
"text-to-image",
"en",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
]
| text-to-image | 2025-04-01T21:49:09Z | ---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: "black-forest-labs/FLUX.1-dev"
pipeline_tag: text-to-image
# widget:
# - text: >-
# prompt
# output:
# url: https://...
instance_prompt: dbnging
---
# Dbnging
<Gallery />
## About this LoRA
This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI.
It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `dbnging` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "dbnging",
"lora_weights": "https://huggingface.co/dananddan/dbnging/resolve/main/lora.safetensors"
}
output = replicate.run(
"black-forest-labs/flux-dev-lora",
input=input
)
for index, item in enumerate(output):
with open(f"output_{index}.webp", "wb") as file:
file.write(item.read())
```
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('dananddan/dbnging', weight_name='lora.safetensors')
image = pipeline('dbnging').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
## Training details
- Steps: 2541
- Learning rate: 0.0004
- LoRA rank: 41
## Contribute your own examples
You can use the [community tab](https://huggingface.co/dananddan/dbnging/discussions) to add images that show off what you’ve made with this LoRA.
|
MinaMila/llama_instbase_Adult_7ep_42 | MinaMila | 2025-04-01T22:17:05Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/Meta-Llama-3.1-8B-Instruct",
"base_model:finetune:unsloth/Meta-Llama-3.1-8B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T22:13:56Z | ---
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** MinaMila
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-Instruct
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
gupshreeya0504/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-bellowing_lithe_pigeon | gupshreeya0504 | 2025-04-01T22:16:53Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"rl-swarm",
"grpo",
"gensyn",
"I am bellowing lithe pigeon",
"trl",
"conversational",
"arxiv:2402.03300",
"base_model:Gensyn/Qwen2.5-0.5B-Instruct",
"base_model:finetune:Gensyn/Qwen2.5-0.5B-Instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T19:59:39Z | ---
base_model: Gensyn/Qwen2.5-0.5B-Instruct
library_name: transformers
model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-bellowing_lithe_pigeon
tags:
- generated_from_trainer
- rl-swarm
- grpo
- gensyn
- I am bellowing lithe pigeon
- trl
licence: license
---
# Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-bellowing_lithe_pigeon
This model is a fine-tuned version of [Gensyn/Qwen2.5-0.5B-Instruct](https://huggingface.co/Gensyn/Qwen2.5-0.5B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="gupshreeya0504/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-bellowing_lithe_pigeon", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
### Framework versions
- TRL: 0.15.2
- Transformers: 4.50.3
- Pytorch: 2.5.1
- Datasets: 3.5.0
- Tokenizers: 0.21.1
## Citations
Cite GRPO as:
```bibtex
@article{zhihong2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
nuriyev/Qwen2.5-0.5B-Instruct-medical-kpo | nuriyev | 2025-04-01T22:16:10Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"trl",
"kto",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T21:58:12Z | ---
library_name: transformers
tags:
- trl
- kto
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
marcuscedricridia/llamalicious3.2-1B-GGUF | marcuscedricridia | 2025-04-01T22:15:14Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
| null | 2025-04-01T22:14:11Z | ---
base_model: unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** marcuscedricridia
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
DanSarm/receipt-construction-model | DanSarm | 2025-04-01T22:13:47Z | 92 | 0 | transformers | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:DanSarm/receipt-core-model",
"base_model:finetune:DanSarm/receipt-core-model",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text2text-generation | 2025-01-29T21:40:29Z | ---
library_name: transformers
license: apache-2.0
base_model: DanSarm/receipt-core-model
tags:
- generated_from_trainer
model-index:
- name: receipt-construction-model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# receipt-construction-model
This model is a fine-tuned version of [DanSarm/receipt-core-model](https://huggingface.co/DanSarm/receipt-core-model) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2963
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 500
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.1652 | 1.0 | 56 | 0.4196 |
| 0.4227 | 2.0 | 112 | 0.2893 |
| 0.3059 | 3.0 | 168 | 0.2561 |
| 0.2414 | 4.0 | 224 | 0.2288 |
| 0.2046 | 5.0 | 280 | 0.2278 |
| 0.1767 | 6.0 | 336 | 0.2160 |
| 0.1565 | 7.0 | 392 | 0.2124 |
| 0.1384 | 8.0 | 448 | 0.2092 |
| 0.1288 | 9.0 | 504 | 0.2077 |
| 0.116 | 10.0 | 560 | 0.2103 |
| 0.1069 | 11.0 | 616 | 0.2136 |
| 0.0966 | 12.0 | 672 | 0.2215 |
| 0.086 | 13.0 | 728 | 0.2201 |
| 0.0822 | 14.0 | 784 | 0.2263 |
| 0.0764 | 15.0 | 840 | 0.2314 |
| 0.0697 | 16.0 | 896 | 0.2298 |
| 0.0677 | 17.0 | 952 | 0.2316 |
| 0.0623 | 18.0 | 1008 | 0.2306 |
| 0.0588 | 19.0 | 1064 | 0.2467 |
| 0.0555 | 20.0 | 1120 | 0.2432 |
| 0.0518 | 21.0 | 1176 | 0.2484 |
| 0.0488 | 22.0 | 1232 | 0.2570 |
| 0.0453 | 23.0 | 1288 | 0.2377 |
| 0.0452 | 24.0 | 1344 | 0.2531 |
| 0.0399 | 25.0 | 1400 | 0.2538 |
| 0.0347 | 26.0 | 1456 | 0.2529 |
| 0.032 | 27.0 | 1512 | 0.2583 |
| 0.0312 | 28.0 | 1568 | 0.2525 |
| 0.0282 | 29.0 | 1624 | 0.2631 |
| 0.0274 | 30.0 | 1680 | 0.2609 |
| 0.0266 | 31.0 | 1736 | 0.2574 |
| 0.0265 | 32.0 | 1792 | 0.2630 |
| 0.0221 | 33.0 | 1848 | 0.2611 |
| 0.0218 | 34.0 | 1904 | 0.2673 |
| 0.0194 | 35.0 | 1960 | 0.2693 |
| 0.0164 | 36.0 | 2016 | 0.2663 |
| 0.0183 | 37.0 | 2072 | 0.2655 |
| 0.0149 | 38.0 | 2128 | 0.2685 |
| 0.0156 | 39.0 | 2184 | 0.2604 |
| 0.0157 | 40.0 | 2240 | 0.2684 |
| 0.0149 | 41.0 | 2296 | 0.2697 |
| 0.0137 | 42.0 | 2352 | 0.2779 |
| 0.0116 | 43.0 | 2408 | 0.2738 |
| 0.0116 | 44.0 | 2464 | 0.2760 |
| 0.011 | 45.0 | 2520 | 0.2824 |
| 0.0109 | 46.0 | 2576 | 0.2894 |
| 0.0094 | 47.0 | 2632 | 0.2818 |
| 0.0098 | 48.0 | 2688 | 0.2885 |
| 0.0089 | 49.0 | 2744 | 0.2850 |
| 0.01 | 50.0 | 2800 | 0.2857 |
| 0.0096 | 51.0 | 2856 | 0.2855 |
| 0.0084 | 52.0 | 2912 | 0.2904 |
| 0.0088 | 53.0 | 2968 | 0.2871 |
| 0.0092 | 54.0 | 3024 | 0.2878 |
| 0.008 | 55.0 | 3080 | 0.2876 |
| 0.0072 | 56.0 | 3136 | 0.2904 |
| 0.0073 | 57.0 | 3192 | 0.2808 |
| 0.0065 | 58.0 | 3248 | 0.2978 |
| 0.0059 | 59.0 | 3304 | 0.2963 |
### Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1
|
lesso16/688208f2-f57e-43b1-b04a-1ae387b3582e | lesso16 | 2025-04-01T22:12:36Z | 0 | 0 | peft | [
"peft",
"safetensors",
"qwen2",
"axolotl",
"generated_from_trainer",
"base_model:Qwen/Qwen2-0.5B-Instruct",
"base_model:adapter:Qwen/Qwen2-0.5B-Instruct",
"license:apache-2.0",
"region:us"
]
| null | 2025-04-01T21:44:29Z | ---
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2-0.5B-Instruct
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 688208f2-f57e-43b1-b04a-1ae387b3582e
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.1`
```yaml
adapter: lora
base_model: Qwen/Qwen2-0.5B-Instruct
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
- d753e273ca3baf00_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/d753e273ca3baf00_train_data.json
type:
field_instruction: instruction
field_output: output
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
do_eval: true
early_stopping_patience: 3
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 500
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: true
hub_model_id: lesso16/688208f2-f57e-43b1-b04a-1ae387b3582e
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.000216
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 50
lora_alpha: 128
lora_dropout: 0.15
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 500
micro_batch_size: 4
mlflow_experiment_name: /tmp/d753e273ca3baf00_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optimizer: adamw_torch_fused
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 500
saves_per_epoch: null
seed: 160
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: e8f0a504-5aee-4d71-8662-6b5b0f9d52f1
wandb_project: 16a
wandb_run: your_name
wandb_runid: e8f0a504-5aee-4d71-8662-6b5b0f9d52f1
warmup_steps: 100
weight_decay: 0.0
xformers_attention: null
```
</details><br>
# 688208f2-f57e-43b1-b04a-1ae387b3582e
This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.9707
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.000216
- train_batch_size: 4
- eval_batch_size: 4
- seed: 160
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 500
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log | 0.0003 | 1 | 1.1171 |
| 0.9944 | 0.1701 | 500 | 0.9707 |
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1 |
glif-loradex-trainer/Swap_agrawal14_creamy_surreal_v1 | glif-loradex-trainer | 2025-04-01T22:09:27Z | 0 | 0 | diffusers | [
"diffusers",
"text-to-image",
"template:sd-lora",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:finetune:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us",
"flux",
"lora",
"base_model:adapter:black-forest-labs/FLUX.1-dev"
]
| text-to-image | 2025-04-01T22:09:19Z | ---
tags:
- diffusers
- text-to-image
- template:sd-lora
- base_model:black-forest-labs/FLUX.1-dev
- base_model:finetune:black-forest-labs/FLUX.1-dev
- license:other
- region:us
- flux
- lora
widget:
- output:
url: samples/1743545235797__000001500_0.jpg
text: penguin eating rice cake icecreamyyyy_lv
- output:
url: samples/1743545260851__000001500_1.jpg
text: Pug demonstrating how to brush your teeth icecreamyyyy_lv
- output:
url: samples/1743545285925__000001500_2.jpg
text: A female silver vampire with sword icecreamyyyy_lv
- output:
url: samples/1743545310990__000001500_3.jpg
text: A group of friends sitting in classroom icecreamyyyy_lv
- output:
url: samples/1743545336175__000001500_4.jpg
text: Mona Lisa and Donald Trump having wine icecreamyyyy_lv
base_model: black-forest-labs/FLUX.1-dev
trigger: "icecreamyyyy_lv"
instance_prompt: "icecreamyyyy_lv"
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
---
# creamy_surreal_v1
Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `Swap_agrawal14`.
<Gallery />
## Trigger words
You should use `icecreamyyyy_lv` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/glif-loradex-trainer/Swap_agrawal14_creamy_surreal_v1/tree/main) them in the Files & versions tab.
## License
This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
|
C10X/merged_model_16bit_dss | C10X | 2025-04-01T22:09:07Z | 0 | 0 | transformers | [
"transformers",
"pytorch",
"qwen2",
"text-generation",
"unsloth",
"trl",
"sft",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T22:08:36Z | ---
library_name: transformers
tags:
- unsloth
- trl
- sft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
MinaMila/llama_instbase_Adult_6ep_42 | MinaMila | 2025-04-01T22:06:11Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/Meta-Llama-3.1-8B-Instruct",
"base_model:finetune:unsloth/Meta-Llama-3.1-8B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T22:02:59Z | ---
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** MinaMila
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-Instruct
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
LingjieBao1998/Qwen2-0.5B-GRPO-test | LingjieBao1998 | 2025-04-01T22:05:01Z | 0 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"generated_from_trainer",
"trl",
"grpo",
"dataset:AI-MO/NuminaMath-TIR",
"arxiv:2402.03300",
"base_model:Qwen/Qwen2-0.5B-Instruct",
"base_model:finetune:Qwen/Qwen2-0.5B-Instruct",
"endpoints_compatible",
"region:us"
]
| null | 2025-04-01T19:14:13Z | ---
base_model: Qwen/Qwen2-0.5B-Instruct
datasets: AI-MO/NuminaMath-TIR
library_name: transformers
model_name: Qwen2-0.5B-GRPO-test
tags:
- generated_from_trainer
- trl
- grpo
licence: license
---
# Model Card for Qwen2-0.5B-GRPO-test
This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on the [AI-MO/NuminaMath-TIR](https://huggingface.co/datasets/AI-MO/NuminaMath-TIR) dataset.
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="LingjieBao1998/Qwen2-0.5B-GRPO-test", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
### Framework versions
- TRL: 0.16.0
- Transformers: 4.50.2
- Pytorch: 2.6.0+cu124
- Datasets: 3.5.0
- Tokenizers: 0.21.1
## Citations
Cite GRPO as:
```bibtex
@article{zhihong2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
ntnu-smil/whisper-large-v3-sandi-train-dev-6 | ntnu-smil | 2025-04-01T22:04:18Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"wft",
"whisper",
"automatic-speech-recognition",
"audio",
"speech",
"generated_from_trainer",
"en",
"dataset:ntnu-smil/sandi2025-ds",
"base_model:ntnu-smil/whisper-large-v3-sandi-train-dev-1-merged",
"base_model:adapter:ntnu-smil/whisper-large-v3-sandi-train-dev-1-merged",
"license:apache-2.0",
"model-index",
"region:us"
]
| automatic-speech-recognition | 2025-04-01T20:25:17Z | ---
library_name: peft
language:
- en
license: apache-2.0
base_model: ntnu-smil/whisper-large-v3-sandi-train-dev-1-merged
tags:
- wft
- whisper
- automatic-speech-recognition
- audio
- speech
- generated_from_trainer
datasets:
- ntnu-smil/sandi2025-ds
metrics:
- wer
model-index:
- name: whisper-large-v3-sandi-train-dev-6
results:
- task:
type: automatic-speech-recognition
name: Automatic Speech Recognition
dataset:
name: ntnu-smil/sandi2025-ds
type: ntnu-smil/sandi2025-ds
metrics:
- type: wer
value: 195.17397318242394
name: Wer
---
<!-- 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. -->
# whisper-large-v3-sandi-train-dev-6
This model is a fine-tuned version of [ntnu-smil/whisper-large-v3-sandi-train-dev-1-merged](https://huggingface.co/ntnu-smil/whisper-large-v3-sandi-train-dev-1-merged) on the ntnu-smil/sandi2025-ds dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6141
- Wer: 195.1740
- Cer: 103.8099
- Decode Runtime: 302.6853
- Wer Runtime: 0.1962
- Cer Runtime: 0.3691
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Use adamw_torch with betas=(0.9,0.98) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- training_steps: 392
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Decode Runtime | Wer Runtime | Cer Runtime |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------------:|:-----------:|:-----------:|
| 0.5955 | 1.0 | 56 | 0.7708 | 199.7404 | 87.4116 | 297.6150 | 0.1968 | 0.3600 |
| 0.583 | 2.0 | 112 | 0.6938 | 198.2328 | 86.9214 | 301.9292 | 0.1913 | 0.3584 |
| 0.4582 | 3.0 | 168 | 0.6606 | 197.2721 | 89.4544 | 308.3536 | 0.1964 | 0.3621 |
| 0.5814 | 4.0 | 224 | 0.6398 | 196.7833 | 95.2803 | 300.6860 | 0.1962 | 0.3622 |
| 0.4986 | 5.0 | 280 | 0.6255 | 196.2085 | 95.9717 | 302.4188 | 0.1945 | 0.3630 |
| 0.4225 | 6.0 | 336 | 0.6170 | 195.3584 | 103.5412 | 301.1984 | 0.1943 | 0.3702 |
| 0.465 | 7.0 | 392 | 0.6141 | 195.1740 | 103.8099 | 302.6853 | 0.1962 | 0.3691 |
### Framework versions
- PEFT 0.15.1
- Transformers 4.48.3
- Pytorch 2.6.0
- Datasets 3.5.0
- Tokenizers 0.21.1 |
mradermacher/asm2asm-deepseek-500k-2ep-mac-GGUF | mradermacher | 2025-04-01T22:03:48Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:ahmedheakl/asm2asm-deepseek-500k-2ep-mac",
"base_model:quantized:ahmedheakl/asm2asm-deepseek-500k-2ep-mac",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
]
| null | 2025-04-01T21:54:16Z | ---
base_model: ahmedheakl/asm2asm-deepseek-500k-2ep-mac
language:
- en
library_name: transformers
license: mit
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/ahmedheakl/asm2asm-deepseek-500k-2ep-mac
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/asm2asm-deepseek-500k-2ep-mac-GGUF/resolve/main/asm2asm-deepseek-500k-2ep-mac.Q2_K.gguf) | Q2_K | 0.7 | |
| [GGUF](https://huggingface.co/mradermacher/asm2asm-deepseek-500k-2ep-mac-GGUF/resolve/main/asm2asm-deepseek-500k-2ep-mac.Q3_K_S.gguf) | Q3_K_S | 0.7 | |
| [GGUF](https://huggingface.co/mradermacher/asm2asm-deepseek-500k-2ep-mac-GGUF/resolve/main/asm2asm-deepseek-500k-2ep-mac.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/asm2asm-deepseek-500k-2ep-mac-GGUF/resolve/main/asm2asm-deepseek-500k-2ep-mac.Q3_K_L.gguf) | Q3_K_L | 0.8 | |
| [GGUF](https://huggingface.co/mradermacher/asm2asm-deepseek-500k-2ep-mac-GGUF/resolve/main/asm2asm-deepseek-500k-2ep-mac.IQ4_XS.gguf) | IQ4_XS | 0.9 | |
| [GGUF](https://huggingface.co/mradermacher/asm2asm-deepseek-500k-2ep-mac-GGUF/resolve/main/asm2asm-deepseek-500k-2ep-mac.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/asm2asm-deepseek-500k-2ep-mac-GGUF/resolve/main/asm2asm-deepseek-500k-2ep-mac.Q4_K_M.gguf) | Q4_K_M | 1.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/asm2asm-deepseek-500k-2ep-mac-GGUF/resolve/main/asm2asm-deepseek-500k-2ep-mac.Q5_K_S.gguf) | Q5_K_S | 1.1 | |
| [GGUF](https://huggingface.co/mradermacher/asm2asm-deepseek-500k-2ep-mac-GGUF/resolve/main/asm2asm-deepseek-500k-2ep-mac.Q5_K_M.gguf) | Q5_K_M | 1.1 | |
| [GGUF](https://huggingface.co/mradermacher/asm2asm-deepseek-500k-2ep-mac-GGUF/resolve/main/asm2asm-deepseek-500k-2ep-mac.Q6_K.gguf) | Q6_K | 1.3 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/asm2asm-deepseek-500k-2ep-mac-GGUF/resolve/main/asm2asm-deepseek-500k-2ep-mac.Q8_0.gguf) | Q8_0 | 1.5 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/asm2asm-deepseek-500k-2ep-mac-GGUF/resolve/main/asm2asm-deepseek-500k-2ep-mac.f16.gguf) | f16 | 2.8 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
marcuscedricridia/llamalicious3.2-1B | marcuscedricridia | 2025-04-01T22:01:46Z | 0 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T22:00:31Z | ---
base_model: unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** marcuscedricridia
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-1b-instruct-unsloth-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
inrainbws/resnet_r16_lora | inrainbws | 2025-04-01T22:01:15Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2025-04-01T19:49:08Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Sufi2425/FrenchLlama-3.2-1B-Instruct | Sufi2425 | 2025-04-01T21:58:12Z | 6 | 0 | null | [
"safetensors",
"llama",
"grammar",
"languages",
"french",
"explanations",
"learning",
"en",
"fr",
"dataset:Sufi2425/French_Grammar_Explanations",
"base_model:meta-llama/Llama-3.2-1B-Instruct",
"base_model:finetune:meta-llama/Llama-3.2-1B-Instruct",
"license:apache-2.0",
"region:us"
]
| null | 2024-12-22T23:43:40Z | ---
license: apache-2.0
language:
- en
- fr
base_model:
- meta-llama/Llama-3.2-1B-Instruct
tags:
- grammar
- languages
- french
- explanations
- learning
datasets:
- Sufi2425/French_Grammar_Explanations
---
[](https://ko-fi.com/I2I1VJQ1O)
This is a custom-built language model, fine-tuned from Meta's Llama 3.2 1B Instruct. I trained it on a dataset of 535 examples that explain French grammar.
It's basically my experiment to see how much a tiny LLM can actually learn to produce coherent outputs.
As an added note, I will be updating this every once in a while. |
chloeli/qwen-2.5-0.5B-instruct-sft-lora-countdown-search-react-seq8k-5k | chloeli | 2025-04-01T21:57:39Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"alignment-handbook",
"trl",
"sft",
"conversational",
"dataset:MelinaLaimon/stream-of-search",
"base_model:Qwen/Qwen2.5-0.5B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-0.5B-Instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T21:34:52Z | ---
base_model: Qwen/Qwen2.5-0.5B-Instruct
datasets: MelinaLaimon/stream-of-search
library_name: transformers
model_name: Qwen/Qwen2.5-0.5B-Instruct
tags:
- generated_from_trainer
- alignment-handbook
- trl
- sft
licence: license
---
# Model Card for Qwen/Qwen2.5-0.5B-Instruct
This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on the [MelinaLaimon/stream-of-search](https://huggingface.co/datasets/MelinaLaimon/stream-of-search) dataset.
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="chloeli/qwen-2.5-0.5B-instruct-sft-lora-countdown-search-react-seq8k-5k", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/chloeli/huggingface/runs/fcgmyt9b)
This model was trained with SFT.
### Framework versions
- TRL: 0.15.2
- Transformers: 4.49.0
- Pytorch: 2.6.0
- Datasets: 3.3.2
- Tokenizers: 0.21.0
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
JLTastet/poca-SoccerTwos | JLTastet | 2025-04-01T21:57:30Z | 0 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"SoccerTwos",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
]
| reinforcement-learning | 2025-04-01T21:57:21Z | ---
library_name: ml-agents
tags:
- SoccerTwos
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SoccerTwos
---
# **poca** Agent playing **SoccerTwos**
This is a trained model of a **poca** agent playing **SoccerTwos**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: JLTastet/poca-SoccerTwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Sufi2425/FrenchLlama-3.2-3B-Instruct-GGUF | Sufi2425 | 2025-04-01T21:56:34Z | 9 | 0 | null | [
"gguf",
"french",
"english",
"grammar",
"text-generation",
"en",
"fr",
"dataset:Sufi2425/French_Grammar_Explanations",
"base_model:Sufi2425/FrenchLlama-3.2-3B-Instruct",
"base_model:quantized:Sufi2425/FrenchLlama-3.2-3B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
| text-generation | 2024-12-29T19:02:05Z | ---
license: apache-2.0
datasets:
- Sufi2425/French_Grammar_Explanations
language:
- en
- fr
base_model:
- Sufi2425/FrenchLlama-3.2-3B-Instruct
pipeline_tag: text-generation
tags:
- french
- english
- grammar
---
[](https://ko-fi.com/I2I1VJQ1O)
# FrenchLlama - The French Grammar Tutor
This is a custom-built language model, fine-tuned from Meta's Llama 3.2 3B Instruct. I trained the first iteration on a dataset of 1500+ examples that explain French grammar.
It's basically my experiment to see how much a tiny LLM can actually learn to produce coherent outputs.
The version you are looking at is a quantization for use in apps like LM Studio. Because the 3B model is heavier than the 1B one, a few more quants are available.
As an added note, I will be updating this every once in a while. As of December 29, 2024, I have decided to include all versions as downloadable ggufs.
I used the following settings during training:
```python
training_args = TrainingArguments(
output_dir="./llama_fine_tuned", # Changed output directory
per_device_train_batch_size=3,
gradient_accumulation_steps=4,
learning_rate=1e-3,
num_train_epochs=5,
weight_decay=0.01,
warmup_steps=100,
save_steps=50,
fp16=False,
bf16=True,
logging_steps=50,
save_total_limit=2,
report_to='none'
)
```
Moreover, I've noticed that **using a system prompt** to steer the output in the right direction appears to make a noticeable impact on both the base Llama 3.2 1B model and FrenchLlama. This applies to the 3B version of the models as well.
```
You are FrenchLlama, a highly knowledgeable and polite AI assistant whose primary purpose is to help users improve their understanding of French grammar. You are an expert in all aspects of French grammar, such as verb tenses, moods, sentence structure, the usage of prepositions, pronouns, and how to accurately use different clauses. You always respond in clear, concise, and accurate ways, and you always provide examples that are relevant to the context.
Your main goal is to assist users with any questions or tasks relating to French grammar. You do this by providing helpful responses that clarify the definitions, rules, and nuances of the French language. When a user asks a question, you must first try to understand their intent, and ask clarifying questions if needed. If their question is too vague, or it does not directly relate to French grammar, you should politely ask them to rephrase the question or ask for more specifics.
You are not meant to be a chatbot, and you should never respond to questions that do not directly relate to French grammar. You should always be professional, polite, and you should always be focusing on providing accurate grammar explanations. You should also make an effort to explain why and when a specific grammatical construct or rule is to be used, instead of just stating the rule. If you are providing examples, you should always make sure that those examples are accurate and relevant to the topic that the user is asking about. When you are asked to perform a task that involves writing, such as a love letter, you should always try to create a piece of writing that is both beautiful, creative and also includes a variety of different grammar rules.
```
## Available Versions (3B)
- [FrenchLlama_v1-3.2-3B-Instruct-Q8_0.gguf](./FrenchLlama_v1-3.2-3B-Instruct-Q8_0.gguf)
## Example Outputs
The 1B family of FrenchLlama models was in all honesty a bit of a disaster in my eyes, but it was also tons of fun seeing them come to life and actually produce **results**!
The very first version of the 3B version of FrenchLlama shows a significant improvement in French grammar and explanations, displaying significantly fewer quirks. I'm certain that with the right training and the right settings, tiny LLMs can be finetuned to the point of matching SOTA-level LLMs at very specific tasks. This could pave the way for router-based architectures to skyrocket, where a network of field-specific LLMs infer based on the user's input.
Unlike MoE (Mixture of Experts), these architectures (I call my version CAMR - Context-Aware Model Routing) use a routing model which mounts the appropriate finetuned LLMs (ideally small ones) to answer domain-specific inquiries. Because most people can't run massive LLMs on their local hardware, networks of tiny LLMs being mounted based on the router model's interpretation of the user input can democratize the use of local LLMs while ensuring higher-quality responses.
1. Verbe Tense Explanations
`User: What is the 'passé composé'?`
```
The 'passé composé' (past completed) is one of the main tenses in French. It's used to describe an action that was completed at a specific time in the past. The tense is formed by combining the auxiliary verb 'avoir' or 'être' with the past participle of the main verb.
For example:
- 'J'ai mangé une pomme.' (I ate an apple.)
- 'Elle est allée au parc.' (She went to the park.)
The choice between 'avoir' and 'être' as the auxiliary depends on the main verb. If the main verb is a regular verb that ends in '-ir,' use 'avoir'; if it's a regular verb that ends in '-re,' use 'être'; or use an irregular verb, which will have its own rules.
The past participle must agree with the subject in gender and number when used as an adjective. When used with the auxiliary verb to form the tense, it remains the same regardless of gender and number of the subject.
For example:
- 'Elle a mangé la pomme.' (She ate the apple.) The 'mangé' agrees with 'elle', which is feminine singular.
- 'Ils ont mangé les pommes.' (They ate the apples.) The 'mangé' does not change, even though there are masculine plural subjects.
```
This first example is a pretty decent explanation of the past compose tense in French. Key mistakes to point out:
1. The English translation of the tense is **Past Compose**, not Past Completed as claimed by FrenchLlama.
2. FrenchLlama incorrectly explains that the choice between the two auxiliary verbs 'avoir' and 'être' depends on the suffix of the main verb. In truth, there is a group of verbs that require 'être', but this is determined by whether a verb is intransitive or transitive.
3. FrenchLlama also says that irregular verbs have their own rules, which is a fabrication in this context.
4. The remainder of the explanation is balderdash. While the past participle must agree with the **direct object** when it **precedes** the past participle, FrenchLlama hallucinated the rest of the response. |
linndfors/uk-gender-swapper_aya-101 | linndfors | 2025-04-01T21:55:56Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2025-04-01T21:52:32Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
MinaMila/llama_instbase_Adult_5ep_42 | MinaMila | 2025-04-01T21:55:19Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/Meta-Llama-3.1-8B-Instruct",
"base_model:finetune:unsloth/Meta-Llama-3.1-8B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T21:52:11Z | ---
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** MinaMila
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-Instruct
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
lmstudio-community/openhands-lm-1.5b-v0.1-GGUF | lmstudio-community | 2025-04-01T21:50:48Z | 0 | 1 | null | [
"gguf",
"agent",
"coding",
"text-generation",
"en",
"dataset:SWE-Gym/SWE-Gym",
"base_model:all-hands/openhands-lm-1.5b-v0.1",
"base_model:quantized:all-hands/openhands-lm-1.5b-v0.1",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
]
| text-generation | 2025-04-01T21:04:08Z | ---
quantized_by: bartowski
pipeline_tag: text-generation
base_model_relation: quantized
datasets:
- SWE-Gym/SWE-Gym
base_model: all-hands/openhands-lm-1.5b-v0.1
tags:
- agent
- coding
language:
- en
license: mit
---
## 💫 Community Model> openhands lm 1.5b v0.1 by All-Hands
*👾 [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on [Discord](https://discord.gg/aPQfnNkxGC)*.
**Model creator:** [all-hands](https://huggingface.co/all-hands)<br>
**Original model**: [openhands-lm-1.5b-v0.1](https://huggingface.co/all-hands/openhands-lm-1.5b-v0.1)<br>
**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b5010](https://github.com/ggerganov/llama.cpp/releases/tag/b5010)<br>
## Technical Details
Supports a native context length of 32k, extendable to 128k with yarn.
Qwen2.5 fine-tuned for coding and a wide range of software development tasks.
Additional details available on their blog here: https://www.all-hands.dev/blog/introducing-openhands-lm-32b----a-strong-open-coding-agent-model
## Special thanks
🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.
## Disclaimers
LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.
|
mradermacher/llama3.2-entity-1b-GGUF | mradermacher | 2025-04-01T21:49:35Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:shadicopty/llama3.2-entity-1b",
"base_model:quantized:shadicopty/llama3.2-entity-1b",
"endpoints_compatible",
"region:us",
"conversational"
]
| null | 2025-04-01T21:41:26Z | ---
base_model: shadicopty/llama3.2-entity-1b
language:
- en
library_name: transformers
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/shadicopty/llama3.2-entity-1b
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-1b-GGUF/resolve/main/llama3.2-entity-1b.Q2_K.gguf) | Q2_K | 0.7 | |
| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-1b-GGUF/resolve/main/llama3.2-entity-1b.Q3_K_S.gguf) | Q3_K_S | 0.7 | |
| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-1b-GGUF/resolve/main/llama3.2-entity-1b.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-1b-GGUF/resolve/main/llama3.2-entity-1b.Q3_K_L.gguf) | Q3_K_L | 0.8 | |
| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-1b-GGUF/resolve/main/llama3.2-entity-1b.IQ4_XS.gguf) | IQ4_XS | 0.8 | |
| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-1b-GGUF/resolve/main/llama3.2-entity-1b.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-1b-GGUF/resolve/main/llama3.2-entity-1b.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-1b-GGUF/resolve/main/llama3.2-entity-1b.Q5_K_S.gguf) | Q5_K_S | 1.0 | |
| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-1b-GGUF/resolve/main/llama3.2-entity-1b.Q5_K_M.gguf) | Q5_K_M | 1.0 | |
| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-1b-GGUF/resolve/main/llama3.2-entity-1b.Q6_K.gguf) | Q6_K | 1.1 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-1b-GGUF/resolve/main/llama3.2-entity-1b.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/llama3.2-entity-1b-GGUF/resolve/main/llama3.2-entity-1b.f16.gguf) | f16 | 2.6 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
pr0ck/outputs | pr0ck | 2025-04-01T21:48:30Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"generated_from_trainer",
"unsloth",
"trl",
"sft",
"base_model:unsloth/phi-4-unsloth-bnb-4bit",
"base_model:finetune:unsloth/phi-4-unsloth-bnb-4bit",
"endpoints_compatible",
"region:us"
]
| null | 2025-04-01T21:25:29Z | ---
base_model: unsloth/phi-4-unsloth-bnb-4bit
library_name: transformers
model_name: outputs
tags:
- generated_from_trainer
- unsloth
- trl
- sft
licence: license
---
# Model Card for outputs
This model is a fine-tuned version of [unsloth/phi-4-unsloth-bnb-4bit](https://huggingface.co/unsloth/phi-4-unsloth-bnb-4bit).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="pr0ck/outputs", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with SFT.
### Framework versions
- TRL: 0.15.2
- Transformers: 4.50.3
- Pytorch: 2.6.0
- Datasets: 3.3.1
- Tokenizers: 0.21.0
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf | RichardErkhov | 2025-04-01T21:47:51Z | 0 | 0 | null | [
"gguf",
"endpoints_compatible",
"region:us",
"conversational"
]
| null | 2025-04-01T20:45:48Z | Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
Phi3_intent_v45_2_w_unknown_8_lr_0.002 - GGUF
- Model creator: https://huggingface.co/magnifi/
- Original model: https://huggingface.co/magnifi/Phi3_intent_v45_2_w_unknown_8_lr_0.002/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q2_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q2_K.gguf) | Q2_K | 1.35GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.IQ3_XS.gguf) | IQ3_XS | 1.49GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.IQ3_S.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.IQ3_S.gguf) | IQ3_S | 1.57GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q3_K_S.gguf) | Q3_K_S | 1.57GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.IQ3_M.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.IQ3_M.gguf) | IQ3_M | 1.65GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q3_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q3_K.gguf) | Q3_K | 1.75GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q3_K_M.gguf) | Q3_K_M | 1.75GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q3_K_L.gguf) | Q3_K_L | 1.9GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.IQ4_XS.gguf) | IQ4_XS | 1.93GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q4_0.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q4_0.gguf) | Q4_0 | 2.03GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.IQ4_NL.gguf) | IQ4_NL | 2.04GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q4_K_S.gguf) | Q4_K_S | 2.04GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q4_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q4_K.gguf) | Q4_K | 2.16GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q4_K_M.gguf) | Q4_K_M | 2.16GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q4_1.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q4_1.gguf) | Q4_1 | 2.24GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q5_0.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q5_0.gguf) | Q5_0 | 2.46GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q5_K_S.gguf) | Q5_K_S | 2.46GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q5_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q5_K.gguf) | Q5_K | 2.53GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q5_K_M.gguf) | Q5_K_M | 2.53GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q5_1.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q5_1.gguf) | Q5_1 | 2.68GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q6_K.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q6_K.gguf) | Q6_K | 2.92GB |
| [Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q8_0.gguf](https://huggingface.co/RichardErkhov/magnifi_-_Phi3_intent_v45_2_w_unknown_8_lr_0.002-gguf/blob/main/Phi3_intent_v45_2_w_unknown_8_lr_0.002.Q8_0.gguf) | Q8_0 | 3.78GB |
Original model description:
---
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- mistral
- trl
base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
---
# Uploaded model
- **Developed by:** magnifi
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-bnb-4bit
This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
bowilleatyou/5ed36781-457d-46b7-83c0-766b2ab7a50a | bowilleatyou | 2025-04-01T21:45:06Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"unsloth",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2025-04-01T15:13:56Z | ---
library_name: transformers
tags:
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
MinaMila/llama_instbase_Adult_4ep_42 | MinaMila | 2025-04-01T21:44:54Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/Meta-Llama-3.1-8B-Instruct",
"base_model:finetune:unsloth/Meta-Llama-3.1-8B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T21:41:48Z | ---
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** MinaMila
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-Instruct
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
triger69/TheBlokeHentaiXL | triger69 | 2025-04-01T21:43:31Z | 0 | 0 | null | [
"region:us"
]
| null | 2025-04-01T21:36:26Z | ---
# 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
TheBlokeHentaiXL
It has been generated using OneTrainer+Kohya_SS+Dreambooth.
## Model Details
All Models will work with AutoMatic1111 and ComfyUi.
### Model Description
All of the Models Here Have been Rated on other sites in the top 50 models!
- **Developed by:** TheBloke
- **Funded by:** https://thebloke.live
- **Shared by:** Everyone
- **Model type:** SDXL
- **Language(s) (NLP):** English
## Uses
TXT-IMAGE or with AnimateDiff TXT-VIDEO
## Bias, Risks, and Limitations
I am not responsable for photos/videos you create!
### Recommendations
Three Sample Photos
Very Simple Crappy Prompt: Stylized portrait of a woman with long blonde hair,black lace bralette,black jacket,hands in pockets,red pendant,confident expression,textured background.
### Training Data
750 Epo 750,000 Steps |
benjamin/Llama3.2-3B-IT-Byte | benjamin | 2025-04-01T21:41:14Z | 0 | 0 | transformers | [
"transformers",
"jax",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T21:33:50Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
glif-loradex-trainer/Hailey_costacos | glif-loradex-trainer | 2025-04-01T21:41:02Z | 0 | 0 | diffusers | [
"diffusers",
"text-to-image",
"template:sd-lora",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:finetune:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us",
"flux",
"lora",
"base_model:adapter:black-forest-labs/FLUX.1-dev"
]
| text-to-image | 2025-04-01T21:40:58Z | ---
tags:
- diffusers
- text-to-image
- template:sd-lora
- base_model:black-forest-labs/FLUX.1-dev
- base_model:finetune:black-forest-labs/FLUX.1-dev
- license:other
- region:us
- flux
- lora
widget:
- output:
url: samples/1743543593574__000000500_0.jpg
text: A skinny superhero swimming in a fish bowl in space. Costacos
- output:
url: samples/1743543618085__000000500_1.jpg
text: Mysterious man wearing a hood swimming in a pool in the sky. Costacos
- output:
url: samples/1743543642585__000000500_2.jpg
text: A skinny superhero drinking wine in the Louvre in Paris. Costacos
base_model: black-forest-labs/FLUX.1-dev
trigger: "Costacos"
instance_prompt: "Costacos"
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
---
# costacos
Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) under the [Glif Loradex program](https://huggingface.co/glif-loradex-trainer) by [Glif](https://glif.app) user `Hailey`.
<Gallery />
## Trigger words
You should use `Costacos` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/glif-loradex-trainer/Hailey_costacos/tree/main) them in the Files & versions tab.
## License
This model is licensed under the [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
|
MarkoHlavaty/lunar-lander-ppo-agent | MarkoHlavaty | 2025-04-01T21:39:18Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2025-04-01T21:39:02Z | ---
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: 282.94 +/- 20.27
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
...
```
|
jesusgs01/results_qwen_fold_1 | jesusgs01 | 2025-04-01T21:38:06Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"generated_from_trainer",
"trl",
"sft",
"base_model:Qwen/Qwen2-VL-7B-Instruct",
"base_model:finetune:Qwen/Qwen2-VL-7B-Instruct",
"endpoints_compatible",
"region:us"
]
| null | 2025-04-01T21:37:58Z | ---
base_model: Qwen/Qwen2-VL-7B-Instruct
library_name: transformers
model_name: results_qwen_fold_1
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for results_qwen_fold_1
This model is a fine-tuned version of [Qwen/Qwen2-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-7B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="jesusgs01/results_qwen_fold_1", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with SFT.
### Framework versions
- TRL: 0.16.0
- Transformers: 4.48.3
- Pytorch: 2.1.2
- Datasets: 3.5.0
- Tokenizers: 0.21.0
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
sskaishev/album_art | sskaishev | 2025-04-01T21:36:45Z | 0 | 0 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"diffusers-training",
"lora",
"base_model:stable-diffusion-v1-5/stable-diffusion-v1-5",
"base_model:adapter:stable-diffusion-v1-5/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"region:us"
]
| text-to-image | 2025-04-01T11:51:55Z | ---
base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
library_name: diffusers
license: creativeml-openrail-m
inference: true
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- diffusers-training
- lora
---
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# LoRA text2image fine-tuning - sskaishev/album_art
These are LoRA adaption weights for stable-diffusion-v1-5/stable-diffusion-v1-5. The weights were fine-tuned on the sskaishev/album-covers-mid2 dataset. You can find some example images in the following.
## Intended uses & limitations
#### How to use
```python
# TODO: add an example code snippet for running this diffusion pipeline
```
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model] |
bowilleatyou/a2863d4f-4472-49f4-8629-290f69d1c7f3 | bowilleatyou | 2025-04-01T21:36:14Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"unsloth",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2025-04-01T16:36:25Z | ---
library_name: transformers
tags:
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
EstherXC/llama_pro_base_dare_tie | EstherXC | 2025-04-01T21:35:26Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"arxiv:2306.01708",
"base_model:GreatCaptainNemo/ProLLaMA",
"base_model:merge:GreatCaptainNemo/ProLLaMA",
"base_model:NousResearch/Llama-2-7b-hf",
"base_model:merge:NousResearch/Llama-2-7b-hf",
"base_model:dnagpt/llama-dna",
"base_model:merge:dnagpt/llama-dna",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T21:32:13Z | ---
base_model:
- dnagpt/llama-dna
- GreatCaptainNemo/ProLLaMA
- NousResearch/Llama-2-7b-hf
library_name: transformers
tags:
- mergekit
- merge
---
# llama_pro_base_dare_tie
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) as a base.
### Models Merged
The following models were included in the merge:
* [dnagpt/llama-dna](https://huggingface.co/dnagpt/llama-dna)
* [GreatCaptainNemo/ProLLaMA](https://huggingface.co/GreatCaptainNemo/ProLLaMA)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: NousResearch/Llama-2-7b-hf
- model: GreatCaptainNemo/ProLLaMA #wanglab/mixtral_7b_dna_pretrain
parameters:
density: 0.5
weight: 0.2
- model: dnagpt/llama-dna #EstherXC/mixtral_7b_protein_pretrain
parameters:
density: 0.5
weight: 0.2
merge_method: ties
base_model: NousResearch/Llama-2-7b-hf #wanglab/mixtral_7b_dna_pretrain
parameters:
normalize: true
dtype: float16
```
|
mradermacher/delta-4b-orange-GGUF | mradermacher | 2025-04-01T21:34:57Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:frankenmerger/delta-4b-orange",
"base_model:quantized:frankenmerger/delta-4b-orange",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
| null | 2025-04-01T20:42:21Z | ---
base_model: frankenmerger/delta-4b-orange
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/frankenmerger/delta-4b-orange
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/delta-4b-orange-GGUF/resolve/main/delta-4b-orange.Q2_K.gguf) | Q2_K | 1.9 | |
| [GGUF](https://huggingface.co/mradermacher/delta-4b-orange-GGUF/resolve/main/delta-4b-orange.Q3_K_S.gguf) | Q3_K_S | 2.2 | |
| [GGUF](https://huggingface.co/mradermacher/delta-4b-orange-GGUF/resolve/main/delta-4b-orange.Q3_K_M.gguf) | Q3_K_M | 2.5 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/delta-4b-orange-GGUF/resolve/main/delta-4b-orange.IQ4_XS.gguf) | IQ4_XS | 2.7 | |
| [GGUF](https://huggingface.co/mradermacher/delta-4b-orange-GGUF/resolve/main/delta-4b-orange.Q3_K_L.gguf) | Q3_K_L | 2.7 | |
| [GGUF](https://huggingface.co/mradermacher/delta-4b-orange-GGUF/resolve/main/delta-4b-orange.Q4_K_S.gguf) | Q4_K_S | 2.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/delta-4b-orange-GGUF/resolve/main/delta-4b-orange.Q4_K_M.gguf) | Q4_K_M | 3.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/delta-4b-orange-GGUF/resolve/main/delta-4b-orange.Q5_K_S.gguf) | Q5_K_S | 3.3 | |
| [GGUF](https://huggingface.co/mradermacher/delta-4b-orange-GGUF/resolve/main/delta-4b-orange.Q5_K_M.gguf) | Q5_K_M | 3.5 | |
| [GGUF](https://huggingface.co/mradermacher/delta-4b-orange-GGUF/resolve/main/delta-4b-orange.Q6_K.gguf) | Q6_K | 3.9 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/delta-4b-orange-GGUF/resolve/main/delta-4b-orange.Q8_0.gguf) | Q8_0 | 5.1 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/delta-4b-orange-GGUF/resolve/main/delta-4b-orange.f16.gguf) | f16 | 9.4 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
MinaMila/llama_instbase_Adult_3ep_42 | MinaMila | 2025-04-01T21:34:01Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/Meta-Llama-3.1-8B-Instruct",
"base_model:finetune:unsloth/Meta-Llama-3.1-8B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T21:30:50Z | ---
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** MinaMila
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-Instruct
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
HOT-HD-VIRALS-VIDEO-Camilla-Araujo/camilla.araujo.video.on.social.media.twitter.x | HOT-HD-VIRALS-VIDEO-Camilla-Araujo | 2025-04-01T21:33:18Z | 0 | 0 | null | [
"region:us"
]
| null | 2025-04-01T21:33:00Z | <animated-image data-catalyst=""><a href="https://alltvsteam.com/viral-video/?v=news-es-tvdf" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a> |
Parraga/qwen2.5_14b_it_lora | Parraga | 2025-04-01T21:33:15Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:Qwen/Qwen2.5-14B-Instruct-1M",
"base_model:finetune:Qwen/Qwen2.5-14B-Instruct-1M",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T21:21:54Z | ---
base_model: Qwen/Qwen2.5-14B-Instruct-1M
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** Parraga
- **License:** apache-2.0
- **Finetuned from model :** Qwen/Qwen2.5-14B-Instruct-1M
This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
vivek1192/merged_medicalQAties-hindi | vivek1192 | 2025-04-01T21:32:53Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"arxiv:2306.01708",
"base_model:BioMistral/BioMistral-7B",
"base_model:merge:BioMistral/BioMistral-7B",
"base_model:OdiaGenAI/mistral_hindi_7b_base_v1",
"base_model:merge:OdiaGenAI/mistral_hindi_7b_base_v1",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:merge:mistralai/Mistral-7B-v0.1",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T21:29:13Z | ---
base_model:
- BioMistral/BioMistral-7B
- mistralai/Mistral-7B-v0.1
- OdiaGenAI/mistral_hindi_7b_base_v1
library_name: transformers
tags:
- mergekit
- merge
---
# merged_models
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base.
### Models Merged
The following models were included in the merge:
* [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B)
* [OdiaGenAI/mistral_hindi_7b_base_v1](https://huggingface.co/OdiaGenAI/mistral_hindi_7b_base_v1)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: mistralai/Mistral-7B-v0.1
dtype: float16
merge_method: ties
modules:
default:
slices:
- sources:
- layer_range: [0, 32]
model: BioMistral/BioMistral-7B
parameters:
density: 0.5
weight: 0.5
- layer_range: [0, 32]
model: OdiaGenAI/mistral_hindi_7b_base_v1
parameters:
density: 0.5
weight: 0.5
- layer_range: [0, 32]
model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: 1.0
normalize: 0.0
```
|
WesPro/QwQ-32B-ArliAI-RPMax-Reasoning-v0-Q4_K_M-GGUF | WesPro | 2025-04-01T21:32:29Z | 0 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:ArliAI/QwQ-32B-ArliAI-RPMax-Reasoning-v0",
"base_model:quantized:ArliAI/QwQ-32B-ArliAI-RPMax-Reasoning-v0",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
| null | 2025-04-01T21:30:56Z | ---
base_model: ArliAI/QwQ-32B-ArliAI-RPMax-Reasoning-v0
license: apache-2.0
tags:
- llama-cpp
- gguf-my-repo
---
# WesPro/QwQ-32B-ArliAI-RPMax-Reasoning-v0-Q4_K_M-GGUF
This model was converted to GGUF format from [`ArliAI/QwQ-32B-ArliAI-RPMax-Reasoning-v0`](https://huggingface.co/ArliAI/QwQ-32B-ArliAI-RPMax-Reasoning-v0) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/ArliAI/QwQ-32B-ArliAI-RPMax-Reasoning-v0) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo WesPro/QwQ-32B-ArliAI-RPMax-Reasoning-v0-Q4_K_M-GGUF --hf-file qwq-32b-arliai-rpmax-reasoning-v0-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo WesPro/QwQ-32B-ArliAI-RPMax-Reasoning-v0-Q4_K_M-GGUF --hf-file qwq-32b-arliai-rpmax-reasoning-v0-q4_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo WesPro/QwQ-32B-ArliAI-RPMax-Reasoning-v0-Q4_K_M-GGUF --hf-file qwq-32b-arliai-rpmax-reasoning-v0-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo WesPro/QwQ-32B-ArliAI-RPMax-Reasoning-v0-Q4_K_M-GGUF --hf-file qwq-32b-arliai-rpmax-reasoning-v0-q4_k_m.gguf -c 2048
```
|
fbaldassarri/openlm-research_open_llama_3b_v2-autoround-int4-gs64-sym | fbaldassarri | 2025-04-01T21:31:48Z | 0 | 0 | null | [
"safetensors",
"llama",
"pytorch",
"causal-lm",
"OpenLLaMA",
"autoround",
"auto-round",
"intel-autoround",
"gptq",
"woq",
"intel",
"openlm-research",
"text-generation",
"dataset:tiiuae/falcon-refinedweb",
"dataset:bigcode/starcoderdata",
"dataset:togethercomputer/RedPajama-Data-1T",
"base_model:openlm-research/open_llama_3b_v2",
"base_model:quantized:openlm-research/open_llama_3b_v2",
"license:apache-2.0",
"4-bit",
"intel/auto-round",
"region:us"
]
| text-generation | 2025-04-01T21:30:48Z | ---
tags:
- pytorch
- causal-lm
- OpenLLaMA
- autoround
- auto-round
- intel-autoround
- gptq
- woq
- intel
- pytorch
- openlm-research
license: apache-2.0
datasets:
- tiiuae/falcon-refinedweb
- bigcode/starcoderdata
- togethercomputer/RedPajama-Data-1T
model_name: OpenLLaMA 3B v2
base_model:
- openlm-research/open_llama_3b_v2
inference: false
model_creator: openlm-research
pipeline_tag: text-generation
prompt_template: '{prompt}
'
quantized_by: fbaldassarri
---
## Model Information
Quantized version of [openlm-research/open_llama_3b_v2](https://huggingface.co/openlm-research/open_llama_3b_v2) using torch.float32 for quantization tuning.
- 4 bits (INT4)
- group size = 64
- Symmetrical Quantization
- Method WoQ (AutoRound format)
Fast and low memory, 2-3X speedup (slight accuracy drop at W4G64)
Quantization framework: [Intel AutoRound](https://github.com/intel/auto-round) v0.4.6
Note: this INT4 version of open_llama_3b_v2 has been quantized to run inference through CPU.
## Replication Recipe
### Step 1 Install Requirements
I suggest to install requirements into a dedicated python-virtualenv or a conda enviroment.
```
wget https://github.com/intel/auto-round/archive/refs/tags/v0.4.6.tar.gz
tar -xvzf v0.4.6.tar.gz
cd auto-round-0.4.6
pip install -r requirements-cpu.txt --upgrade
```
### Step 2 Build Intel AutoRound wheel from sources
```
pip install -vvv --no-build-isolation -e .[cpu]
```
### Step 3 Script for Quantization
```
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "openlm-research/open_llama_3b_v2"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
from auto_round import AutoRound
bits, group_size, sym, device, amp = 4, 64, True, 'cpu', False
autoround = AutoRound(model, tokenizer, nsamples=128, iters=200, seqlen=512, batch_size=4, bits=bits, group_size=group_size, sym=sym, device=device, amp=amp)
autoround.quantize()
output_dir = "./AutoRound/openlm-research_open_llama_3b_v2-autoround-int4-gs64-sym"
autoround.save_quantized(output_dir, format='auto_round', inplace=True)
```
## License
[Apache 2.0 License](https://choosealicense.com/licenses/apache-2.0/)
## Disclaimer
This quantized model comes with no warranty. It has been developed only for research purposes.
|
triger69/TheBlokeRealisticXL | triger69 | 2025-04-01T21:31:45Z | 0 | 1 | null | [
"region:us"
]
| null | 2025-04-01T21:12:47Z | ---
# 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
TheBlokeRealisticXL
It has been generated using OneTrainer+Kohya_SS+Dreambooth.
## Model Details
All Models will work with AutoMatic1111 and ComfyUi.
### Model Description
All of the Models Here Have been Rated on other sites in the top 50 models!
- **Developed by:** TheBloke
- **Funded by:** https://thebloke.live
- **Shared by:** Everyone
- **Model type:** SDXL
- **Language(s) (NLP):** English
## Uses
TXT-IMAGE or with AnimateDiff TXT-VIDEO
## Bias, Risks, and Limitations
I am not responsable for photos/videos you create!
### Recommendations
Three Sample Photos
Very Simple Crappy Prompt: Stylized portrait of a woman with long blonde hair,black lace bralette,black jacket,hands in pockets,red pendant,confident expression,textured background.
### Training Data
750 Epo 750,000 Steps |
Emmanuelprime/vanessa_medical_v3.0-DeepSeek-R | Emmanuelprime | 2025-04-01T21:31:40Z | 0 | 0 | transformers | [
"transformers",
"unsloth",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2025-04-01T21:31:37Z | ---
library_name: transformers
tags:
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Emmanuelprime/vanessa_medical_v3.0-DeepSeek-R1 | Emmanuelprime | 2025-04-01T21:31:36Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"base_model:unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit",
"base_model:finetune:unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| null | 2025-04-01T21:31:18Z | ---
base_model: unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** Emmanuelprime
- **License:** apache-2.0
- **Finetuned from model :** unsloth/DeepSeek-R1-Distill-Llama-8B-unsloth-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
jiaxin-wen/truthfulqa-preference-iter3-incontext-shuffle | jiaxin-wen | 2025-04-01T21:30:40Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T21:25:36Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
KandoCare/camembert-care-plan | KandoCare | 2025-04-01T21:26:51Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"camembert",
"fill-mask",
"french",
"text-classification",
"intent-detection",
"tensorboard",
"fr",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:eu"
]
| text-classification | 2025-04-01T06:39:43Z | ---
language: fr
tags:
- french
- text-classification
- intent-detection
- tensorboard
- transformers
- camembert
library_name: transformers
pipeline_tag: text-classification
inference: true
license: mit
model-index:
- name: "KandoCare/camembert-intent-27"
results:
- task:
type: text-classification
name: Text Classification
metrics:
- type: accuracy
value: 0.93
name: Accuracy
- type: f1
value: 0.93
name: F1 Score
- type: precision
value: 0.93
name: Precision
- type: recall
value: 0.93
name: Recall
---
# Intent Detection Model
## Model Description
This model is fine-tuned on CamemBERT for intent detection in French text.
## Intended Use
This model is designed for classifying intents in French text.
## Usage
```python
from transformers import pipeline
classifier = pipeline("text-classification", model="KandoCare/camembert-intent")
result = classifier("affiche le plan de soins.")
```
|
HOT-HD-VIRALS-VIDEO-Camilla-Araujo/new.camilla.araujo.video.on.social.media.trending.now | HOT-HD-VIRALS-VIDEO-Camilla-Araujo | 2025-04-01T21:26:40Z | 0 | 0 | null | [
"region:us"
]
| null | 2025-04-01T21:25:39Z | <animated-image data-catalyst=""><a href="https://alltvsteam.com/viral-video/?v=news-es-tvdf" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a> |
pictgensupport/arboretum | pictgensupport | 2025-04-01T21:23:37Z | 0 | 0 | diffusers | [
"diffusers",
"flux",
"lora",
"replicate",
"text-to-image",
"en",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
]
| text-to-image | 2025-04-01T21:23:34Z | ---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: "black-forest-labs/FLUX.1-dev"
pipeline_tag: text-to-image
# widget:
# - text: >-
# prompt
# output:
# url: https://...
instance_prompt: flowerpower
---
# Arboretum
<Gallery />
Trained on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `flowerpower` to trigger the image generation.
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('pictgensupport/arboretum', weight_name='lora.safetensors')
image = pipeline('your prompt').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
|
nouraa5/whisper-small-ur | nouraa5 | 2025-04-01T21:20:25Z | 0 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"hf-asr-leaderboard",
"generated_from_trainer",
"ar",
"dataset:mozilla-foundation/common_voice_11_0",
"base_model:openai/whisper-small",
"base_model:finetune:openai/whisper-small",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| automatic-speech-recognition | 2025-04-01T08:08:01Z | ---
library_name: transformers
language:
- ar
license: apache-2.0
base_model: openai/whisper-small
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
model-index:
- name: Whisper Small Ar - Huzaifa Tahir
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. -->
# Whisper Small Ar - Huzaifa Tahir
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 150
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.50.2
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
|
S-Chaves/dqn-SpaceInvadersNoFrameskip-v4 | S-Chaves | 2025-04-01T21:19:34Z | 13 | 0 | stable-baselines3 | [
"stable-baselines3",
"SpaceInvadersNoFrameskip-v4",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
]
| reinforcement-learning | 2025-03-29T20:30:13Z | ---
library_name: stable-baselines3
tags:
- SpaceInvadersNoFrameskip-v4
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: DQN
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: SpaceInvadersNoFrameskip-v4
type: SpaceInvadersNoFrameskip-v4
metrics:
- type: mean_reward
value: 581.00 +/- 269.29
name: mean_reward
verified: false
---
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4**
This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
The RL Zoo is a training framework for Stable Baselines3
reinforcement learning agents,
with hyperparameter optimization and pre-trained agents included.
## Usage (with SB3 RL Zoo)
RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
SB3: https://github.com/DLR-RM/stable-baselines3<br/>
SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
SBX (SB3 + Jax): https://github.com/araffin/sbx
Install the RL Zoo (with SB3 and SB3-Contrib):
```bash
pip install rl_zoo3
```
```
# Download model and save it into the logs/ folder
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga S-Chaves -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
```
python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga S-Chaves -f logs/
python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
```
## Training (with the RL Zoo)
```
python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/
# Upload the model and generate video (when possible)
python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga S-Chaves
```
## Hyperparameters
```python
OrderedDict([('batch_size', 32),
('buffer_size', 100000),
('env_wrapper',
['stable_baselines3.common.atari_wrappers.AtariWrapper']),
('exploration_final_eps', 0.01),
('exploration_fraction', 0.1),
('frame_stack', 4),
('gradient_steps', 1),
('learning_rate', 0.0001),
('learning_starts', 100000),
('n_timesteps', 1000000.0),
('optimize_memory_usage', False),
('policy', 'CnnPolicy'),
('target_update_interval', 1000),
('train_freq', 4),
('normalize', False)])
```
# Environment Arguments
```python
{'render_mode': 'rgb_array'}
```
|
inrainbws/resnet_r16_mlora_exp_wn | inrainbws | 2025-04-01T21:17:49Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2025-04-01T21:17:46Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
jonahdvt/whisper-fleurs-large-afri | jonahdvt | 2025-04-01T21:16:01Z | 0 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"whisper",
"automatic-speech-recognition",
"ig,lg,sw,yo,ha",
"generated_from_trainer",
"multilingual",
"dataset:google/fleurs",
"base_model:openai/whisper-large-v3",
"base_model:finetune:openai/whisper-large-v3",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
]
| automatic-speech-recognition | 2025-04-01T15:59:35Z | ---
library_name: transformers
language:
- multilingual
license: apache-2.0
base_model: openai/whisper-large-v3
tags:
- ig,lg,sw,yo,ha
- generated_from_trainer
datasets:
- google/fleurs
model-index:
- name: Whisper Large FLEURS - Afri - Fine-tuning
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. -->
# Whisper Large FLEURS - Afri - Fine-tuning
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the FLEURS dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 4400
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.48.3
- Pytorch 2.6.0+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0
|
15e/magu | 15e | 2025-04-01T21:15:33Z | 0 | 0 | diffusers | [
"diffusers",
"flux",
"lora",
"replicate",
"text-to-image",
"en",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
]
| text-to-image | 2025-04-01T20:41:27Z | ---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: "black-forest-labs/FLUX.1-dev"
pipeline_tag: text-to-image
# widget:
# - text: >-
# prompt
# output:
# url: https://...
instance_prompt: MAGU
---
# Magu
<Gallery />
## About this LoRA
This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI.
It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `MAGU` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "MAGU",
"lora_weights": "https://huggingface.co/15e/magu/resolve/main/lora.safetensors"
}
output = replicate.run(
"black-forest-labs/flux-dev-lora",
input=input
)
for index, item in enumerate(output):
with open(f"output_{index}.webp", "wb") as file:
file.write(item.read())
```
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('15e/magu', weight_name='lora.safetensors')
image = pipeline('MAGU').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
## Training details
- Steps: 1000
- Learning rate: 0.0004
- LoRA rank: 16
## Contribute your own examples
You can use the [community tab](https://huggingface.co/15e/magu/discussions) to add images that show off what you’ve made with this LoRA.
|
ToastyPigeon/g3-27b-merge-C-Q4_K_S-GGUF | ToastyPigeon | 2025-04-01T21:15:32Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"llama-cpp",
"gguf-my-repo",
"base_model:ToastyPigeon/g3-27b-merge-C",
"base_model:quantized:ToastyPigeon/g3-27b-merge-C",
"endpoints_compatible",
"region:us",
"conversational"
]
| null | 2025-04-01T21:14:21Z | ---
base_model: ToastyPigeon/g3-27b-merge-C
library_name: transformers
tags:
- mergekit
- merge
- llama-cpp
- gguf-my-repo
---
# ToastyPigeon/g3-27b-merge-C-Q4_K_S-GGUF
This model was converted to GGUF format from [`ToastyPigeon/g3-27b-merge-C`](https://huggingface.co/ToastyPigeon/g3-27b-merge-C) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/ToastyPigeon/g3-27b-merge-C) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo ToastyPigeon/g3-27b-merge-C-Q4_K_S-GGUF --hf-file g3-27b-merge-c-q4_k_s.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo ToastyPigeon/g3-27b-merge-C-Q4_K_S-GGUF --hf-file g3-27b-merge-c-q4_k_s.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo ToastyPigeon/g3-27b-merge-C-Q4_K_S-GGUF --hf-file g3-27b-merge-c-q4_k_s.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo ToastyPigeon/g3-27b-merge-C-Q4_K_S-GGUF --hf-file g3-27b-merge-c-q4_k_s.gguf -c 2048
```
|
pierre-livetrend/llama381binstruct_summarize_short_merged | pierre-livetrend | 2025-04-01T21:12:28Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"trl",
"sft",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
]
| text-generation | 2025-04-01T20:05:15Z | ---
library_name: transformers
tags:
- trl
- sft
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
vivek1192/merged_medicalQAdella-hindi | vivek1192 | 2025-04-01T21:12:17Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"arxiv:2406.11617",
"base_model:BioMistral/BioMistral-7B",
"base_model:merge:BioMistral/BioMistral-7B",
"base_model:OdiaGenAI/mistral_hindi_7b_base_v1",
"base_model:merge:OdiaGenAI/mistral_hindi_7b_base_v1",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:merge:mistralai/Mistral-7B-v0.1",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T21:08:37Z | ---
base_model:
- BioMistral/BioMistral-7B
- mistralai/Mistral-7B-v0.1
- OdiaGenAI/mistral_hindi_7b_base_v1
library_name: transformers
tags:
- mergekit
- merge
---
# merged_models
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [DELLA](https://arxiv.org/abs/2406.11617) merge method using [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base.
### Models Merged
The following models were included in the merge:
* [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B)
* [OdiaGenAI/mistral_hindi_7b_base_v1](https://huggingface.co/OdiaGenAI/mistral_hindi_7b_base_v1)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: mistralai/Mistral-7B-v0.1
dtype: float16
merge_method: della
modules:
default:
slices:
- sources:
- layer_range: [0, 32]
model: BioMistral/BioMistral-7B
parameters:
density: 0.5
weight: 0.5
- layer_range: [0, 32]
model: OdiaGenAI/mistral_hindi_7b_base_v1
parameters:
density: 0.5
weight: 0.5
- layer_range: [0, 32]
model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: 1.0
normalize: 0.0
```
|
MinaMila/llama_instbase_Adult_1ep_42 | MinaMila | 2025-04-01T21:12:11Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/Meta-Llama-3.1-8B-Instruct",
"base_model:finetune:unsloth/Meta-Llama-3.1-8B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T21:08:59Z | ---
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** MinaMila
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-Instruct
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
ljnlonoljpiljm/florence-2-base-ft-p-frozen | ljnlonoljpiljm | 2025-04-01T21:10:01Z | 41 | 0 | transformers | [
"transformers",
"safetensors",
"florence2",
"text-generation",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"region:us"
]
| text-generation | 2025-03-29T15:47:56Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
pierre-livetrend/llama381binstruct_summarize_short | pierre-livetrend | 2025-04-01T21:07:28Z | 0 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"generated_from_trainer",
"trl",
"sft",
"base_model:NousResearch/Meta-Llama-3.1-8B-Instruct",
"base_model:finetune:NousResearch/Meta-Llama-3.1-8B-Instruct",
"endpoints_compatible",
"region:us"
]
| null | 2025-04-01T20:04:03Z | ---
base_model: NousResearch/Meta-Llama-3.1-8B-Instruct
library_name: transformers
model_name: llama381binstruct_summarize_short
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for llama381binstruct_summarize_short
This model is a fine-tuned version of [NousResearch/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3.1-8B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="pierre-livetrend/llama381binstruct_summarize_short", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/livetrend/huggingface/runs/uphd67vi)
This model was trained with SFT.
### Framework versions
- TRL: 0.16.0
- Transformers: 4.50.3
- Pytorch: 2.6.0+cu124
- Datasets: 3.5.0
- Tokenizers: 0.21.1
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
mradermacher/TinyLlama-1.1B-Instruct-GGUF | mradermacher | 2025-04-01T21:06:15Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"en",
"dataset:cerebras/SlimPajama-627B",
"dataset:bigcode/starcoderdata",
"dataset:HuggingFaceH4/ultrachat_200k",
"dataset:HuggingFaceH4/ultrafeedback_binarized",
"base_model:LlamaFinetuneBase/TinyLlama-1.1B-Instruct",
"base_model:quantized:LlamaFinetuneBase/TinyLlama-1.1B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
| null | 2025-04-01T20:58:08Z | ---
base_model: LlamaFinetuneBase/TinyLlama-1.1B-Instruct
datasets:
- cerebras/SlimPajama-627B
- bigcode/starcoderdata
- HuggingFaceH4/ultrachat_200k
- HuggingFaceH4/ultrafeedback_binarized
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/LlamaFinetuneBase/TinyLlama-1.1B-Instruct
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q2_K.gguf) | Q2_K | 0.5 | |
| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.6 | |
| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q3_K_L.gguf) | Q3_K_L | 0.7 | |
| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.IQ4_XS.gguf) | IQ4_XS | 0.7 | |
| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q5_K_S.gguf) | Q5_K_S | 0.9 | |
| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q5_K_M.gguf) | Q5_K_M | 0.9 | |
| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q6_K.gguf) | Q6_K | 1.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/TinyLlama-1.1B-Instruct-GGUF/resolve/main/TinyLlama-1.1B-Instruct.f16.gguf) | f16 | 2.3 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
vivek1192/merged_medicalQAdare_ties-hindi | vivek1192 | 2025-04-01T21:02:29Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"mistral",
"text-generation",
"mergekit",
"merge",
"arxiv:2311.03099",
"base_model:BioMistral/BioMistral-7B",
"base_model:merge:BioMistral/BioMistral-7B",
"base_model:OdiaGenAI/mistral_hindi_7b_base_v1",
"base_model:merge:OdiaGenAI/mistral_hindi_7b_base_v1",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:merge:mistralai/Mistral-7B-v0.1",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T20:58:50Z | ---
base_model:
- BioMistral/BioMistral-7B
- mistralai/Mistral-7B-v0.1
- OdiaGenAI/mistral_hindi_7b_base_v1
library_name: transformers
tags:
- mergekit
- merge
---
# merged_models
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) as a base.
### Models Merged
The following models were included in the merge:
* [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B)
* [OdiaGenAI/mistral_hindi_7b_base_v1](https://huggingface.co/OdiaGenAI/mistral_hindi_7b_base_v1)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: mistralai/Mistral-7B-v0.1
dtype: float16
merge_method: dare_ties
modules:
default:
slices:
- sources:
- layer_range: [0, 32]
model: BioMistral/BioMistral-7B
parameters:
density: 0.5
weight: 0.5
- layer_range: [0, 32]
model: OdiaGenAI/mistral_hindi_7b_base_v1
parameters:
density: 0.5
weight: 0.5
- layer_range: [0, 32]
model: mistralai/Mistral-7B-v0.1
parameters:
int8_mask: 1.0
normalize: 0.0
```
|
krmk90/qwen2_5-7b-grounding_absolute_coord_augmented | krmk90 | 2025-04-01T21:02:20Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:Qwen/Qwen2.5-VL-7B-Instruct",
"base_model:adapter:Qwen/Qwen2.5-VL-7B-Instruct",
"license:apache-2.0",
"region:us"
]
| null | 2025-04-01T19:36:43Z | ---
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen2.5-VL-7B-Instruct
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: qwen2_5-7b-grounding_absolute_coord_augmented
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. -->
# qwen2_5-7b-grounding_absolute_coord_augmented
This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 3
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 24
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 5
### Training results
### Framework versions
- PEFT 0.13.0
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.0.1
- Tokenizers 0.21.0 |
aisys2803/ai_sys_deepseek_7B-Q4_K_M-GGUF | aisys2803 | 2025-04-01T21:01:42Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"unsloth",
"llama-cpp",
"gguf-my-repo",
"base_model:aisys2803/ai_sys_deepseek_7B",
"base_model:quantized:aisys2803/ai_sys_deepseek_7B",
"endpoints_compatible",
"region:us",
"conversational"
]
| null | 2025-04-01T21:01:20Z | ---
base_model: aisys2803/ai_sys_deepseek_7B
library_name: transformers
tags:
- unsloth
- llama-cpp
- gguf-my-repo
---
# aisys2803/ai_sys_deepseek_7B-Q4_K_M-GGUF
This model was converted to GGUF format from [`aisys2803/ai_sys_deepseek_7B`](https://huggingface.co/aisys2803/ai_sys_deepseek_7B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/aisys2803/ai_sys_deepseek_7B) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo aisys2803/ai_sys_deepseek_7B-Q4_K_M-GGUF --hf-file ai_sys_deepseek_7b-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo aisys2803/ai_sys_deepseek_7B-Q4_K_M-GGUF --hf-file ai_sys_deepseek_7b-q4_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo aisys2803/ai_sys_deepseek_7B-Q4_K_M-GGUF --hf-file ai_sys_deepseek_7b-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo aisys2803/ai_sys_deepseek_7B-Q4_K_M-GGUF --hf-file ai_sys_deepseek_7b-q4_k_m.gguf -c 2048
```
|
mradermacher/falcon3-decompiler-7b-v1-GGUF | mradermacher | 2025-04-01T21:01:41Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:Neo111x/falcon3-decompiler-7b-v1",
"base_model:quantized:Neo111x/falcon3-decompiler-7b-v1",
"endpoints_compatible",
"region:us"
]
| null | 2025-04-01T20:38:28Z | ---
base_model: Neo111x/falcon3-decompiler-7b-v1
language:
- en
library_name: transformers
quantized_by: mradermacher
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/Neo111x/falcon3-decompiler-7b-v1
<!-- provided-files -->
weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/falcon3-decompiler-7b-v1-GGUF/resolve/main/falcon3-decompiler-7b-v1.Q2_K.gguf) | Q2_K | 3.0 | |
| [GGUF](https://huggingface.co/mradermacher/falcon3-decompiler-7b-v1-GGUF/resolve/main/falcon3-decompiler-7b-v1.Q3_K_S.gguf) | Q3_K_S | 3.5 | |
| [GGUF](https://huggingface.co/mradermacher/falcon3-decompiler-7b-v1-GGUF/resolve/main/falcon3-decompiler-7b-v1.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/falcon3-decompiler-7b-v1-GGUF/resolve/main/falcon3-decompiler-7b-v1.Q3_K_L.gguf) | Q3_K_L | 4.1 | |
| [GGUF](https://huggingface.co/mradermacher/falcon3-decompiler-7b-v1-GGUF/resolve/main/falcon3-decompiler-7b-v1.IQ4_XS.gguf) | IQ4_XS | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/falcon3-decompiler-7b-v1-GGUF/resolve/main/falcon3-decompiler-7b-v1.Q4_K_S.gguf) | Q4_K_S | 4.4 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/falcon3-decompiler-7b-v1-GGUF/resolve/main/falcon3-decompiler-7b-v1.Q4_K_M.gguf) | Q4_K_M | 4.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/falcon3-decompiler-7b-v1-GGUF/resolve/main/falcon3-decompiler-7b-v1.Q5_K_S.gguf) | Q5_K_S | 5.3 | |
| [GGUF](https://huggingface.co/mradermacher/falcon3-decompiler-7b-v1-GGUF/resolve/main/falcon3-decompiler-7b-v1.Q5_K_M.gguf) | Q5_K_M | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/falcon3-decompiler-7b-v1-GGUF/resolve/main/falcon3-decompiler-7b-v1.Q6_K.gguf) | Q6_K | 6.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/falcon3-decompiler-7b-v1-GGUF/resolve/main/falcon3-decompiler-7b-v1.Q8_0.gguf) | Q8_0 | 8.0 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/falcon3-decompiler-7b-v1-GGUF/resolve/main/falcon3-decompiler-7b-v1.f16.gguf) | f16 | 15.0 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
camilla-araujo-viral-videoss-leak/new.camilla.araujo.video.on.social.media.trending.now | camilla-araujo-viral-videoss-leak | 2025-04-01T21:01:28Z | 0 | 0 | null | [
"region:us"
]
| null | 2025-04-01T21:00:23Z | <animated-image data-catalyst=""><a href="https://alltvsteam.com/viral-video/?v=news-es-tvdf" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a> |
MinaMila/llama_instbase_Adult_15ep_33 | MinaMila | 2025-04-01T21:00:15Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/Meta-Llama-3.1-8B-Instruct",
"base_model:finetune:unsloth/Meta-Llama-3.1-8B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T20:56:57Z | ---
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** MinaMila
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-Instruct
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
NguyenDuyPhuc/DistressAI | NguyenDuyPhuc | 2025-04-01T20:58:45Z | 0 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"DistressAI",
"trl",
"sft",
"conversational",
"base_model:Qwen/Qwen2.5-0.5B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-0.5B-Instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
]
| text-generation | 2025-04-01T20:20:20Z | ---
base_model: Qwen/Qwen2.5-0.5B-Instruct
library_name: transformers
model_name: DistressAI
tags:
- generated_from_trainer
- DistressAI
- trl
- sft
licence: license
---
# Model Card for DistressAI
This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="NguyenDuyPhuc/DistressAI", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/duyphuclenguyen-university-of-south-florida/huggingface/runs/87xcg9jo)
This model was trained with SFT.
### Framework versions
- TRL: 0.15.2
- Transformers: 4.50.3
- Pytorch: 2.6.0
- Datasets: 3.3.2
- Tokenizers: 0.21.0
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
camilla-araujo-viral-videoss-leak/new.hd.Camilla.Araujo.video.official.tutorial.now | camilla-araujo-viral-videoss-leak | 2025-04-01T20:57:56Z | 0 | 0 | null | [
"region:us"
]
| null | 2025-04-01T20:57:39Z | <animated-image data-catalyst=""><a href="https://alltvsteam.com/viral-video/?v=news-es-tvdf" rel="nofollow" data-target="animated-image.originalLink"><img src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" alt="Foo" data-canonical-src="https://static.wixstatic.com/media/b249f9_adac8f70fb3f45b88691696c77de18f3~mv2.gif" style="max-width: 100%; display: inline-block;" data-target="animated-image.originalImage"></a> |
ShauryaJain/HunyuanForge | ShauryaJain | 2025-04-01T20:56:41Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
]
| null | 2025-03-30T20:35:30Z | ---
license: apache-2.0
---
|
ntnu-smil/sla-p4_sla-p4_Phi-4-multimodal-instruct_0401V1_V1_0401_NoQuestions | ntnu-smil | 2025-04-01T20:56:05Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"phi4mm",
"text-generation",
"generated_from_trainer",
"conversational",
"custom_code",
"base_model:ntnu-smil/sla-p4_Phi-4-multimodal-instruct_0401V1_V1",
"base_model:finetune:ntnu-smil/sla-p4_Phi-4-multimodal-instruct_0401V1_V1",
"license:mit",
"autotrain_compatible",
"region:us"
]
| text-generation | 2025-04-01T20:11:50Z | ---
library_name: transformers
license: mit
base_model: ntnu-smil/sla-p4_Phi-4-multimodal-instruct_0401V1_V1
tags:
- generated_from_trainer
model-index:
- name: sla-p4_sla-p4_Phi-4-multimodal-instruct_0401V1_V1_0401_NoQuestions
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. -->
# sla-p4_sla-p4_Phi-4-multimodal-instruct_0401V1_V1_0401_NoQuestions
This model is a fine-tuned version of [ntnu-smil/sla-p4_Phi-4-multimodal-instruct_0401V1_V1](https://huggingface.co/ntnu-smil/sla-p4_Phi-4-multimodal-instruct_0401V1_V1) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.95) and epsilon=1e-07 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.48.2
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
|
sagasti/cabelious-flux-dev-lora | sagasti | 2025-04-01T20:56:03Z | 0 | 0 | diffusers | [
"diffusers",
"flux",
"lora",
"replicate",
"text-to-image",
"en",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
]
| text-to-image | 2025-04-01T20:56:02Z | ---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: "black-forest-labs/FLUX.1-dev"
pipeline_tag: text-to-image
# widget:
# - text: >-
# prompt
# output:
# url: https://...
instance_prompt: Cabelious
---
# Cabelious Flux Dev Lora
<Gallery />
## About this LoRA
This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI.
It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `Cabelious` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "Cabelious",
"lora_weights": "https://huggingface.co/sagasti/cabelious-flux-dev-lora/resolve/main/lora.safetensors"
}
output = replicate.run(
"black-forest-labs/flux-dev-lora",
input=input
)
for index, item in enumerate(output):
with open(f"output_{index}.webp", "wb") as file:
file.write(item.read())
```
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('sagasti/cabelious-flux-dev-lora', weight_name='lora.safetensors')
image = pipeline('Cabelious').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
## Training details
- Steps: 2000
- Learning rate: 0.0004
- LoRA rank: 16
## Contribute your own examples
You can use the [community tab](https://huggingface.co/sagasti/cabelious-flux-dev-lora/discussions) to add images that show off what you’ve made with this LoRA.
|
tinycompany/Adi-TK-128K | tinycompany | 2025-04-01T20:55:51Z | 0 | 0 | transformers | [
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
]
| null | 2025-04-01T20:55:50Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Ai-chive/HunyuanForge | Ai-chive | 2025-04-01T20:54:44Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
]
| null | 2025-03-30T20:36:14Z | ---
license: apache-2.0
---
|
Subsets and Splits