modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-05-25 00:44:43
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 476
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 54
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-05-25 00:44:09
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
mlfoundations-dev/e1_code_fasttext_r1_1k | mlfoundations-dev | 2025-05-21T23:27:14Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"llama-factory",
"full",
"generated_from_trainer",
"conversational",
"base_model:Qwen/Qwen2.5-7B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-7B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-21T20:17:21Z | ---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: e1_code_fasttext_r1_1k
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. -->
# e1_code_fasttext_r1_1k
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/e1_code_fasttext_r1_1k 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
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 24
- total_train_batch_size: 96
- total_eval_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7.0
### Training results
### Framework versions
- Transformers 4.46.1
- Pytorch 2.6.0+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3
|
mradermacher/General-Reasoner-14B-preview-GGUF | mradermacher | 2025-05-21T23:26:55Z | 288 | 2 | transformers | [
"transformers",
"gguf",
"en",
"dataset:TIGER-Lab/VisualWebInstruct-Verified",
"base_model:TIGER-Lab/General-Reasoner-Qwen2.5-14B",
"base_model:quantized:TIGER-Lab/General-Reasoner-Qwen2.5-14B",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-04-12T13:37:09Z | ---
base_model: TIGER-Lab/General-Reasoner-Qwen2.5-14B
datasets:
- TIGER-Lab/VisualWebInstruct-Verified
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/TIGER-Lab/General-Reasoner-Qwen2.5-14B
<!-- 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/General-Reasoner-14B-preview-GGUF/resolve/main/General-Reasoner-14B-preview.Q2_K.gguf) | Q2_K | 5.9 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-14B-preview-GGUF/resolve/main/General-Reasoner-14B-preview.Q3_K_S.gguf) | Q3_K_S | 6.8 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-14B-preview-GGUF/resolve/main/General-Reasoner-14B-preview.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-14B-preview-GGUF/resolve/main/General-Reasoner-14B-preview.Q3_K_L.gguf) | Q3_K_L | 8.0 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-14B-preview-GGUF/resolve/main/General-Reasoner-14B-preview.IQ4_XS.gguf) | IQ4_XS | 8.3 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-14B-preview-GGUF/resolve/main/General-Reasoner-14B-preview.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-14B-preview-GGUF/resolve/main/General-Reasoner-14B-preview.Q4_K_M.gguf) | Q4_K_M | 9.1 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-14B-preview-GGUF/resolve/main/General-Reasoner-14B-preview.Q5_K_S.gguf) | Q5_K_S | 10.4 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-14B-preview-GGUF/resolve/main/General-Reasoner-14B-preview.Q5_K_M.gguf) | Q5_K_M | 10.6 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-14B-preview-GGUF/resolve/main/General-Reasoner-14B-preview.Q6_K.gguf) | Q6_K | 12.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-14B-preview-GGUF/resolve/main/General-Reasoner-14B-preview.Q8_0.gguf) | Q8_0 | 15.8 | fast, best quality |
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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
Wrq7z/chhat | Wrq7z | 2025-05-21T23:25:55Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2025-05-21T23:25:55Z | ---
license: apache-2.0
---
|
rosieyzh/uf-dpo-llama3_1_8b_instruct-checkpoint_375-seed_42 | rosieyzh | 2025-05-21T23:25:30Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-21T23:19:25Z | ---
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] |
MinaMila/llama_instbase_LoRa_GermanCredit_ep1_42 | MinaMila | 2025-05-21T23:23:51Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T23:23:47Z | ---
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] |
juanperez2022/lapkits2 | juanperez2022 | 2025-05-21T23:22:57Z | 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 | 2025-05-21T22:59:04Z | ---
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: lapkits
---
# Lapkits2
<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 `lapkits` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "lapkits",
"lora_weights": "https://huggingface.co/juanperez2022/lapkits2/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('juanperez2022/lapkits2', weight_name='lora.safetensors')
image = pipeline('lapkits').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: 20
## Contribute your own examples
You can use the [community tab](https://huggingface.co/juanperez2022/lapkits2/discussions) to add images that show off what you’ve made with this LoRA.
|
99eren99/ColBERT-ModernBERT-base-Turkish-uncased | 99eren99 | 2025-05-21T23:18:56Z | 66 | 5 | PyLate | [
"PyLate",
"safetensors",
"modernbert",
"ColBERT",
"sentence-transformers",
"sentence-similarity",
"generated_from_trainer",
"reranker",
"bert",
"tr",
"base_model:99eren99/ModernBERT-base-Turkish-uncased-mlm",
"base_model:finetune:99eren99/ModernBERT-base-Turkish-uncased-mlm",
"license:apache-2.0",
"region:us"
] | sentence-similarity | 2025-02-14T09:36:16Z | ---
base_model: 99eren99/ModernBERT-base-Turkish-uncased-mlm
language:
- tr
library_name: PyLate
pipeline_tag: sentence-similarity
tags:
- ColBERT
- PyLate
- sentence-transformers
- sentence-similarity
- generated_from_trainer
- reranker
- bert
license: apache-2.0
---
# Turkish Long Context ColBERT Based Reranker
This is a [PyLate](https://github.com/lightonai/pylate) model finetuned from [99eren99/ModernBERT-base-Turkish-uncased-mlm](99eren99/ModernBERT-base-Turkish-uncased-mlm). It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator.
# Better Models
512 context length: [99eren99/TrColBERT](https://huggingface.co/99eren99/TrColBERT)<br>
8192 context length: [99eren99/TrColBERT-Long](https://huggingface.co/99eren99/TrColBERT-Long)
# Model Sources
- **Documentation:** [PyLate Documentation](https://lightonai.github.io/pylate/)
- **Repository:** [PyLate on GitHub](https://github.com/lightonai/pylate)
- **Hugging Face:** [PyLate models on Hugging Face](https://huggingface.co/models?library=PyLate)
# Evaluation Results
nDCG and Recall scores for long context late interaction retrieval models, test code and detailed metrics in ["./assets"](https://huggingface.co/99eren99/ColBERT-ModernBERT-base-Turkish-uncased/tree/main/assets)
<img src="https://huggingface.co/99eren99/ColBERT-ModernBERT-base-Turkish-uncased/resolve/main/assets/tokenlengths.png"
alt="drawing"/>
# Usage
First install the PyLate library:
```bash
pip install -U einops flash_attn
pip install -U pylate
```
Then normalize your text - > lambda x: x.replace("İ", "i").replace("I", "ı").lower()
# Retrieval
PyLate provides a streamlined interface to index and retrieve documents using ColBERT models. The index leverages the Voyager HNSW index to efficiently handle document embeddings and enable fast retrieval.
# Indexing documents
First, load the ColBERT model and initialize the Voyager index, then encode and index your documents:
```python
from pylate import indexes, models, retrieve
# Step 1: Load the ColBERT model
document_length = 180#some integer [0,8192] for truncating documents, you can maybe try rope scaling for longer inputs
model = models.ColBERT(
model_name_or_path="99eren99/ColBERT-ModernBERT-base-Turkish-uncased", document_length=document_length
)
try:
model.tokenizer.model_input_names.remove("token_type_ids")
except:
pass
#model.to("cuda")
# Step 2: Initialize the Voyager index
index = indexes.Voyager(
index_folder="pylate-index",
index_name="index",
override=True, # This overwrites the existing index if any
)
# Step 3: Encode the documents
documents_ids = ["1", "2", "3"]
documents = ["document 1 text", "document 2 text", "document 3 text"]
documents_embeddings = model.encode(
documents,
batch_size=32,
is_query=False, # Ensure that it is set to False to indicate that these are documents, not queries
show_progress_bar=True,
)
# Step 4: Add document embeddings to the index by providing embeddings and corresponding ids
index.add_documents(
documents_ids=documents_ids,
documents_embeddings=documents_embeddings,
)
```
Note that you do not have to recreate the index and encode the documents every time. Once you have created an index and added the documents, you can re-use the index later by loading it:
```python
# To load an index, simply instantiate it with the correct folder/name and without overriding it
index = indexes.Voyager(
index_folder="pylate-index",
index_name="index",
)
```
# Retrieving top-k documents for queries
Once the documents are indexed, you can retrieve the top-k most relevant documents for a given set of queries.
To do so, initialize the ColBERT retriever with the index you want to search in, encode the queries and then retrieve the top-k documents to get the top matches ids and relevance scores:
```python
# Step 1: Initialize the ColBERT retriever
retriever = retrieve.ColBERT(index=index)
# Step 2: Encode the queries
queries_embeddings = model.encode(
["query for document 3", "query for document 1"],
batch_size=32,
is_query=True, # # Ensure that it is set to False to indicate that these are queries
show_progress_bar=True,
)
# Step 3: Retrieve top-k documents
scores = retriever.retrieve(
queries_embeddings=queries_embeddings,
k=10, # Retrieve the top 10 matches for each query
)
```
# Reranking
If you only want to use the ColBERT model to perform reranking on top of your first-stage retrieval pipeline without building an index, you can simply use rank function and pass the queries and documents to rerank:
```python
from pylate import rank, models
queries = [
"query A",
"query B",
]
documents = [
["document A", "document B"],
["document 1", "document C", "document B"],
]
documents_ids = [
[1, 2],
[1, 3, 2],
]
model = models.ColBERT(
model_name_or_path=pylate_model_id,
)
queries_embeddings = model.encode(
queries,
is_query=True,
)
documents_embeddings = model.encode(
documents,
is_query=False,
)
reranked_documents = rank.rerank(
documents_ids=documents_ids,
queries_embeddings=queries_embeddings,
documents_embeddings=documents_embeddings,
)
``` |
ajmalmahmood/a2c-PandaReachDense-v3 | ajmalmahmood | 2025-05-21T23:16:41Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"PandaReachDense-v3",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2025-05-21T23:12:31Z | ---
library_name: stable-baselines3
tags:
- PandaReachDense-v3
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: PandaReachDense-v3
type: PandaReachDense-v3
metrics:
- type: mean_reward
value: -0.21 +/- 0.11
name: mean_reward
verified: false
---
# **A2C** Agent playing **PandaReachDense-v3**
This is a trained model of a **A2C** agent playing **PandaReachDense-v3**
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
...
```
|
mradermacher/AV-BI-Qwen2.5-72B-PT-BR-Instruct-GGUF | mradermacher | 2025-05-21T23:16:04Z | 21 | 0 | transformers | [
"transformers",
"gguf",
"text-generation-inference",
"pt",
"base_model:amadeusai/Amadeus-Verbo-BI-Qwen-2.5-72B-PT-BR-Instruct-Experimental",
"base_model:quantized:amadeusai/Amadeus-Verbo-BI-Qwen-2.5-72B-PT-BR-Instruct-Experimental",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-04-16T09:16:07Z | ---
base_model: amadeusai/Amadeus-Verbo-BI-Qwen-2.5-72B-PT-BR-Instruct-Experimental
language:
- pt
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- text-generation-inference
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/amadeusai/Amadeus-Verbo-BI-Qwen-2.5-72B-PT-BR-Instruct-Experimental
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/AV-BI-Qwen2.5-72B-PT-BR-Instruct-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-72B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-72B-PT-BR-Instruct.Q2_K.gguf) | Q2_K | 29.9 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-72B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-72B-PT-BR-Instruct.Q3_K_S.gguf) | Q3_K_S | 34.6 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-72B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-72B-PT-BR-Instruct.Q3_K_M.gguf) | Q3_K_M | 37.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-72B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-72B-PT-BR-Instruct.Q3_K_L.gguf) | Q3_K_L | 39.6 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-72B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-72B-PT-BR-Instruct.IQ4_XS.gguf) | IQ4_XS | 40.3 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-72B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-72B-PT-BR-Instruct.Q4_K_S.gguf) | Q4_K_S | 44.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-72B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-72B-PT-BR-Instruct.Q4_K_M.gguf) | Q4_K_M | 47.5 | fast, recommended |
| [PART 1](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-72B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-72B-PT-BR-Instruct.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-72B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-72B-PT-BR-Instruct.Q5_K_S.gguf.part2of2) | Q5_K_S | 51.5 | |
| [PART 1](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-72B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-72B-PT-BR-Instruct.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-72B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-72B-PT-BR-Instruct.Q5_K_M.gguf.part2of2) | Q5_K_M | 54.5 | |
| [PART 1](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-72B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-72B-PT-BR-Instruct.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-72B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-72B-PT-BR-Instruct.Q6_K.gguf.part2of2) | Q6_K | 64.4 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-72B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-72B-PT-BR-Instruct.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-72B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-72B-PT-BR-Instruct.Q8_0.gguf.part2of2) | Q8_0 | 77.4 | fast, best quality |
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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
mradermacher/AV-BI-Qwen2.5-3B-PT-BR-Instruct-GGUF | mradermacher | 2025-05-21T23:15:53Z | 25 | 0 | transformers | [
"transformers",
"gguf",
"text-generation-inference",
"pt",
"base_model:amadeusai/Amadeus-Verbo-BI-Qwen-2.5-3B-PT-BR-Instruct-Experimental",
"base_model:quantized:amadeusai/Amadeus-Verbo-BI-Qwen-2.5-3B-PT-BR-Instruct-Experimental",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-04-16T09:41:54Z | ---
base_model: amadeusai/Amadeus-Verbo-BI-Qwen-2.5-3B-PT-BR-Instruct-Experimental
language:
- pt
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- text-generation-inference
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/amadeusai/Amadeus-Verbo-BI-Qwen-2.5-3B-PT-BR-Instruct-Experimental
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/AV-BI-Qwen2.5-3B-PT-BR-Instruct-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-3B-PT-BR-Instruct.Q2_K.gguf) | Q2_K | 1.4 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-3B-PT-BR-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.8 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-3B-PT-BR-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-3B-PT-BR-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-3B-PT-BR-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-3B-PT-BR-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.3 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-3B-PT-BR-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.3 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-3B-PT-BR-Instruct.Q6_K.gguf) | Q6_K | 2.6 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-3B-PT-BR-Instruct.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-3B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-3B-PT-BR-Instruct.f16.gguf) | f16 | 6.3 | 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 -->
|
mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-GGUF | mradermacher | 2025-05-21T23:15:19Z | 44 | 0 | transformers | [
"transformers",
"gguf",
"text-generation-inference",
"pt",
"base_model:amadeusai/Amadeus-Verbo-BI-Qwen-2.5-32B-PT-BR-Instruct-Experimental",
"base_model:quantized:amadeusai/Amadeus-Verbo-BI-Qwen-2.5-32B-PT-BR-Instruct-Experimental",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-04-16T12:05:37Z | ---
base_model: amadeusai/Amadeus-Verbo-BI-Qwen-2.5-32B-PT-BR-Instruct-Experimental
language:
- pt
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- text-generation-inference
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/amadeusai/Amadeus-Verbo-BI-Qwen-2.5-32B-PT-BR-Instruct-Experimental
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.Q2_K.gguf) | Q2_K | 12.4 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.Q3_K_S.gguf) | Q3_K_S | 14.5 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.Q3_K_M.gguf) | Q3_K_M | 16.0 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.Q3_K_L.gguf) | Q3_K_L | 17.3 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.IQ4_XS.gguf) | IQ4_XS | 18.0 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.Q4_K_S.gguf) | Q4_K_S | 18.9 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.Q4_K_M.gguf) | Q4_K_M | 20.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.Q5_K_S.gguf) | Q5_K_S | 22.7 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.Q5_K_M.gguf) | Q5_K_M | 23.4 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.Q6_K.gguf) | Q6_K | 27.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.Q8_0.gguf) | Q8_0 | 34.9 | fast, best quality |
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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF | mradermacher | 2025-05-21T23:15:06Z | 144 | 0 | transformers | [
"transformers",
"gguf",
"text-generation-inference",
"pt",
"base_model:amadeusai/Amadeus-Verbo-BI-Qwen-2.5-32B-PT-BR-Instruct-Experimental",
"base_model:quantized:amadeusai/Amadeus-Verbo-BI-Qwen-2.5-32B-PT-BR-Instruct-Experimental",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2025-04-16T13:18:34Z | ---
base_model: amadeusai/Amadeus-Verbo-BI-Qwen-2.5-32B-PT-BR-Instruct-Experimental
language:
- pt
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- text-generation-inference
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/amadeusai/Amadeus-Verbo-BI-Qwen-2.5-32B-PT-BR-Instruct-Experimental
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | |
| [GGUF](https://huggingface.co/mradermacher/AV-BI-Qwen2.5-32B-PT-BR-Instruct-i1-GGUF/resolve/main/AV-BI-Qwen2.5-32B-PT-BR-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
mradermacher/General-Reasoner-7B-preview-i1-GGUF | mradermacher | 2025-05-21T23:14:52Z | 395 | 1 | transformers | [
"transformers",
"gguf",
"General-Reasoner-7B",
"zho",
"eng",
"fra",
"spa",
"por",
"deu",
"ita",
"rus",
"jpn",
"kor",
"vie",
"tha",
"ara",
"base_model:TIGER-Lab/General-Reasoner-Qwen2.5-7B",
"base_model:quantized:TIGER-Lab/General-Reasoner-Qwen2.5-7B",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2025-04-16T14:30:04Z | ---
base_model: TIGER-Lab/General-Reasoner-Qwen2.5-7B
language:
- zho
- eng
- fra
- spa
- por
- deu
- ita
- rus
- jpn
- kor
- vie
- tha
- ara
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- General-Reasoner-7B
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/TIGER-Lab/General-Reasoner-Qwen2.5-7B
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/General-Reasoner-7B-preview-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-7B-preview-i1-GGUF/resolve/main/General-Reasoner-7B-preview.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
jinx2321/mt5-tagged-1e4-paper | jinx2321 | 2025-05-21T23:14:28Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"mt5",
"text2text-generation",
"generated_from_trainer",
"base_model:google/mt5-small",
"base_model:finetune:google/mt5-small",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2025-05-21T21:28:31Z | ---
library_name: transformers
license: apache-2.0
base_model: google/mt5-small
tags:
- generated_from_trainer
model-index:
- name: mt5-tagged-1e4-paper
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. -->
# mt5-tagged-1e4-paper
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None 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: 0.0001
- train_batch_size: 128
- eval_batch_size: 8
- 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: 3
### Training results
### Framework versions
- Transformers 4.52.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1
|
rosieyzh/uf-dpo-llama3_1_8b_instruct-checkpoint_2625-seed_42 | rosieyzh | 2025-05-21T23:12:21Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-21T23:05:52Z | ---
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] |
bruhzair/group1-d | bruhzair | 2025-05-21T23:11:36Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"mergekit",
"merge",
"conversational",
"arxiv:2403.19522",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-21T22:50:45Z | ---
base_model: []
library_name: transformers
tags:
- mergekit
- merge
---
# group1-d
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using /workspace/cache/models--TheSkullery--L3.1x3.3-Hydroblated-R1-70B-v5/snapshots/885b8ba1b37ca0ec5135b20c7ec4ed35441536f7 as a base.
### Models Merged
The following models were included in the merge:
* /workspace/cache/models--Daemontatox--Llama3.3-70B-CogniLink/snapshots/99ede7d64184a107a405eea01f0a3eb5dc9f669a
* /workspace/cache/models--Doctor-Shotgun--L3.3-70B-Magnum-Nexus/snapshots/1fc6f9b78d8921a26003edb06a292e94488a4c52
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: /workspace/cache/models--TheSkullery--L3.1x3.3-Hydroblated-R1-70B-v5/snapshots/885b8ba1b37ca0ec5135b20c7ec4ed35441536f7
- model: /workspace/cache/models--Doctor-Shotgun--L3.3-70B-Magnum-Nexus/snapshots/1fc6f9b78d8921a26003edb06a292e94488a4c52
- model: /workspace/cache/models--Daemontatox--Llama3.3-70B-CogniLink/snapshots/99ede7d64184a107a405eea01f0a3eb5dc9f669a
base_model: /workspace/cache/models--TheSkullery--L3.1x3.3-Hydroblated-R1-70B-v5/snapshots/885b8ba1b37ca0ec5135b20c7ec4ed35441536f7
merge_method: model_stock
tokenizer:
source: union
int8_mask: true
dtype: bfloat16
```
|
SalehAhmad/llama3.1-8b-qlora | SalehAhmad | 2025-05-21T23:10:56Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"generated_from_trainer",
"base_model:meta-llama/Llama-3.1-8B",
"base_model:adapter:meta-llama/Llama-3.1-8B",
"license:llama3.1",
"region:us"
] | null | 2025-05-21T20:02:07Z | ---
library_name: peft
license: llama3.1
base_model: meta-llama/Llama-3.1-8B
tags:
- generated_from_trainer
model-index:
- name: llama3.1-8b-qlora
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. -->
# llama3.1-8b-qlora
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) 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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 256
- 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: 1
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| No log | 0.9961 | 190 | 1.2664 |
### Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1 |
Inabia-AI/Kymera_Revage_standalone_lora_3.1_2025_05_21_23_04_14 | Inabia-AI | 2025-05-21T23:09:02Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-21T23:07:29Z | ---
base_model: unsloth/meta-llama-3.1-8b-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** Inabia-AI
- **License:** apache-2.0
- **Finetuned from model :** unsloth/meta-llama-3.1-8b-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)
|
Wilhelmas02/1000phisingmistrall-Q4_K_M-GGUF | Wilhelmas02 | 2025-05-21T23:07:02Z | 0 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"base_model:Wilhelmas02/1000phisingmistrall",
"base_model:quantized:Wilhelmas02/1000phisingmistrall",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-21T23:06:44Z | ---
base_model: Wilhelmas02/1000phisingmistrall
tags:
- llama-cpp
- gguf-my-repo
---
# Wilhelmas02/1000phisingmistrall-Q4_K_M-GGUF
This model was converted to GGUF format from [`Wilhelmas02/1000phisingmistrall`](https://huggingface.co/Wilhelmas02/1000phisingmistrall) 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/Wilhelmas02/1000phisingmistrall) 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 Wilhelmas02/1000phisingmistrall-Q4_K_M-GGUF --hf-file 1000phisingmistrall-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Wilhelmas02/1000phisingmistrall-Q4_K_M-GGUF --hf-file 1000phisingmistrall-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 Wilhelmas02/1000phisingmistrall-Q4_K_M-GGUF --hf-file 1000phisingmistrall-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Wilhelmas02/1000phisingmistrall-Q4_K_M-GGUF --hf-file 1000phisingmistrall-q4_k_m.gguf -c 2048
```
|
Kurosawama/Llama-2-7b-DPO-beamsearch-align | Kurosawama | 2025-05-21T23:06:42Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"trl",
"dpo",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T23:06:30Z | ---
library_name: transformers
tags:
- trl
- dpo
---
# 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] |
morturr/Mistral-7B-v0.1-amazon-seed-18-2025-05-21 | morturr | 2025-05-21T23:03:25Z | 0 | 0 | peft | [
"peft",
"safetensors",
"trl",
"sft",
"generated_from_trainer",
"base_model:mistralai/Mistral-7B-v0.1",
"base_model:adapter:mistralai/Mistral-7B-v0.1",
"license:apache-2.0",
"region:us"
] | null | 2025-05-21T13:26:56Z | ---
library_name: peft
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Mistral-7B-v0.1-amazon-seed-18-2025-05-21
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. -->
# Mistral-7B-v0.1-amazon-seed-18-2025-05-21
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None 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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 18
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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
- num_epochs: 3
### Training results
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.1
- Pytorch 2.5.1+cu124
- Datasets 3.0.2
- Tokenizers 0.20.1 |
g-assismoraes/gemma-3-4b-it-fpi-alpha2.0-var-tiebe | g-assismoraes | 2025-05-21T23:02:05Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gemma3",
"image-text-to-text",
"arxiv:1910.09700",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | image-text-to-text | 2025-05-21T22:57:54Z | ---
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] |
BootesVoid/cmaygehmz03iju1cgc8dee12h_cmayilpi703k6u1cgqh53d03c | BootesVoid | 2025-05-21T23:00:56Z | 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 | 2025-05-21T23:00:47Z | ---
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: BELOWZERO
---
# Cmaygehmz03Iju1Cgc8Dee12H_Cmayilpi703K6U1Cgqh53D03C
<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 `BELOWZERO` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "BELOWZERO",
"lora_weights": "https://huggingface.co/BootesVoid/cmaygehmz03iju1cgc8dee12h_cmayilpi703k6u1cgqh53d03c/resolve/main/lora.safetensors"
}
output = replicate.run(
"black-forest-labs/flux-dev-lora",
input=input
)
for index, item in enumerate(output):
with open(f"output_{index}.webp", "wb") as file:
file.write(item.read())
```
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('BootesVoid/cmaygehmz03iju1cgc8dee12h_cmayilpi703k6u1cgqh53d03c', weight_name='lora.safetensors')
image = pipeline('BELOWZERO').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
## Training details
- Steps: 2000
- Learning rate: 0.0004
- LoRA rank: 16
## Contribute your own examples
You can use the [community tab](https://huggingface.co/BootesVoid/cmaygehmz03iju1cgc8dee12h_cmayilpi703k6u1cgqh53d03c/discussions) to add images that show off what you’ve made with this LoRA.
|
refikcam/poca-SoccerTwos | refikcam | 2025-05-21T23:00:31Z | 0 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"SoccerTwos",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
] | reinforcement-learning | 2025-05-21T23:00:10Z | ---
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: refikcam/poca-SoccerTwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
salmanalii/ppo-LunarLander-v2 | salmanalii | 2025-05-21T22:59:48Z | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | 2025-05-21T22:59:24Z | ---
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: 241.27 +/- 16.77
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
...
```
|
TenthWax/wethair | TenthWax | 2025-05-21T22:58:42Z | 0 | 0 | diffusers | [
"diffusers",
"text-to-image",
"lora",
"template:diffusion-lora",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:creativeml-openrail-m",
"region:us"
] | text-to-image | 2025-05-21T22:58:38Z | ---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: "UNICODE\0\0r\0e\0v\0e\0a\0l\0i\0n\0g\0 \0a\0 \0b\0r\0i\0g\0h\0t\0,\0 \0a\0s\0 \0i\0t\0 \0c\0l\0i\0n\0g\0s\0 \0t\0o\0 \0h\0e\0r\0 \0s\0h\0o\0u\0l\0d\0e\0r\0s\0.\0 \0H\0e\0r\0 \0h\0a\0i\0r\0 \0i\0s\0 \0p\0a\0r\0t\0e\0d\0 \0i\0n\0 \0t\0h\0e\0 \0m\0i\0d\0d\0l\0e\0 \0a\0n\0d\0 \0c\0a\0s\0c\0a\0d\0e\0s\0 \0d\0o\0w\0n\0 \0t\0o\0 \0h\0e\0r\0 \0s\0h\0o\0u\0l\0d\0e\0r\0s\0.\0,\0 \0s\0o\0m\0e\0w\0h\0a\0t\0 \0s\0u\0r\0r\0e\0a\0l\0i\0s\0t\0i\0c\0 \0t\0e\0c\0h\0n\0i\0q\0u\0e\0,\0 \0r\0e\0v\0e\0a\0l\0i\0n\0g\0 \0h\0e\0r\0 \0f\0a\0c\0e\0 \0c\0l\0e\0a\0r\0l\0y\0.\0,\0 \0s\0p\0r\0a\0y\0i\0n\0g\0 \0w\0a\0t\0e\0r\0 \0o\0n\0t\0o\0 \0h\0e\0r\0.\0 \0T\0h\0e\0 \0w\0o\0m\0a\0n\0 \0i\0s\0 \0o\0f\0 \0C\0a\0u\0c\0a\0s\0i\0a\0n\0 \0e\0t\0h\0n\0i\0c\0i\0t\0y\0,\0 \0r\0e\0f\0l\0e\0c\0t\0i\0v\0e\0 \0s\0u\0r\0f\0a\0c\0e\0 \0v\0i\0s\0i\0b\0l\0e\0 \0i\0n\0 \0t\0h\0e\0 \0b\0a\0c\0k\0g\0r\0o\0u\0n\0d\0.\0 \0T\0h\0e\0 \0w\0o\0m\0a\0n\0'\0s\0 \0h\0a\0i\0r\0 \0i\0s\0 \0w\0e\0t\0,\0 \0g\0i\0v\0i\0n\0g\0 \0h\0e\0r\0 \0a\0n\0 \0i\0n\0t\0r\0o\0s\0p\0e\0c\0t\0i\0v\0e\0 \0a\0p\0p\0e\0a\0r\0a\0n\0c\0e\0.\0 \0H\0e\0r\0 \0e\0y\0e\0b\0r\0o\0w\0s\0 \0a\0r\0e\0 \0w\0e\0l\0l\0-\0g\0r\0o\0o\0m\0e\0d\0,\0 \0w\0h\0i\0c\0h\0 \0c\0l\0i\0n\0g\0s\0 \0t\0o\0 \0h\0e\0r\0 \0b\0o\0d\0y\0"
output:
url: images/soaking_wet_hair_e000010_00_20250209104440.jpeg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: wethair
license: creativeml-openrail-m
---
# Wet Hair
<Gallery />
## Trigger words
You should use `wethair` to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](/TenthWax/wethair/tree/main) them in the Files & versions tab.
|
rosieyzh/uf-dpo-llama3_1_8b_instruct-checkpoint_2500-seed_42 | rosieyzh | 2025-05-21T22:58:33Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-21T22:52:27Z | ---
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] |
async0x42/Devstral-Small-2505-exl3_4.5bpw | async0x42 | 2025-05-21T22:57:59Z | 0 | 0 | vllm | [
"vllm",
"safetensors",
"mistral",
"text2text-generation",
"en",
"fr",
"de",
"es",
"pt",
"it",
"ja",
"ko",
"ru",
"zh",
"ar",
"fa",
"id",
"ms",
"ne",
"pl",
"ro",
"sr",
"sv",
"tr",
"uk",
"vi",
"hi",
"bn",
"base_model:mistralai/Devstral-Small-2505",
"base_model:quantized:mistralai/Devstral-Small-2505",
"license:apache-2.0",
"exl3",
"region:us"
] | text2text-generation | 2025-05-21T22:52:01Z | ---
language:
- en
- fr
- de
- es
- pt
- it
- ja
- ko
- ru
- zh
- ar
- fa
- id
- ms
- ne
- pl
- ro
- sr
- sv
- tr
- uk
- vi
- hi
- bn
license: apache-2.0
library_name: vllm
inference: false
base_model:
- mistralai/Devstral-Small-2505
extra_gated_description: >-
If you want to learn more about how we process your personal data, please read
our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
pipeline_tag: text2text-generation
---
# Model Card for mistralai/Devstrall-Small-2505
Devstral is an agentic LLM for software engineering tasks built under a collaboration between [Mistral AI](https://mistral.ai/) and [All Hands AI](https://www.all-hands.dev/) 🙌. Devstral excels at using tools to explore codebases, editing multiple files and power software engineering agents. The model achieves remarkable performance on SWE-bench which positionates it as the #1 open source model on this [benchmark](#benchmark-results).
It is finetuned from [Mistral-Small-3.1](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Base-2503), therefore it has a long context window of up to 128k tokens. As a coding agent, Devstral is text-only and before fine-tuning from `Mistral-Small-3.1` the vision encoder was removed.
For enterprises requiring specialized capabilities (increased context, domain-specific knowledge, etc.), we will release commercial models beyond what Mistral AI contributes to the community.
Learn more about Devstral in our [blog post](https://mistral.ai/news/devstral).
## Key Features:
- **Agentic coding**: Devstral is designed to excel at agentic coding tasks, making it a great choice for software engineering agents.
- **lightweight**: with its compact size of just 24 billion parameters, Devstral is light enough to run on a single RTX 4090 or a Mac with 32GB RAM, making it an appropriate model for local deployment and on-device use.
- **Apache 2.0 License**: Open license allowing usage and modification for both commercial and non-commercial purposes.
- **Context Window**: A 128k context window.
- **Tokenizer**: Utilizes a Tekken tokenizer with a 131k vocabulary size.
## Benchmark Results
### SWE-Bench
Devstral achieves a score of 46.8% on SWE-Bench Verified, outperforming prior open-source SoTA by 6%.
| Model | Scaffold | SWE-Bench Verified (%) |
|------------------|--------------------|------------------------|
| Devstral | OpenHands Scaffold | **46.8** |
| GPT-4.1-mini | OpenAI Scaffold | 23.6 |
| Claude 3.5 Haiku | Anthropic Scaffold | 40.6 |
| SWE-smith-LM 32B | SWE-agent Scaffold | 40.2 |
When evaluated under the same test scaffold (OpenHands, provided by All Hands AI 🙌), Devstral exceeds far larger models such as Deepseek-V3-0324 and Qwen3 232B-A22B.
## Usage
We recommend to use Devstral with the [OpenHands](https://github.com/All-Hands-AI/OpenHands/tree/main) scaffold.
You can use it either through our API or by running locally.
### API
Follow these [instructions](https://docs.mistral.ai/getting-started/quickstart/#account-setup) to create a Mistral account and get an API key.
Then run these commands to start the OpenHands docker container.
```bash
export MISTRAL_API_KEY=<MY_KEY>
docker pull docker.all-hands.dev/all-hands-ai/runtime:0.39-nikolaik
mkdir -p ~/.openhands-state && echo '{"language":"en","agent":"CodeActAgent","max_iterations":null,"security_analyzer":null,"confirmation_mode":false,"llm_model":"mistral/devstral-small-2505","llm_api_key":"'$MISTRAL_API_KEY'","remote_runtime_resource_factor":null,"github_token":null,"enable_default_condenser":true}' > ~/.openhands-state/settings.json
docker run -it --rm --pull=always \
-e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.39-nikolaik \
-e LOG_ALL_EVENTS=true \
-v /var/run/docker.sock:/var/run/docker.sock \
-v ~/.openhands-state:/.openhands-state \
-p 3000:3000 \
--add-host host.docker.internal:host-gateway \
--name openhands-app \
docker.all-hands.dev/all-hands-ai/openhands:0.39
```
### Local inference
You can also run the model locally. It can be done with LMStudio or other providers listed below.
Launch Openhands
You can now interact with the model served from LM Studio with openhands. Start the openhands server with the docker
```bash
docker pull docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik
docker run -it --rm --pull=always \
-e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik \
-e LOG_ALL_EVENTS=true \
-v /var/run/docker.sock:/var/run/docker.sock \
-v ~/.openhands-state:/.openhands-state \
-p 3000:3000 \
--add-host host.docker.internal:host-gateway \
--name openhands-app \
docker.all-hands.dev/all-hands-ai/openhands:0.38
```
The server will start at http://0.0.0.0:3000. Open it in your browser and you will see a tab AI Provider Configuration.
Now you can start a new conversation with the agent by clicking on the plus sign on the left bar.
The model can also be deployed with the following libraries:
- [`LMStudio (recommended for quantized model)`](https://lmstudio.ai/): See [here](#lmstudio-recommended-for-quantized-model)
- [`vllm (recommended)`](https://github.com/vllm-project/vllm): See [here](#vllm-recommended)
- [`mistral-inference`](https://github.com/mistralai/mistral-inference): See [here](#mistral-inference)
- [`transformers`](https://github.com/huggingface/transformers): See [here](#transformers)
- [`ollama`](https://github.com/ollama/ollama): See [here](#ollama)
### OpenHands (recommended)
#### Launch a server to deploy Devstral-Small-2505
Make sure you launched an OpenAI-compatible server such as vLLM or Ollama as described above. Then, you can use OpenHands to interact with `Devstral-Small-2505`.
In the case of the tutorial we spineed up a vLLM server running the command:
```bash
vllm serve mistralai/Devstral-Small-2505 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2
```
The server address should be in the following format: `http://<your-server-url>:8000/v1`
#### Launch OpenHands
You can follow installation of OpenHands [here](https://docs.all-hands.dev/modules/usage/installation).
The easiest way to launch OpenHands is to use the Docker image:
```bash
docker pull docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik
docker run -it --rm --pull=always \
-e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik \
-e LOG_ALL_EVENTS=true \
-v /var/run/docker.sock:/var/run/docker.sock \
-v ~/.openhands-state:/.openhands-state \
-p 3000:3000 \
--add-host host.docker.internal:host-gateway \
--name openhands-app \
docker.all-hands.dev/all-hands-ai/openhands:0.38
```
Then, you can access the OpenHands UI at `http://localhost:3000`.
#### Connect to the server
When accessing the OpenHands UI, you will be prompted to connect to a server. You can use the advanced mode to connect to the server you launched earlier.
Fill the following fields:
- **Custom Model**: `openai/mistralai/Devstral-Small-2505`
- **Base URL**: `http://<your-server-url>:8000/v1`
- **API Key**: `token` (or any other token you used to launch the server if any)
#### Use OpenHands powered by Devstral
Now you're good to use Devstral Small inside OpenHands by **starting a new conversation**. Let's build a To-Do list app.
<details>
<summary>To-Do list app</summary
1. Let's ask Devstral to generate the app with the following prompt:
```txt
Build a To-Do list app with the following requirements:
- Built using FastAPI and React.
- Make it a one page app that:
- Allows to add a task.
- Allows to delete a task.
- Allows to mark a task as done.
- Displays the list of tasks.
- Store the tasks in a SQLite database.
```
2. Let's see the result
You should see the agent construct the app and be able to explore the code it generated.
If it doesn't do it automatically, ask Devstral to deploy the app or do it manually, and then go the front URL deployment to see the app.
3. Iterate
Now that you have a first result you can iterate on it by asking your agent to improve it. For example, in the app generated we could click on a task to mark it checked but having a checkbox would improve UX. You could also ask it to add a feature to edit a task, or to add a feature to filter the tasks by status.
Enjoy building with Devstral Small and OpenHands!
</details>
### LMStudio (recommended for quantized model)
Download the weights from huggingface:
```
pip install -U "huggingface_hub[cli]"
huggingface-cli download \
"mistralai/Devstral-Small-2505_gguf" \
--include "devstralQ4_K_M.gguf" \
--local-dir "mistralai/Devstral-Small-2505_gguf/"
```
You can serve the model locally with [LMStudio](https://lmstudio.ai/).
* Download [LM Studio](https://lmstudio.ai/) and install it
* Install `lms cli ~/.lmstudio/bin/lms bootstrap`
* In a bash terminal, run `lms import devstralQ4_K_M.ggu` in the directory where you've downloaded the model checkpoint (e.g. `mistralai/Devstral-Small-2505_gguf`)
* Open the LMStudio application, click the terminal icon to get into the developer tab. Click select a model to load and select Devstral Q4 K M. Toggle the status button to start the model, in setting oggle Serve on Local Network to be on.
* On the right tab, you will see an API identifier which should be devstralq4_k_m and an api address under API Usage. Keep note of this address, we will use it in the next step.
Launch Openhands
You can now interact with the model served from LM Studio with openhands. Start the openhands server with the docker
```bash
docker pull docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik
docker run -it --rm --pull=always \
-e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik \
-e LOG_ALL_EVENTS=true \
-v /var/run/docker.sock:/var/run/docker.sock \
-v ~/.openhands-state:/.openhands-state \
-p 3000:3000 \
--add-host host.docker.internal:host-gateway \
--name openhands-app \
docker.all-hands.dev/all-hands-ai/openhands:0.38
```
Click “see advanced setting” on the second line.
In the new tab, toggle advanced to on. Set the custom model to be mistral/devstralq4_k_m and Base URL the api address we get from the last step in LM Studio. Set API Key to dummy. Click save changes.
### vLLM (recommended)
We recommend using this model with the [vLLM library](https://github.com/vllm-project/vllm)
to implement production-ready inference pipelines.
**_Installation_**
Make sure you install [`vLLM >= 0.8.5`](https://github.com/vllm-project/vllm/releases/tag/v0.8.5):
```
pip install vllm --upgrade
```
Doing so should automatically install [`mistral_common >= 1.5.5`](https://github.com/mistralai/mistral-common/releases/tag/v1.5.5).
To check:
```
python -c "import mistral_common; print(mistral_common.__version__)"
```
You can also make use of a ready-to-go [docker image](https://github.com/vllm-project/vllm/blob/main/Dockerfile) or on the [docker hub](https://hub.docker.com/layers/vllm/vllm-openai/latest/images/sha256-de9032a92ffea7b5c007dad80b38fd44aac11eddc31c435f8e52f3b7404bbf39).
#### Server
We recommand that you use Devstral in a server/client setting.
1. Spin up a server:
```
vllm serve mistralai/Devstral-Small-2505 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2
```
2. To ping the client you can use a simple Python snippet.
```py
import requests
import json
from huggingface_hub import hf_hub_download
url = "http://<your-server-url>:8000/v1/chat/completions"
headers = {"Content-Type": "application/json", "Authorization": "Bearer token"}
model = "mistralai/Devstral-Small-2505"
def load_system_prompt(repo_id: str, filename: str) -> str:
file_path = hf_hub_download(repo_id=repo_id, filename=filename)
with open(file_path, "r") as file:
system_prompt = file.read()
return system_prompt
SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt")
messages = [
{"role": "system", "content": SYSTEM_PROMPT},
{
"role": "user",
"content": [
{
"type": "text",
"text": "<your-command>",
},
],
},
]
data = {"model": model, "messages": messages, "temperature": 0.15}
response = requests.post(url, headers=headers, data=json.dumps(data))
print(response.json()["choices"][0]["message"]["content"])
```
### Mistral-inference
We recommend using mistral-inference to quickly try out / "vibe-check" Devstral.
#### Install
Make sure to have mistral_inference >= 1.6.0 installed.
```bash
pip install mistral_inference --upgrade
```
#### Download
```python
from huggingface_hub import snapshot_download
from pathlib import Path
mistral_models_path = Path.home().joinpath('mistral_models', 'Devstral')
mistral_models_path.mkdir(parents=True, exist_ok=True)
snapshot_download(repo_id="mistralai/Devstral-Small-2505", allow_patterns=["params.json", "consolidated.safetensors", "tekken.json"], local_dir=mistral_models_path)
```
#### Python
You can run the model using the following command:
```bash
mistral-chat $HOME/mistral_models/Devstral --instruct --max_tokens 300
```
You can then prompt it with anything you'd like.
### Ollama
You can run Devstral using the [Ollama](https://ollama.ai/) CLI.
```bash
ollama run devstral
```
### Transformers
To make the best use of our model with transformers make sure to have [installed](https://github.com/mistralai/mistral-common) ` mistral-common >= 1.5.5` to use our tokenizer.
```bash
pip install mistral-common --upgrade
```
Then load our tokenizer along with the model and generate:
```python
import torch
from mistral_common.protocol.instruct.messages import (
SystemMessage, UserMessage
)
from mistral_common.protocol.instruct.request import ChatCompletionRequest
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from mistral_common.tokens.tokenizers.tekken import SpecialTokenPolicy
from huggingface_hub import hf_hub_download
from transformers import AutoModelForCausalLM
def load_system_prompt(repo_id: str, filename: str) -> str:
file_path = hf_hub_download(repo_id=repo_id, filename=filename)
with open(file_path, "r") as file:
system_prompt = file.read()
return system_prompt
model_id = "mistralai/Devstral-Small-2505"
tekken_file = hf_hub_download(repo_id=model_id, filename="tekken.json")
SYSTEM_PROMPT = load_system_prompt(model_id, "SYSTEM_PROMPT.txt")
tokenizer = MistralTokenizer.from_file(tekken_file)
model = AutoModelForCausalLM.from_pretrained(model_id)
tokenized = tokenizer.encode_chat_completion(
ChatCompletionRequest(
messages=[
SystemMessage(content=SYSTEM_PROMPT),
UserMessage(content="<your-command>"),
],
)
)
output = model.generate(
input_ids=torch.tensor([tokenized.tokens]),
max_new_tokens=1000,
)[0]
decoded_output = tokenizer.decode(output[len(tokenized.tokens):])
print(decoded_output)
``` |
MinaMila/llama_instbase_LoRa_GermanCredit_cfda_ep10_66 | MinaMila | 2025-05-21T22:57:41Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:57:38Z | ---
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] |
FormlessAI/3dcd1774-d5ca-4d59-befe-9aafa1b66d9d | FormlessAI | 2025-05-21T22:56:50Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"phi3",
"text-generation",
"generated_from_trainer",
"trl",
"dpo",
"conversational",
"custom_code",
"arxiv:2305.18290",
"base_model:microsoft/Phi-3-mini-4k-instruct",
"base_model:finetune:microsoft/Phi-3-mini-4k-instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-21T21:13:12Z | ---
base_model: microsoft/Phi-3-mini-4k-instruct
library_name: transformers
model_name: 3dcd1774-d5ca-4d59-befe-9aafa1b66d9d
tags:
- generated_from_trainer
- trl
- dpo
licence: license
---
# Model Card for 3dcd1774-d5ca-4d59-befe-9aafa1b66d9d
This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-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="FormlessAI/3dcd1774-d5ca-4d59-befe-9aafa1b66d9d", 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/phoenix-formless/Gradients/runs/c41evs60)
This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
### Framework versions
- TRL: 0.17.0
- Transformers: 4.51.3
- Pytorch: 2.7.0+cu118
- Datasets: 3.5.1
- Tokenizers: 0.21.1
## Citations
Cite DPO as:
```bibtex
@inproceedings{rafailov2023direct,
title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
year = 2023,
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
MinaMila/llama_instbase_LoRa_GermanCredit_ep10_66 | MinaMila | 2025-05-21T22:56:02Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:55:57Z | ---
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] |
xuan-luo/MTPQwen3-8B-T1234-Eagle-d4-noembed | xuan-luo | 2025-05-21T22:55:42Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"mtpqwen3",
"text-generation",
"conversational",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"region:us"
] | text-generation | 2025-05-21T22:52:39Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
papacliff/orpheus-3b-0.1-ft-ru | papacliff | 2025-05-21T22:52:23Z | 0 | 0 | null | [
"text-to-speech",
"ru",
"dataset:its5Q/bigger-ru-book",
"base_model:canopylabs/orpheus-3b-0.1-ft",
"base_model:finetune:canopylabs/orpheus-3b-0.1-ft",
"license:apache-2.0",
"region:us"
] | text-to-speech | 2025-05-21T10:59:04Z | ---
license: apache-2.0
datasets:
- its5Q/bigger-ru-book
language:
- ru
base_model:
- canopylabs/orpheus-3b-0.1-ft
pipeline_tag: text-to-speech
---
### (WIP) 40_000 / 100_000 steps done.
- Total dataset length: ~188 hours of russian speech.
- Training steps: 10 epochs of 10_000 steps
- Loss: (To be updated. Current value avg) 3.794000
### Available russian speakers (original dataset speaker names):
| Speaker | Samples | Duration (hours) |
|-------------------|---------|------------------|
| irina_bulekova | 8012 | 17.50 |
| smelova_s | 26371 | 41.65 |
| alina_archibasova | 14097 | 22.07 |
| maksim_suslov | 6440 | 20.70 |
| daniel_che | 5502 | 19.20 |
| evgenii_lebedev | 3811 | 12.50 |
| evgenii_babincev | 5614 | 8.90 |
| aleksandr_zbarovskii | 6212 | 9.39 |
| jam_nebesky | 8052 | 19.82 |
| aleksandr_kotov | 12706 | 16.63 |
| **TOTAL** | 96817 | 188.35 |
---
# Original model card
Orpheus TTS is a state-of-the-art, Llama-based Speech-LLM designed for high-quality, empathetic text-to-speech generation. This model has been finetuned to deliver human-level speech synthesis, achieving exceptional clarity, expressiveness, and real-time streaming performances.
# Model Details
### Model Capabilities
- **Human-Like Speech**: Natural intonation, emotion, and rhythm that is superior to SOTA closed source models
- **Zero-Shot Voice Cloning**: Clone voices without prior fine-tuning
- **Guided Emotion and Intonation**: Control speech and emotion characteristics with simple tags
- **Low Latency**: ~200ms streaming latency for realtime applications, reducible to ~100ms with input streaming
### Model Sources
- **GitHub Repo:** [https://github.com/canopyai/Orpheus-TTS](https://github.com/canopyai/Orpheus-TTS)
- **Blog Post:** [https://canopylabs.ai/model-releases](https://canopylabs.ai/model-releases)
- **Colab Inference Notebook:** [notebook link](https://colab.research.google.com/drive/1KhXT56UePPUHhqitJNUxq63k-pQomz3N?usp=sharing)
- **One-Click Deployment on Baseten:** [https://www.baseten.co/library/orpheus-tts/](https://www.baseten.co/library/orpheus-tts/)
# Usage
Check out our Colab ([link to Colab](https://colab.research.google.com/drive/1KhXT56UePPUHhqitJNUxq63k-pQomz3N?usp=sharing)) or GitHub ([link to GitHub](https://github.com/canopyai/Orpheus-TTS)) on how to run easy inference on our finetuned models.
# Model Misuse
Do not use our models for impersonation without consent, misinformation or deception (including fake news or fraudulent calls), or any illegal or harmful activity. By using this model, you agree to follow all applicable laws and ethical guidelines. We disclaim responsibility for any use.
|
haihp02/147143ee-df4f-4a04-b39b-0dfaca9271dd-phase2-adapter | haihp02 | 2025-05-21T22:50:20Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"generated_from_trainer",
"trl",
"sft",
"dpo",
"arxiv:2305.18290",
"base_model:Qwen/Qwen2.5-1.5B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-1.5B-Instruct",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:49:49Z | ---
base_model: Qwen/Qwen2.5-1.5B-Instruct
library_name: transformers
model_name: 147143ee-df4f-4a04-b39b-0dfaca9271dd-phase2-adapter
tags:
- generated_from_trainer
- trl
- sft
- dpo
licence: license
---
# Model Card for 147143ee-df4f-4a04-b39b-0dfaca9271dd-phase2-adapter
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-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="haihp02/147143ee-df4f-4a04-b39b-0dfaca9271dd-phase2-adapter", 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/trunghainguyenhp02/sn56-dpo-train/runs/kzueml1q)
This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
### Framework versions
- TRL: 0.15.2
- Transformers: 4.51.3
- Pytorch: 2.7.0+cu126
- Datasets: 3.6.0
- Tokenizers: 0.21.1
## Citations
Cite DPO as:
```bibtex
@inproceedings{rafailov2023direct,
title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
year = 2023,
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
Original-Jaisalmer-Tharki-Baba-Viral-Video/18.Jaisalmer.old.Baba.viral.video | Original-Jaisalmer-Tharki-Baba-Viral-Video | 2025-05-21T22:48:50Z | 0 | 0 | null | [
"region:us"
] | null | 2025-05-21T22:47:35Z | <a rel="nofollow" href="https://tinyurl.com/58snvazm?V=Jaisalmer-old-man-viral"><img src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif" alt="fsd"></a>
<a rel="nofollow" href="https://tinyurl.com/58snvazm?V=Jaisalmer-viral-video">🌐 CLICK HERE 🟢==►► WATCH NOW</a>
<a rel="nofollow" href="https://tinyurl.com/58snvazm?V=Jaisalmer-old-man-viral">🔴 CLICK HERE 🌐==►► Download Now)</a>
|
the-acorn-ai/Qwen3-4B-Leon-0521-sft-lora-merged | the-acorn-ai | 2025-05-21T22:48:04Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen3",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-21T22:45:22Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
mlfoundations-dev/openmathreasoning_300k | mlfoundations-dev | 2025-05-21T22:46:42Z | 55 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"qwen2",
"text-generation",
"llama-factory",
"full",
"generated_from_trainer",
"conversational",
"base_model:Qwen/Qwen2.5-7B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-7B-Instruct",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-04T16:27:51Z | ---
library_name: transformers
license: other
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: openmathreasoning_300k
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. -->
# openmathreasoning_300k
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/openmathreasoning_300k 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: 8e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- gradient_accumulation_steps: 32
- total_train_batch_size: 512
- total_eval_batch_size: 128
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
### Training results
### Framework versions
- Transformers 4.46.1
- Pytorch 2.5.0a0+b465a5843b.nv24.09
- Datasets 3.5.0
- Tokenizers 0.20.3
|
mradermacher/Jedi-3B-1080p-GGUF | mradermacher | 2025-05-21T22:46:22Z | 167 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:xlangai/Jedi-3B-1080p",
"base_model:quantized:xlangai/Jedi-3B-1080p",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-04-30T15:01:26Z | ---
base_model: xlangai/Jedi-3B-1080p
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/xlangai/Jedi-3B-1080p
<!-- 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/Jedi-3B-1080p-GGUF/resolve/main/Jedi-3B-1080p.Q2_K.gguf) | Q2_K | 1.4 | |
| [GGUF](https://huggingface.co/mradermacher/Jedi-3B-1080p-GGUF/resolve/main/Jedi-3B-1080p.mmproj-fp16.gguf) | mmproj-fp16 | 1.4 | vision supplement |
| [GGUF](https://huggingface.co/mradermacher/Jedi-3B-1080p-GGUF/resolve/main/Jedi-3B-1080p.Q3_K_S.gguf) | Q3_K_S | 1.6 | |
| [GGUF](https://huggingface.co/mradermacher/Jedi-3B-1080p-GGUF/resolve/main/Jedi-3B-1080p.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Jedi-3B-1080p-GGUF/resolve/main/Jedi-3B-1080p.Q3_K_L.gguf) | Q3_K_L | 1.8 | |
| [GGUF](https://huggingface.co/mradermacher/Jedi-3B-1080p-GGUF/resolve/main/Jedi-3B-1080p.IQ4_XS.gguf) | IQ4_XS | 1.9 | |
| [GGUF](https://huggingface.co/mradermacher/Jedi-3B-1080p-GGUF/resolve/main/Jedi-3B-1080p.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Jedi-3B-1080p-GGUF/resolve/main/Jedi-3B-1080p.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Jedi-3B-1080p-GGUF/resolve/main/Jedi-3B-1080p.Q5_K_S.gguf) | Q5_K_S | 2.3 | |
| [GGUF](https://huggingface.co/mradermacher/Jedi-3B-1080p-GGUF/resolve/main/Jedi-3B-1080p.Q5_K_M.gguf) | Q5_K_M | 2.3 | |
| [GGUF](https://huggingface.co/mradermacher/Jedi-3B-1080p-GGUF/resolve/main/Jedi-3B-1080p.Q6_K.gguf) | Q6_K | 2.6 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Jedi-3B-1080p-GGUF/resolve/main/Jedi-3B-1080p.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Jedi-3B-1080p-GGUF/resolve/main/Jedi-3B-1080p.f16.gguf) | f16 | 6.3 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
ngetichkevinhector/athens-ai-llama-3.1-8b-gguf | ngetichkevinhector | 2025-05-21T22:46:11Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama",
"text-generation-inference",
"unsloth",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-21T22:44:52Z | ---
base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- gguf
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** ngetichkevinhector
- **License:** apache-2.0
- **Finetuned from model :** unsloth/meta-llama-3.1-8b-instruct-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)
|
rosieyzh/uf-dpo-llama3_1_8b_instruct-checkpoint_2250-seed_42 | rosieyzh | 2025-05-21T22:45:22Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-21T22:39:11Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
MinaMila/llama_instbase_LoRa_GermanCredit_cfda_ep8_66 | MinaMila | 2025-05-21T22:44:57Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:44:53Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
kenonix/h1-merged-16-Q8_0-GGUF | kenonix | 2025-05-21T22:44:33Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"qwen3",
"trl",
"sft",
"grpo",
"llama-cpp",
"gguf-my-repo",
"en",
"base_model:kenonix/h1-merged-16",
"base_model:quantized:kenonix/h1-merged-16",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-21T22:44:14Z | ---
base_model: kenonix/h1-merged-16
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
- sft
- grpo
- llama-cpp
- gguf-my-repo
license: apache-2.0
language:
- en
---
# kenonix/h1-merged-16-Q8_0-GGUF
This model was converted to GGUF format from [`kenonix/h1-merged-16`](https://huggingface.co/kenonix/h1-merged-16) 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/kenonix/h1-merged-16) 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 kenonix/h1-merged-16-Q8_0-GGUF --hf-file h1-merged-16-q8_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo kenonix/h1-merged-16-Q8_0-GGUF --hf-file h1-merged-16-q8_0.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo kenonix/h1-merged-16-Q8_0-GGUF --hf-file h1-merged-16-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo kenonix/h1-merged-16-Q8_0-GGUF --hf-file h1-merged-16-q8_0.gguf -c 2048
```
|
MinaMila/llama_instbase_LoRa_GermanCredit_ep8_66 | MinaMila | 2025-05-21T22:43:11Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:43:03Z | ---
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] |
mlfoundations-dev/openthoughts2_math_300k | mlfoundations-dev | 2025-05-21T22:42:57Z | 19 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"qwen2",
"text-generation",
"llama-factory",
"full",
"generated_from_trainer",
"conversational",
"base_model:Qwen/Qwen2.5-7B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-7B-Instruct",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-12T02:02:47Z | ---
library_name: transformers
license: other
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: openthoughts2_math_300k
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. -->
# openthoughts2_math_300k
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/openthoughts2_math_300k 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: 8e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- gradient_accumulation_steps: 32
- total_train_batch_size: 512
- total_eval_batch_size: 128
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5.0
### Training results
### Framework versions
- Transformers 4.46.1
- Pytorch 2.5.0a0+b465a5843b.nv24.09
- Datasets 3.5.0
- Tokenizers 0.20.3
|
kenonix/h1-merged-16-Q4_K_M-GGUF | kenonix | 2025-05-21T22:42:48Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"qwen3",
"trl",
"sft",
"grpo",
"llama-cpp",
"gguf-my-repo",
"en",
"base_model:kenonix/h1-merged-16",
"base_model:quantized:kenonix/h1-merged-16",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-21T22:42:36Z | ---
base_model: kenonix/h1-merged-16
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
- sft
- grpo
- llama-cpp
- gguf-my-repo
license: apache-2.0
language:
- en
---
# kenonix/h1-merged-16-Q4_K_M-GGUF
This model was converted to GGUF format from [`kenonix/h1-merged-16`](https://huggingface.co/kenonix/h1-merged-16) 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/kenonix/h1-merged-16) 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 kenonix/h1-merged-16-Q4_K_M-GGUF --hf-file h1-merged-16-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo kenonix/h1-merged-16-Q4_K_M-GGUF --hf-file h1-merged-16-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 kenonix/h1-merged-16-Q4_K_M-GGUF --hf-file h1-merged-16-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo kenonix/h1-merged-16-Q4_K_M-GGUF --hf-file h1-merged-16-q4_k_m.gguf -c 2048
```
|
mlfoundations-dev/e1_science_longest_r1_0.3k | mlfoundations-dev | 2025-05-21T22:41:49Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"llama-factory",
"full",
"generated_from_trainer",
"conversational",
"base_model:Qwen/Qwen2.5-7B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-7B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-21T21:24:43Z | ---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: e1_science_longest_r1_0.3k
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. -->
# e1_science_longest_r1_0.3k
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/e1_science_longest_r1_0.3k 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
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- total_eval_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 13.0
### Training results
### Framework versions
- Transformers 4.46.1
- Pytorch 2.6.0+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3
|
silverside/PBCUP_BITE_v2 | silverside | 2025-05-21T22:41:06Z | 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 | 2025-05-21T21:05:44Z | ---
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: PBCUP_BITE
---
# Pbcup_Bite_V2
<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 `PBCUP_BITE` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "PBCUP_BITE",
"lora_weights": "https://huggingface.co/silverside/PBCUP_BITE_v2/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('silverside/PBCUP_BITE_v2', weight_name='lora.safetensors')
image = pipeline('PBCUP_BITE').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: 1200
- Learning rate: 0.0003
- LoRA rank: 32
## Contribute your own examples
You can use the [community tab](https://huggingface.co/silverside/PBCUP_BITE_v2/discussions) to add images that show off what you’ve made with this LoRA.
|
kureha295/ortho_model_pr | kureha295 | 2025-05-21T22:40:09Z | 3 | 0 | null | [
"safetensors",
"llama",
"license:mit",
"region:us"
] | null | 2025-05-15T16:22:01Z | ---
license: mit
---
This model has been created by taking the activations from the first 150 tokens in the prompt-cot combo. |
viral-video-one-girl-one-wolf/one.girl.one.wolf.leaked.video.original | viral-video-one-girl-one-wolf | 2025-05-21T22:38:49Z | 0 | 0 | null | [
"region:us"
] | null | 2025-05-21T22:38:12Z | <a rel="nofollow" href="https://tinyurl.com/58snvazm?V=katrina-lim-kiffy-viral-new-original-video"><img src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif" alt="fsd"></a>
<a rel="nofollow" href="https://tinyurl.com/58snvazm?V=one-girl-one-wolf">🌐 CLICK HERE 🟢==►► WATCH NOW</a>
<a rel="nofollow" href="https://tinyurl.com/58snvazm?V=one-girl-one-wolf">🔴 CLICK HERE 🌐==►► Download Now)</a> |
minaiosu/blacksnowskill | minaiosu | 2025-05-21T22:38:02Z | 0 | 0 | null | [
"region:us"
] | null | 2024-11-15T12:28:19Z | Please support https://boosty.to/blacksnowskill |
MinaMila/llama_instbase_LoRa_GermanCredit_ep7_66 | MinaMila | 2025-05-21T22:36:45Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:36:41Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Kudod/roberta-mlm-model-v2.4 | Kudod | 2025-05-21T22:35:35Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"roberta",
"fill-mask",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | 2025-05-21T03:31:40Z | ---
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: roberta-mlm-model-v2.4
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. -->
# roberta-mlm-model-v2.4
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: nan
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- 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: 1000
- num_epochs: 5
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:-----:|:---------------:|
| 9.3279 | 0.8315 | 10000 | 10.3457 |
| 8.983 | 1.6631 | 20000 | 9.0828 |
| 12.3327 | 2.4946 | 30000 | nan |
| 0.0 | 3.3261 | 40000 | nan |
| 0.0 | 4.1577 | 50000 | nan |
| 0.0 | 4.9892 | 60000 | nan |
### Framework versions
- Transformers 4.51.3
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1
|
mradermacher/pc-agent-72b-GGUF | mradermacher | 2025-05-21T22:35:15Z | 60 | 0 | transformers | [
"transformers",
"gguf",
"llama-factory",
"full",
"generated_from_trainer",
"en",
"dataset:henryhe0123/PC-Agent-E",
"base_model:henryhe0123/PC-Agent-E",
"base_model:quantized:henryhe0123/PC-Agent-E",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-05T22:51:42Z | ---
base_model: henryhe0123/PC-Agent-E
datasets:
- henryhe0123/PC-Agent-E
language:
- en
library_name: transformers
license: mit
quantized_by: mradermacher
tags:
- llama-factory
- full
- generated_from_trainer
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/henryhe0123/PC-Agent-E
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-GGUF/resolve/main/pc-agent-72b.Q2_K.gguf) | Q2_K | 29.9 | |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-GGUF/resolve/main/pc-agent-72b.Q3_K_S.gguf) | Q3_K_S | 34.6 | |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-GGUF/resolve/main/pc-agent-72b.Q3_K_M.gguf) | Q3_K_M | 37.8 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-GGUF/resolve/main/pc-agent-72b.Q3_K_L.gguf) | Q3_K_L | 39.6 | |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-GGUF/resolve/main/pc-agent-72b.IQ4_XS.gguf) | IQ4_XS | 40.3 | |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-GGUF/resolve/main/pc-agent-72b.Q4_K_S.gguf) | Q4_K_S | 44.0 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-GGUF/resolve/main/pc-agent-72b.Q4_K_M.gguf) | Q4_K_M | 47.5 | fast, recommended |
| [PART 1](https://huggingface.co/mradermacher/pc-agent-72b-GGUF/resolve/main/pc-agent-72b.Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/pc-agent-72b-GGUF/resolve/main/pc-agent-72b.Q5_K_S.gguf.part2of2) | Q5_K_S | 51.5 | |
| [PART 1](https://huggingface.co/mradermacher/pc-agent-72b-GGUF/resolve/main/pc-agent-72b.Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/pc-agent-72b-GGUF/resolve/main/pc-agent-72b.Q5_K_M.gguf.part2of2) | Q5_K_M | 54.5 | |
| [PART 1](https://huggingface.co/mradermacher/pc-agent-72b-GGUF/resolve/main/pc-agent-72b.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/pc-agent-72b-GGUF/resolve/main/pc-agent-72b.Q6_K.gguf.part2of2) | Q6_K | 64.4 | very good quality |
| [PART 1](https://huggingface.co/mradermacher/pc-agent-72b-GGUF/resolve/main/pc-agent-72b.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/pc-agent-72b-GGUF/resolve/main/pc-agent-72b.Q8_0.gguf.part2of2) | Q8_0 | 77.4 | fast, best quality |
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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
mradermacher/pc-agent-72b-i1-GGUF | mradermacher | 2025-05-21T22:34:26Z | 313 | 0 | transformers | [
"transformers",
"gguf",
"llama-factory",
"full",
"generated_from_trainer",
"en",
"dataset:henryhe0123/PC-Agent-E",
"base_model:henryhe0123/PC-Agent-E",
"base_model:quantized:henryhe0123/PC-Agent-E",
"license:mit",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2025-05-06T02:21:03Z | ---
base_model: henryhe0123/PC-Agent-E
datasets:
- henryhe0123/PC-Agent-E
language:
- en
library_name: transformers
license: mit
quantized_by: mradermacher
tags:
- llama-factory
- full
- generated_from_trainer
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: nicoboss -->
weighted/imatrix quants of https://huggingface.co/henryhe0123/PC-Agent-E
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/pc-agent-72b-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-IQ1_S.gguf) | i1-IQ1_S | 22.8 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-IQ1_M.gguf) | i1-IQ1_M | 23.8 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 25.6 | |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 27.2 | |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-IQ2_S.gguf) | i1-IQ2_S | 28.0 | |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-IQ2_M.gguf) | i1-IQ2_M | 29.4 | |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 29.7 | very low quality |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-Q2_K.gguf) | i1-Q2_K | 29.9 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 31.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 32.9 | |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-IQ3_S.gguf) | i1-IQ3_S | 34.6 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 34.6 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-IQ3_M.gguf) | i1-IQ3_M | 35.6 | |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 37.8 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 39.6 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 39.8 | |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-Q4_0.gguf) | i1-Q4_0 | 41.5 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 44.0 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-Q4_1.gguf) | i1-Q4_1 | 45.8 | |
| [GGUF](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 47.5 | fast, recommended |
| [PART 1](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-Q5_K_S.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-Q5_K_S.gguf.part2of2) | i1-Q5_K_S | 51.5 | |
| [PART 1](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-Q5_K_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-Q5_K_M.gguf.part2of2) | i1-Q5_K_M | 54.5 | |
| [PART 1](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/pc-agent-72b-i1-GGUF/resolve/main/pc-agent-72b.i1-Q6_K.gguf.part2of2) | i1-Q6_K | 64.4 | practically like static Q6_K |
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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
MinaMila/llama_instbase_LoRa_GermanCredit_cfda_ep6_66 | MinaMila | 2025-05-21T22:32:12Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:32:08Z | ---
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] |
rosieyzh/uf-dpo-llama3_1_8b_instruct-checkpoint_2000-seed_42 | rosieyzh | 2025-05-21T22:32:01Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-21T22:25:42Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
mradermacher/GLM-V5-Mag-GGUF | mradermacher | 2025-05-21T22:27:03Z | 524 | 1 | transformers | [
"transformers",
"gguf",
"roleplay",
"storywriting",
"axolotl",
"text-generation-inference",
"finetune",
"en",
"dataset:PocketDoc/Dans-Personamaxx-Logs",
"dataset:anthracite-org/kalo-opus-instruct-22k-no-refusal",
"dataset:lodrick-the-lafted/kalo-opus-instruct-3k-filtered",
"dataset:anthracite-org/nopm_claude_writing_fixed",
"dataset:anthracite-org/kalo_opus_misc_240827",
"dataset:anthracite-org/kalo_misc_part2",
"dataset:NewEden/Claude-Instruct-5K",
"dataset:NewEden/Claude-Instruct-2.7K",
"base_model:Delta-Vector/Rei-V1-32B-Base",
"base_model:quantized:Delta-Vector/Rei-V1-32B-Base",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-07T07:24:51Z | ---
base_model: Delta-Vector/Rei-V1-32B-Base
datasets:
- PocketDoc/Dans-Personamaxx-Logs
- anthracite-org/kalo-opus-instruct-22k-no-refusal
- lodrick-the-lafted/kalo-opus-instruct-3k-filtered
- anthracite-org/nopm_claude_writing_fixed
- anthracite-org/kalo_opus_misc_240827
- anthracite-org/kalo_misc_part2
- NewEden/Claude-Instruct-5K
- NewEden/Claude-Instruct-2.7K
language:
- en
library_name: transformers
quantized_by: mradermacher
tags:
- roleplay
- storywriting
- axolotl
- text-generation-inference
- finetune
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/Delta-Vector/Rei-V1-32B-Base
<!-- 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/GLM-V5-Mag-GGUF/resolve/main/GLM-V5-Mag.Q2_K.gguf) | Q2_K | 12.4 | |
| [GGUF](https://huggingface.co/mradermacher/GLM-V5-Mag-GGUF/resolve/main/GLM-V5-Mag.Q3_K_S.gguf) | Q3_K_S | 14.5 | |
| [GGUF](https://huggingface.co/mradermacher/GLM-V5-Mag-GGUF/resolve/main/GLM-V5-Mag.Q3_K_M.gguf) | Q3_K_M | 16.0 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/GLM-V5-Mag-GGUF/resolve/main/GLM-V5-Mag.Q3_K_L.gguf) | Q3_K_L | 17.3 | |
| [GGUF](https://huggingface.co/mradermacher/GLM-V5-Mag-GGUF/resolve/main/GLM-V5-Mag.IQ4_XS.gguf) | IQ4_XS | 17.9 | |
| [GGUF](https://huggingface.co/mradermacher/GLM-V5-Mag-GGUF/resolve/main/GLM-V5-Mag.Q4_K_S.gguf) | Q4_K_S | 18.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/GLM-V5-Mag-GGUF/resolve/main/GLM-V5-Mag.Q4_K_M.gguf) | Q4_K_M | 19.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/GLM-V5-Mag-GGUF/resolve/main/GLM-V5-Mag.Q5_K_S.gguf) | Q5_K_S | 22.6 | |
| [GGUF](https://huggingface.co/mradermacher/GLM-V5-Mag-GGUF/resolve/main/GLM-V5-Mag.Q5_K_M.gguf) | Q5_K_M | 23.2 | |
| [GGUF](https://huggingface.co/mradermacher/GLM-V5-Mag-GGUF/resolve/main/GLM-V5-Mag.Q6_K.gguf) | Q6_K | 26.8 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/GLM-V5-Mag-GGUF/resolve/main/GLM-V5-Mag.Q8_0.gguf) | Q8_0 | 34.7 | fast, best quality |
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 -->
|
rosieyzh/uf-dpo-llama3_1_8b_instruct-checkpoint_1875-seed_42 | rosieyzh | 2025-05-21T22:25:11Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-21T22:18:59Z | ---
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] |
ymroddi/gemma-3 | ymroddi | 2025-05-21T22:24:12Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"gemma3_text",
"trl",
"en",
"base_model:unsloth/gemma-3-1b-it-unsloth-bnb-4bit",
"base_model:finetune:unsloth/gemma-3-1b-it-unsloth-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:24:05Z | ---
base_model: unsloth/gemma-3-1b-it-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- gemma3_text
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** ymroddi
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gemma-3-1b-it-unsloth-bnb-4bit
This gemma3_text model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
MinaMila/llama_instbase_LoRa_GermanCredit_ep5_66 | MinaMila | 2025-05-21T22:24:00Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:23:56Z | ---
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] |
anonymousneurips008/CryoDRGN_model_weights | anonymousneurips008 | 2025-05-21T22:22:18Z | 0 | 0 | null | [
"license:mit",
"region:us"
] | null | 2025-05-21T20:53:52Z | ---
license: mit
---
Model weights of 3 CryoDRGN models trained on the validation dataset of EMPIAR-10076:
1. Using the original images
2. Using low-res images (16x downsampled)
3. Using CryoGEN reconstructed images (16x downsampled, sampling ratio 0.8) |
pictgencustomer/danceparade_107 | pictgencustomer | 2025-05-21T22:21:24Z | 0 | 0 | diffusers | [
"diffusers",
"flux",
"lora",
"replicate",
"text-to-image",
"en",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
] | text-to-image | 2025-05-21T22:21:13Z | ---
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: danceparade_5
---
# Danceparade_107
<Gallery />
Trained on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `danceparade_5` 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('pictgencustomer/danceparade_107', 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)
|
Viral-Video-18-katrina-lim-kiffy-katrinali/Video.18.katrina.lim.kiffy.katrinalim123.katrina.lim.tg.telegram | Viral-Video-18-katrina-lim-kiffy-katrinali | 2025-05-21T22:21:00Z | 0 | 0 | null | [
"region:us"
] | null | 2025-05-21T22:17:42Z | <a rel="nofollow" href="https://tinyurl.com/58snvazm?V=katrina-lim ">🌐 CLICK HERE 🟢==►► WATCH NOW</a>
<a rel="nofollow" href="https://tinyurl.com/58snvazm?V=katrina-lim">🔴 CLICK HERE 🌐==►► Download Now)</a>
<a rel="nofollow" href="https://tinyurl.com/58snvazm?V=katrina lim viral kiffy"><img src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif" alt="fsd"></a>
|
anonymousneurips008/empiar10076-ddpm-ema-cryoem-128x128 | anonymousneurips008 | 2025-05-21T22:20:15Z | 12 | 0 | diffusers | [
"diffusers",
"safetensors",
"license:mit",
"diffusers:DDPMPipeline",
"region:us"
] | null | 2025-05-20T19:30:28Z | ---
license: mit
library_name: diffusers
---
DDPM trained on EMPIAR10076 training dataset with 105,519 images of size 128x128 |
Gabriel2502/NIH1 | Gabriel2502 | 2025-05-21T22:20:15Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:20:12Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
MinaMila/llama_instbase_LoRa_GermanCredit_cfda_ep4_66 | MinaMila | 2025-05-21T22:19:19Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:19:15Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
rosieyzh/uf-dpo-llama3_1_8b_instruct-checkpoint_1750-seed_42 | rosieyzh | 2025-05-21T22:18:27Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-21T22:11:57Z | ---
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] |
ngetichkevinhector/athens-ai-llama-3.1-8b-LORA | ngetichkevinhector | 2025-05-21T22:17:50Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:17:45Z | ---
base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** ngetichkevinhector
- **License:** apache-2.0
- **Finetuned from model :** unsloth/meta-llama-3.1-8b-instruct-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)
|
MinaMila/llama_instbase_LoRa_GermanCredit_ep4_66 | MinaMila | 2025-05-21T22:17:38Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:17:33Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
cheetahbooked/ppo-Pyramids-Training | cheetahbooked | 2025-05-21T22:17:30Z | 0 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"Pyramids",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Pyramids",
"region:us"
] | reinforcement-learning | 2025-05-21T22:17:27Z | ---
library_name: ml-agents
tags:
- Pyramids
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Pyramids
---
# **ppo** Agent playing **Pyramids**
This is a trained model of a **ppo** agent playing **Pyramids**
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: cheetahbooked/ppo-Pyramids-Training
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
laion/Empathic-Insight-Voice-Small | laion | 2025-05-21T22:15:27Z | 0 | 0 | null | [
"license:cc-by-4.0",
"region:us"
] | null | 2025-05-18T20:06:13Z | ---
license: cc-by-4.0
---
# Empathic-Insight-Voice-Small
[](https://colab.research.google.com/drive/1WR-B6j--Y5RdhIyRGF_tJ3YdFF8BkUA2)
**Empathic-Insight-Voice-Small** is a suite of 40+ emotion and attribute regression models trained on the large-scale, multilingual synthetic voice-acting dataset LAION'S GOT TALENT (~ 5.000 hours) & an "in the wild" dataset of voice snippets (also ~ 5.000 hours). Each model is designed to predict the intensity of a specific fine-grained emotion or attribute from speech audio. These models leverage embeddings from a fine-tuned Whisper model (laion/BUD-E-Whisper) followed by dedicated MLP regression heads for each dimension.
This work is based on the research paper:
**"EMONET-VOICE: A Fine-Grained, Expert-Verified Benchmark for Speech Emotion Detection"**
## Example Video Analyses (Top 3 Emotions)
<!-- This section will be populated by the HTML from Cell 0 -->
<div style='display: flex; flex-wrap: wrap; justify-content: flex-start; gap: 15px;'>
<div style='flex: 0 1 auto; margin-bottom: 15px; text-align: center; width: 480px; max-width: 480px;'>
<a href='https://www.youtube.com/watch?v=TsTVKCmqHhk' target='_blank' title='Watch video TsTVKCmqHhk'>
<img src='https://img.youtube.com/vi/TsTVKCmqHhk/hqdefault.jpg' alt='YouTube Thumbnail for TsTVKCmqHhk' style='width: 100%; height: auto; border: 1px solid #ccc; border-radius: 4px; display: block;'>
</a>
<p style='font-size: 0.8em; margin-top: 5px; word-break: break-all;'>ID: TsTVKCmqHhk</p>
</div>
<div style='flex: 0 1 auto; margin-bottom: 15px; text-align: center; width: 480px; max-width: 480px;'>
<a href='https://www.youtube.com/watch?v=sErqFgL4vA8' target='_blank' title='Watch video sErqFgL4vA8'>
<img src='https://img.youtube.com/vi/sErqFgL4vA8/hqdefault.jpg' alt='YouTube Thumbnail for sErqFgL4vA8' style='width: 100%; height: auto; border: 1px solid #ccc; border-radius: 4px; display: block;'>
</a>
<p style='font-size: 0.8em; margin-top: 5px; word-break: break-all;'>ID: sErqFgL4vA8</p>
</div>
<div style='flex: 0 1 auto; margin-bottom: 15px; text-align: center; width: 480px; max-width: 480px;'>
<a href='https://www.youtube.com/watch?v=BUnfuiwE_IM' target='_blank' title='Watch video BUnfuiwE_IM'>
<img src='https://img.youtube.com/vi/BUnfuiwE_IM/hqdefault.jpg' alt='YouTube Thumbnail for BUnfuiwE_IM' style='width: 100%; height: auto; border: 1px solid #ccc; border-radius: 4px; display: block;'>
</a>
<p style='font-size: 0.8em; margin-top: 5px; word-break: break-all;'>ID: BUnfuiwE_IM</p>
</div>
<div style='flex: 0 1 auto; margin-bottom: 15px; text-align: center; width: 480px; max-width: 480px;'>
<a href='https://www.youtube.com/watch?v=dDrmjcUq8W4' target='_blank' title='Watch video dDrmjcUq8W4'>
<img src='https://img.youtube.com/vi/dDrmjcUq8W4/hqdefault.jpg' alt='YouTube Thumbnail for dDrmjcUq8W4' style='width: 100%; height: auto; border: 1px solid #ccc; border-radius: 4px; display: block;'>
</a>
<p style='font-size: 0.8em; margin-top: 5px; word-break: break-all;'>ID: dDrmjcUq8W4</p>
</div>
</div>
## Model Description
The Empathic-Insight-Voice-Small suite consists of over 54 individual MLP models (40 for primary emotions, plus others for attributes like valence, arousal, gender, etc.). Each model takes a Whisper audio embedding as input and outputs a continuous score for one of the emotion/attribute categories defined in the EMONET-VOICE taxonomy and extended attribute set.
The models were trained on a large dataset of synthetic & "in the wild" speech (both each ~ 5.000 hours).
## Intended Use
These models are intended for research purposes in affective computing, speech emotion recognition (SER), human-AI interaction, and voice AI development. They can be used to:
* Analyze and predict fine-grained emotional states and vocal attributes from speech.
* Serve as a baseline for developing more advanced SER systems.
* Facilitate research into nuanced emotional understanding in voice AI.
* Explore multilingual and cross-cultural aspects of speech emotion (given the foundation dataset).
**Out-of-Scope Use:**
These models are trained on synthetic speech and their generalization to spontaneous real-world speech needs further evaluation. They should not be used for making critical decisions about individuals, for surveillance, or in any manner that could lead to discriminatory outcomes or infringe on privacy without due diligence and ethical review.
## How to Use
The primary way to use these models is through the provided [Google Colab Notebook](https://colab.research.google.com/drive/1WR-B6j--Y5RdhIyRGF_tJ3YdFF8BkUA2). The notebook handles dependencies, model loading, audio processing, and provides examples for:
* Batch processing a folder of audio files.
* Generating a comprehensive HTML report with per-file emotion scores, waveforms, and audio players.
* Generating individual JSON files with all predicted scores for each audio file.
Below is a conceptual example of how to perform inference for a single audio file, extracting all emotion and attribute scores. For the full, runnable version, please refer to the Colab notebook.
**Conceptual Python Example for Single Audio File Inference:**
```python
import torch
import torch.nn as nn
import librosa
import numpy as np
from pathlib import Path
from transformers import WhisperProcessor, WhisperForConditionalGeneration
from huggingface_hub import snapshot_download # For downloading MLP models
import gc # For memory management
# --- Configuration (should match Cell 2 of the Colab) ---
SAMPLING_RATE = 16000
MAX_AUDIO_SECONDS = 30.0
WHISPER_MODEL_ID = "mkrausio/EmoWhisper-AnS-Small-v0.1"
HF_MLP_REPO_ID = "laion/Empathic-Insight-Voice-Small" # Or -Large if using those
LOCAL_MLP_MODELS_DOWNLOAD_DIR = Path("./empathic_insight_voice_small_models_downloaded")
WHISPER_SEQ_LEN = 1500
WHISPER_EMBED_DIM = 768
PROJECTION_DIM_FOR_FULL_EMBED = 64 # For 'Small' models
MLP_HIDDEN_DIMS = [64, 32, 16] # For 'Small' models
MLP_DROPOUTS = [0.0, 0.1, 0.1, 0.1] # For 'Small' models
# Mapping from .pth file name parts to human-readable dimension keys
# (Abridged, full map in Colab Cell 2)
FILENAME_PART_TO_TARGET_KEY_MAP: Dict[str, str] = {
"Affection": "Affection", "Age": "Age", "Amusement": "Amusement", "Anger": "Anger",
"Arousal": "Arousal", "Astonishment_Surprise": "Astonishment/Surprise",
"Authenticity": "Authenticity", "Awe": "Awe", "Background_Noise": "Background_Noise",
"Bitterness": "Bitterness", "Concentration": "Concentration",
"Confident_vs._Hesitant": "Confident_vs._Hesitant", "Confusion": "Confusion",
"Contemplation": "Contemplation", "Contempt": "Contempt", "Contentment": "Contentment",
"Disappointment": "Disappointment", "Disgust": "Disgust", "Distress": "Distress",
"Doubt": "Doubt", "Elation": "Elation", "Embarrassment": "Embarrassment",
"Emotional_Numbness": "Emotional Numbness", "Fatigue_Exhaustion": "Fatigue/Exhaustion",
"Fear": "Fear", "Gender": "Gender", "Helplessness": "Helplessness",
"High-Pitched_vs._Low-Pitched": "High-Pitched_vs._Low-Pitched",
"Hope_Enthusiasm_Optimism": "Hope/Enthusiasm/Optimism",
"Impatience_and_Irritability": "Impatience and Irritability",
"Infatuation": "Infatuation", "Interest": "Interest",
"Intoxication_Altered_States_of_Consciousness": "Intoxication/Altered States of Consciousness",
"Jealousy_&_Envy": "Jealousy / Envy", "Longing": "Longing",
"Malevolence_Malice": "Malevolence/Malice",
"Monotone_vs._Expressive": "Monotone_vs._Expressive", "Pain": "Pain",
"Pleasure_Ecstasy": "Pleasure/Ecstasy", "Pride": "Pride",
"Recording_Quality": "Recording_Quality", "Relief": "Relief", "Sadness": "Sadness",
"Serious_vs._Humorous": "Serious_vs._Humorous", "Sexual_Lust": "Sexual Lust",
"Shame": "Shame", "Soft_vs._Harsh": "Soft_vs._Harsh", "Sourness": "Sourness",
"Submissive_vs._Dominant": "Submissive_vs._Dominant", "Teasing": "Teasing",
"Thankfulness_Gratitude": "Thankfulness/Gratitude", "Triumph": "Triumph",
"Valence": "Valence",
"Vulnerable_vs._Emotionally_Detached": "Vulnerable_vs._Emotionally_Detached",
"Warm_vs._Cold": "Warm_vs._Cold"
}
TARGET_EMOTION_KEYS_FOR_REPORT: List[str] = [
"Amusement", "Elation", "Pleasure/Ecstasy", "Contentment", "Thankfulness/Gratitude",
"Affection", "Infatuation", "Hope/Enthusiasm/Optimism", "Triumph", "Pride",
"Interest", "Awe", "Astonishment/Surprise", "Concentration", "Contemplation",
"Relief", "Longing", "Teasing", "Impatience and Irritability",
"Sexual Lust", "Doubt", "Fear", "Distress", "Confusion", "Embarrassment", "Shame",
"Disappointment", "Sadness", "Bitterness", "Contempt", "Disgust", "Anger",
"Malevolence/Malice", "Sourness", "Pain", "Helplessness", "Fatigue/Exhaustion",
"Emotional Numbness", "Intoxication/Altered States of Consciousness", "Jealousy / Envy"
]
# --- MLP Model Definition (from Colab Cell 2) ---
class FullEmbeddingMLP(nn.Module):
def __init__(self, seq_len, embed_dim, projection_dim, mlp_hidden_dims, mlp_dropout_rates):
super().__init__()
if len(mlp_dropout_rates) != len(mlp_hidden_dims) + 1:
raise ValueError("Dropout rates length error.")
self.flatten = nn.Flatten()
self.proj = nn.Linear(seq_len * embed_dim, projection_dim)
layers = [nn.ReLU(), nn.Dropout(mlp_dropout_rates[0])]
current_dim = projection_dim
for i, h_dim in enumerate(mlp_hidden_dims):
layers.extend([nn.Linear(current_dim, h_dim), nn.ReLU(), nn.Dropout(mlp_dropout_rates[i+1])])
current_dim = h_dim
layers.append(nn.Linear(current_dim, 1))
self.mlp = nn.Sequential(*layers)
def forward(self, x):
if x.ndim == 4 and x.shape[1] == 1: x = x.squeeze(1)
return self.mlp(self.proj(self.flatten(x)))
# --- Global Model Placeholders ---
whisper_model_global = None
whisper_processor_global = None
all_mlp_model_paths_dict = {} # To be populated
WHISPER_DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
MLP_DEVICE = torch.device("cpu") # As per USE_CPU_OFFLOADING_FOR_MLPS in Colab
def initialize_models():
global whisper_model_global, whisper_processor_global, all_mlp_model_paths_dict
print(f"Whisper will run on: {WHISPER_DEVICE}")
print(f"MLPs will run on: {MLP_DEVICE}")
# Load Whisper
if whisper_model_global is None:
print(f"Loading Whisper model '{WHISPER_MODEL_ID}'...")
whisper_processor_global = WhisperProcessor.from_pretrained(WHISPER_MODEL_ID)
whisper_model_global = WhisperForConditionalGeneration.from_pretrained(WHISPER_MODEL_ID).to(WHISPER_DEVICE).eval()
print("Whisper model loaded.")
# Download and map MLPs (paths only, models loaded on-demand)
if not all_mlp_model_paths_dict:
print(f"Downloading MLP checkpoints from {HF_MLP_REPO_ID} to {LOCAL_MLP_MODELS_DOWNLOAD_DIR}...")
LOCAL_MLP_MODELS_DOWNLOAD_DIR.mkdir(parents=True, exist_ok=True)
snapshot_download(
repo_id=HF_MLP_REPO_ID,
local_dir=LOCAL_MLP_MODELS_DOWNLOAD_DIR,
local_dir_use_symlinks=False,
allow_patterns=["*.pth"],
repo_type="model"
)
print("MLP checkpoints downloaded.")
# Map .pth files to target keys (simplified from Colab Cell 2)
for pth_file in LOCAL_MLP_MODELS_DOWNLOAD_DIR.glob("model_*_best.pth"):
try:
filename_part = pth_file.name.split("model_")[1].split("_best.pth")[0]
if filename_part in FILENAME_PART_TO_TARGET_KEY_MAP:
target_key = FILENAME_PART_TO_TARGET_KEY_MAP[filename_part]
all_mlp_model_paths_dict[target_key] = pth_file
except IndexError:
print(f"Warning: Could not parse filename part from {pth_file.name}")
print(f"Mapped {len(all_mlp_model_paths_dict)} MLP model paths.")
if not all_mlp_model_paths_dict:
raise RuntimeError("No MLP model paths could be mapped. Check FILENAME_PART_TO_TARGET_KEY_MAP and downloaded files.")
@torch.no_grad()
def get_whisper_embedding(audio_waveform_np):
if whisper_model_global is None or whisper_processor_global is None:
raise RuntimeError("Whisper model not initialized. Call initialize_models() first.")
input_features = whisper_processor_global(
audio_waveform_np, sampling_rate=SAMPLING_RATE, return_tensors="pt"
).input_features.to(WHISPER_DEVICE).to(whisper_model_global.dtype)
encoder_outputs = whisper_model_global.get_encoder()(input_features=input_features)
embedding = encoder_outputs.last_hidden_state
current_seq_len = embedding.shape[1]
if current_seq_len < WHISPER_SEQ_LEN:
padding = torch.zeros((1, WHISPER_SEQ_LEN - current_seq_len, WHISPER_EMBED_DIM),
device=WHISPER_DEVICE, dtype=embedding.dtype)
embedding = torch.cat((embedding, padding), dim=1)
elif current_seq_len > WHISPER_SEQ_LEN:
embedding = embedding[:, :WHISPER_SEQ_LEN, :]
return embedding
def load_single_mlp(model_path, target_key):
# Simplified loading for example (Colab Cell 2 has more robust loading)
# For this example, assumes USE_HALF_PRECISION_FOR_MLPS=False, USE_TORCH_COMPILE_FOR_MLPS=False
print(f" Loading MLP for '{target_key}'...")
model_instance = FullEmbeddingMLP(
WHISPER_SEQ_LEN, WHISPER_EMBED_DIM, PROJECTION_DIM_FOR_FULL_EMBED,
MLP_HIDDEN_DIMS, MLP_DROPOUTS
)
state_dict = torch.load(model_path, map_location='cpu')
# Handle potential '_orig_mod.' prefix if model was torch.compile'd during training
if any(k.startswith("_orig_mod.") for k in state_dict.keys()):
state_dict = {k.replace("_orig_mod.", ""): v for k, v in state_dict.items()}
model_instance.load_state_dict(state_dict)
model_instance = model_instance.to(MLP_DEVICE).eval()
return model_instance
@torch.no_grad()
def predict_with_mlp(embedding, mlp_model):
embedding_for_mlp = embedding.to(MLP_DEVICE)
# Ensure dtype matches (simplified)
mlp_dtype = next(mlp_model.parameters()).dtype
prediction = mlp_model(embedding_for_mlp.to(mlp_dtype))
return prediction.item()
def process_audio_file(audio_file_path_str: str) -> Dict[str, float]:
if not all_mlp_model_paths_dict:
initialize_models() # Ensure models are ready
print(f"Processing audio file: {audio_file_path_str}")
try:
waveform, sr = librosa.load(audio_file_path_str, sr=SAMPLING_RATE, mono=True)
max_samples = int(MAX_AUDIO_SECONDS * SAMPLING_RATE)
if len(waveform) > max_samples:
waveform = waveform[:max_samples]
print(f"Audio loaded. Duration: {len(waveform)/SAMPLING_RATE:.2f}s")
except Exception as e:
print(f"Error loading audio {audio_file_path_str}: {e}")
return {}
embedding = get_whisper_embedding(waveform)
del waveform; gc.collect();
if WHISPER_DEVICE.type == 'cuda': torch.cuda.empty_cache()
all_scores: Dict[str, float] = {}
for target_key, mlp_model_path in all_mlp_model_paths_dict.items():
if target_key not in FILENAME_PART_TO_TARGET_KEY_MAP.values(): # Only process mapped keys
continue
current_mlp_model = load_single_mlp(mlp_model_path, target_key)
if current_mlp_model:
score = predict_with_mlp(embedding, current_mlp_model)
all_scores[target_key] = score
print(f" {target_key}: {score:.4f}")
del current_mlp_model # Unload after use
gc.collect()
if MLP_DEVICE.type == 'cuda': torch.cuda.empty_cache()
else:
all_scores[target_key] = float('nan')
del embedding; gc.collect();
if WHISPER_DEVICE.type == 'cuda': torch.cuda.empty_cache()
# Optional: Calculate Softmax for the 40 primary emotions
emotion_raw_scores = [all_scores.get(k, -float('inf')) for k in TARGET_EMOTION_KEYS_FOR_REPORT if k in all_scores]
if emotion_raw_scores:
softmax_probs = torch.softmax(torch.tensor(emotion_raw_scores, dtype=torch.float32), dim=0)
print("\nTop 3 Emotions (Softmax Probabilities):")
# Create a dictionary of {emotion_key: softmax_prob}
emotion_softmax_dict = {
key: prob.item()
for key, prob in zip(
[k for k in TARGET_EMOTION_KEYS_FOR_REPORT if k in all_scores], # only keys that had scores
softmax_probs
)
}
sorted_emotions = sorted(emotion_softmax_dict.items(), key=lambda item: item[1], reverse=True)
for i, (emotion, prob) in enumerate(sorted_emotions[:3]):
print(f" {i+1}. {emotion}: {prob:.4f} (Raw: {all_scores.get(emotion, float('nan')):.4f})")
return all_scores
# --- Example Usage (Run this after defining functions and initializing models) ---
# Make sure to have an audio file (e.g., "sample.mp3") in your current directory or provide a full path.
# And ensure FILENAME_PART_TO_TARGET_KEY_MAP and TARGET_EMOTION_KEYS_FOR_REPORT are fully populated.
#
# initialize_models() # Call this once
#
# # Create a dummy sample.mp3 for testing if it doesn't exist
# if not Path("sample.mp3").exists():
# print("Creating dummy sample.mp3 for testing...")
# dummy_sr = 16000
# dummy_duration = 5 # seconds
# dummy_tone_freq = 440 # A4 note
# t = np.linspace(0, dummy_duration, int(dummy_sr * dummy_duration), endpoint=False)
# dummy_waveform = 0.5 * np.sin(2 * np.pi * dummy_tone_freq * t)
# import soundfile as sf
# sf.write("sample.mp3", dummy_waveform, dummy_sr)
# print("Dummy sample.mp3 created.")
#
# if Path("sample.mp3").exists() and FILENAME_PART_TO_TARGET_KEY_MAP and TARGET_EMOTION_KEYS_FOR_REPORT:
# results = process_audio_file("sample.mp3")
# # print("\nFull Scores Dictionary:", results)
# else:
# print("Skipping example usage: 'sample.mp3' not found or maps are not fully populated.")
```
## Taxonomy
The core 40 emotion categories are (from EMONET-VOICE, Appendix A.1):
Affection, Amusement, Anger, Astonishment/Surprise, Awe, Bitterness, Concentration, Confusion, Contemplation, Contempt, Contentment, Disappointment, Disgust, Distress, Doubt, Elation, Embarrassment, Emotional Numbness, Fatigue/Exhaustion, Fear, Helplessness, Hope/Enthusiasm/Optimism, Impatience and Irritability, Infatuation, Interest, Intoxication/Altered States of Consciousness, Jealousy & Envy, Longing, Malevolence/Malice, Pain, Pleasure/Ecstasy, Pride, Relief, Sadness, Sexual Lust, Shame, Sourness, Teasing, Thankfulness/Gratitude, Triumph.
Additional vocal attributes (e.g., Valence, Arousal, Gender, Age, Pitch characteristics) are also predicted by corresponding MLP models in the suite. The full list of predictable dimensions can be inferred from the FILENAME_PART_TO_TARGET_KEY_MAP in the Colab notebook (Cell 2).
## Ethical Considerations
The EMONET-VOICE suite was developed with ethical considerations as a priority:
Privacy Preservation: The use of synthetic voice generation fundamentally circumvents privacy concerns associated with collecting real human emotional expressions, especially for sensitive states.
Responsible Use: These models are released for research. Users are urged to consider the ethical implications of their applications and avoid misuse, such as for emotional manipulation, surveillance, or in ways that could lead to unfair, biased, or harmful outcomes. The broader societal implications and mitigation of potential misuse of SER technology remain important ongoing considerations.
|
ToastyPigeon/gemma-3-starshine-merge-A | ToastyPigeon | 2025-05-21T22:14:23Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gemma3",
"image-text-to-text",
"mergekit",
"merge",
"conversational",
"arxiv:2203.05482",
"base_model:ToastyPigeon/Gemma-3-Starshine-12B",
"base_model:merge:ToastyPigeon/Gemma-3-Starshine-12B",
"base_model:ToastyPigeon/gemma-3-starshine-12b-continued",
"base_model:merge:ToastyPigeon/gemma-3-starshine-12b-continued",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | image-text-to-text | 2025-05-21T22:11:28Z | ---
base_model:
- ToastyPigeon/gemma-3-starshine-12b-continued
- ToastyPigeon/Gemma-3-Starshine-12B
library_name: transformers
tags:
- mergekit
- merge
---
# mergeA
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 [Linear](https://arxiv.org/abs/2203.05482) merge method.
### Models Merged
The following models were included in the merge:
* [ToastyPigeon/gemma-3-starshine-12b-continued](https://huggingface.co/ToastyPigeon/gemma-3-starshine-12b-continued)
* [ToastyPigeon/Gemma-3-Starshine-12B](https://huggingface.co/ToastyPigeon/Gemma-3-Starshine-12B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: ToastyPigeon/gemma-3-starshine-12b-continued
parameters:
weight: 0.5
- model: ToastyPigeon/Gemma-3-Starshine-12B
parameters:
weight: 0.5
merge_method: linear
dtype: bfloat16
```
|
RafaelTerra/a_photo_of_james | RafaelTerra | 2025-05-21T22:14:21Z | 0 | 0 | null | [
"license:other",
"region:us"
] | null | 2025-05-21T20:57:20Z | ---
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
--- |
z1c2/test111 | z1c2 | 2025-05-21T22:13:47Z | 0 | 0 | null | [
"license:other",
"region:us"
] | null | 2025-04-09T10:54:11Z | ---
license: other
license_name: fff
license_link: LICENSE
---
|
debbieliang/llama-dpo-default_20250521_1 | debbieliang | 2025-05-21T22:12:32Z | 0 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"generated_from_trainer",
"trl",
"dpo",
"arxiv:2305.18290",
"base_model:unsloth/Llama-3.2-11B-Vision-Instruct",
"base_model:finetune:unsloth/Llama-3.2-11B-Vision-Instruct",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:12:02Z | ---
base_model: unsloth/Llama-3.2-11B-Vision-Instruct
library_name: transformers
model_name: llama-dpo-default_20250521_1
tags:
- generated_from_trainer
- trl
- dpo
licence: license
---
# Model Card for llama-dpo-default_20250521_1
This model is a fine-tuned version of [unsloth/Llama-3.2-11B-Vision-Instruct](https://huggingface.co/unsloth/Llama-3.2-11B-Vision-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="debbieliang/llama-dpo-default_20250521_1", 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/debbieliang/huggingface/runs/g6yu6fw8)
This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
### Framework versions
- TRL: 0.15.2
- Transformers: 4.51.3
- Pytorch: 2.7.0
- Datasets: 3.6.0
- Tokenizers: 0.21.1
## Citations
Cite DPO as:
```bibtex
@inproceedings{rafailov2023direct,
title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
year = 2023,
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
MikeSu2025/bittol | MikeSu2025 | 2025-05-21T22:11:38Z | 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 | 2025-05-21T21:21:59Z | ---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: "black-forest-labs/FLUX.1-dev"
pipeline_tag: text-to-image
# widget:
# - text: >-
# prompt
# output:
# url: https://...
instance_prompt: TINTINBAK
---
# Bittol
<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 `TINTINBAK` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "TINTINBAK",
"lora_weights": "https://huggingface.co/MikeSu2025/bittol/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('MikeSu2025/bittol', weight_name='lora.safetensors')
image = pipeline('TINTINBAK').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/MikeSu2025/bittol/discussions) to add images that show off what you’ve made with this LoRA.
|
rosieyzh/uf-dpo-llama3_1_8b_instruct-checkpoint_1625-seed_42 | rosieyzh | 2025-05-21T22:11:25Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-21T22:05:12Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
MinaMila/llama_instbase_LoRa_GermanCredit_ep3_66 | MinaMila | 2025-05-21T22:11:15Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:11:11Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
johngreendr1/27e9f9cd-ec99-4149-9d17-1a561e1782d3 | johngreendr1 | 2025-05-21T22:10:43Z | 0 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:microsoft/Phi-3-mini-4k-instruct",
"base_model:adapter:microsoft/Phi-3-mini-4k-instruct",
"region:us"
] | null | 2025-05-21T19:44:50Z | ---
base_model: microsoft/Phi-3-mini-4k-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 |
hubble658/obss-qwen-7b-1.5ep | hubble658 | 2025-05-21T22:10:23Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen2_5_vl",
"trl",
"en",
"base_model:hubble658/obss-merged-qwen-new",
"base_model:finetune:hubble658/obss-merged-qwen-new",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:10:11Z | ---
base_model: hubble658/obss-merged-qwen-new
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2_5_vl
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** hubble658
- **License:** apache-2.0
- **Finetuned from model :** hubble658/obss-merged-qwen-new
This qwen2_5_vl 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/R3-Qwen3-8B-LoRA-4k-GGUF | mradermacher | 2025-05-21T22:07:05Z | 77 | 0 | transformers | [
"transformers",
"gguf",
"lora",
"en",
"dataset:rubricreward/R3-Dataset-4K",
"base_model:rubricreward/R3-Qwen3-8B-LoRA-4k",
"base_model:adapter:rubricreward/R3-Qwen3-8B-LoRA-4k",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-20T07:48:03Z | ---
base_model: rubricreward/R3-Qwen3-8B-LoRA-4k
datasets:
- rubricreward/R3-Dataset-4K
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- lora
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/rubricreward/R3-Qwen3-8B-LoRA-4k
<!-- 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/R3-Qwen3-8B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-8B-LoRA-4k.Q2_K.gguf) | Q2_K | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-8B-LoRA-4k.Q3_K_S.gguf) | Q3_K_S | 3.9 | |
| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-8B-LoRA-4k.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-8B-LoRA-4k.Q3_K_L.gguf) | Q3_K_L | 4.5 | |
| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-8B-LoRA-4k.IQ4_XS.gguf) | IQ4_XS | 4.7 | |
| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-8B-LoRA-4k.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-8B-LoRA-4k.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-8B-LoRA-4k.Q5_K_S.gguf) | Q5_K_S | 5.8 | |
| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-8B-LoRA-4k.Q5_K_M.gguf) | Q5_K_M | 6.0 | |
| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-8B-LoRA-4k.Q6_K.gguf) | Q6_K | 6.8 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-8B-LoRA-4k.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/R3-Qwen3-8B-LoRA-4k-GGUF/resolve/main/R3-Qwen3-8B-LoRA-4k.f16.gguf) | f16 | 16.5 | 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_LoRa_GermanCredit_cfda_ep2_66 | MinaMila | 2025-05-21T22:06:15Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:06:11Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
mradermacher/E1-Code-14B-GGUF | mradermacher | 2025-05-21T22:05:57Z | 28 | 0 | transformers | [
"transformers",
"gguf",
"en",
"dataset:agentica-org/DeepCoder-Preview-Dataset",
"base_model:Salesforce/E1-Code-14B",
"base_model:quantized:Salesforce/E1-Code-14B",
"license:cc-by-nc-4.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-21T08:12:14Z | ---
base_model: Salesforce/E1-Code-14B
datasets:
- agentica-org/DeepCoder-Preview-Dataset
language:
- en
library_name: transformers
license: cc-by-nc-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/Salesforce/E1-Code-14B
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/E1-Code-14B-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/E1-Code-14B-GGUF/resolve/main/E1-Code-14B.Q2_K.gguf) | Q2_K | 5.9 | |
| [GGUF](https://huggingface.co/mradermacher/E1-Code-14B-GGUF/resolve/main/E1-Code-14B.Q3_K_S.gguf) | Q3_K_S | 6.8 | |
| [GGUF](https://huggingface.co/mradermacher/E1-Code-14B-GGUF/resolve/main/E1-Code-14B.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/E1-Code-14B-GGUF/resolve/main/E1-Code-14B.Q3_K_L.gguf) | Q3_K_L | 8.0 | |
| [GGUF](https://huggingface.co/mradermacher/E1-Code-14B-GGUF/resolve/main/E1-Code-14B.IQ4_XS.gguf) | IQ4_XS | 8.3 | |
| [GGUF](https://huggingface.co/mradermacher/E1-Code-14B-GGUF/resolve/main/E1-Code-14B.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/E1-Code-14B-GGUF/resolve/main/E1-Code-14B.Q4_K_M.gguf) | Q4_K_M | 9.1 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/E1-Code-14B-GGUF/resolve/main/E1-Code-14B.Q5_K_S.gguf) | Q5_K_S | 10.4 | |
| [GGUF](https://huggingface.co/mradermacher/E1-Code-14B-GGUF/resolve/main/E1-Code-14B.Q5_K_M.gguf) | Q5_K_M | 10.6 | |
| [GGUF](https://huggingface.co/mradermacher/E1-Code-14B-GGUF/resolve/main/E1-Code-14B.Q6_K.gguf) | Q6_K | 12.2 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/E1-Code-14B-GGUF/resolve/main/E1-Code-14B.Q8_0.gguf) | Q8_0 | 15.8 | fast, best quality |
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_LoRa_GermanCredit_ep2_66 | MinaMila | 2025-05-21T22:04:52Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:04:48Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
rosieyzh/uf-dpo-llama3_1_8b_instruct-checkpoint_1500-seed_42 | rosieyzh | 2025-05-21T22:04:40Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-21T21:58:23Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF | mradermacher | 2025-05-21T22:04:29Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"en",
"dataset:TIGER-Lab/VisualWebInstruct-Verified",
"base_model:TIGER-Lab/General-Reasoner-Qwen2.5-14B",
"base_model:quantized:TIGER-Lab/General-Reasoner-Qwen2.5-14B",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2025-05-21T20:36:16Z | ---
base_model: TIGER-Lab/General-Reasoner-Qwen2.5-14B
datasets:
- TIGER-Lab/VisualWebInstruct-Verified
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: nicoboss -->
weighted/imatrix quants of https://huggingface.co/TIGER-Lab/General-Reasoner-Qwen2.5-14B
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-14B-i1-GGUF/resolve/main/General-Reasoner-Qwen2.5-14B.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | practically like static Q6_K |
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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
<!-- end -->
|
likhonsheikhdev/mujib71 | likhonsheikhdev | 2025-05-21T22:02:48Z | 0 | 1 | null | [
"region:us"
] | null | 2025-05-21T22:02:22Z | # Bengali-Code LLM Training Pipeline
A comprehensive pipeline for training a Bengali language model specialized in code understanding and generation. The model is fine-tuned on Bengali programming tutorials, documentation, and code examples.
## 🌟 Features
- Automated data collection from Bengali Wikipedia and Prothom Alo
- Custom tokenizer training with SentencePiece for Bengali text and code
- Model fine-tuning using TinyLlama base model
- Comprehensive evaluation suite for Bengali code generation
- GitHub Actions workflow for automated training
- Weights & Biases integration for experiment tracking
## 📋 Requirements
- Python 3.10 or higher
- CUDA-capable GPU (recommended)
- 16GB+ RAM
- Internet connection for data collection
## 🚀 Quick Start
1. Clone the repository:
```bash
git clone https://github.com/yourusername/bengali-code-llm.git
cd bengali-code-llm
```
2. Install dependencies:
```bash
pip install -r requirements.txt
```
3. Set up environment variables:
```bash
export HUGGINGFACE_TOKEN="your_token_here"
export WANDB_API_KEY="your_wandb_key_here"
```
4. Run the complete pipeline:
```bash
# Collect data
python scripts/data_collector.py
# Train tokenizer
python scripts/tokenizer_trainer.py
# Train model
python scripts/model_trainer.py
# Evaluate model
python scripts/model_evaluator.py
```
## 🏗️ Pipeline Components
### Data Collection (`scripts/data_collector.py`)
- Scrapes Bengali text from Wikipedia and Prothom Alo
- Implements rate limiting and error handling
- Outputs processed data in JSON format
### Tokenizer Training (`scripts/tokenizer_trainer.py`)
- Uses SentencePiece for tokenizer training
- Custom vocabulary with Bengali and code tokens
- Generates HuggingFace-compatible tokenizer files
### Model Training (`scripts/model_trainer.py`)
- Fine-tunes TinyLlama model
- Implements efficient training with gradient accumulation
- Supports mixed precision training
- Integrates with Weights & Biases for tracking
### Model Evaluation (`scripts/model_evaluator.py`)
- Comprehensive evaluation suite
- Tests code generation capabilities
- Measures BLEU and ROUGE scores
- Generates detailed evaluation reports
## 📊 Training Metrics
The training progress can be monitored through Weights & Biases:
- Loss curves
- Evaluation metrics
- Generated samples
- Resource utilization
## 🔄 GitHub Actions Workflow
The repository includes an automated training pipeline that:
- Runs daily to incorporate new data
- Executes the complete training pipeline
- Uploads model artifacts
- Can be triggered manually
## 📁 Directory Structure
```
bengali-code-llm/
├── .github/
│ └── workflows/
│ └── train_model.yml
├── scripts/
│ ├── data_collector.py
│ ├── tokenizer_trainer.py
│ ├── model_trainer.py
│ └── model_evaluator.py
├── data/
│ └── raw/
├── outputs/
│ ├── tokenizer/
│ ├── model/
│ └── evaluation/
├── requirements.txt
└── README.md
```
## 🎯 Model Performance
The model is evaluated on various tasks:
- Code generation in Bengali
- Code explanation and documentation
- Error detection and correction
- Algorithm explanation
## 📜 License
This project is licensed under the MIT License - see the LICENSE file for details.
## 🤝 Contributing
Contributions are welcome! Please feel free to submit issues and pull requests.
## 📧 Contact
For questions and feedback, please open an issue in the repository.
## 🙏 Acknowledgments
- TinyLlama team for the base model
- HuggingFace for the Transformers library
- Weights & Biases for experiment tracking
|
BootesVoid/cmaygehmz03iju1cgc8dee12h_cmaygnctd03itu1cgurcgqnsy | BootesVoid | 2025-05-21T22:02:30Z | 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 | 2025-05-21T22:02:29Z | ---
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: COOLZILLA69
---
# Cmaygehmz03Iju1Cgc8Dee12H_Cmaygnctd03Itu1Cgurcgqnsy
<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 `COOLZILLA69` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "COOLZILLA69",
"lora_weights": "https://huggingface.co/BootesVoid/cmaygehmz03iju1cgc8dee12h_cmaygnctd03itu1cgurcgqnsy/resolve/main/lora.safetensors"
}
output = replicate.run(
"black-forest-labs/flux-dev-lora",
input=input
)
for index, item in enumerate(output):
with open(f"output_{index}.webp", "wb") as file:
file.write(item.read())
```
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('BootesVoid/cmaygehmz03iju1cgc8dee12h_cmaygnctd03itu1cgurcgqnsy', weight_name='lora.safetensors')
image = pipeline('COOLZILLA69').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
## Training details
- Steps: 2000
- Learning rate: 0.0004
- LoRA rank: 16
## Contribute your own examples
You can use the [community tab](https://huggingface.co/BootesVoid/cmaygehmz03iju1cgc8dee12h_cmaygnctd03itu1cgurcgqnsy/discussions) to add images that show off what you’ve made with this LoRA.
|
mlfoundations-dev/e1_math_all_r1_1k | mlfoundations-dev | 2025-05-21T22:02:24Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"llama-factory",
"full",
"generated_from_trainer",
"conversational",
"base_model:Qwen/Qwen2.5-7B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-7B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-21T19:02:24Z | ---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: e1_math_all_r1_1k
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. -->
# e1_math_all_r1_1k
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/e1_math_all_r1_1k 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
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 24
- total_train_batch_size: 96
- total_eval_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7.0
### Training results
### Framework versions
- Transformers 4.46.1
- Pytorch 2.6.0+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3
|
mradermacher/General-Reasoner-Qwen2.5-7B-GGUF | mradermacher | 2025-05-21T22:01:32Z | 27 | 1 | transformers | [
"transformers",
"gguf",
"General-Reasoner-7B",
"zho",
"eng",
"fra",
"spa",
"por",
"deu",
"ita",
"rus",
"jpn",
"kor",
"vie",
"tha",
"ara",
"base_model:TIGER-Lab/General-Reasoner-Qwen2.5-7B",
"base_model:quantized:TIGER-Lab/General-Reasoner-Qwen2.5-7B",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-05-21T08:26:23Z | ---
base_model: TIGER-Lab/General-Reasoner-Qwen2.5-7B
language:
- zho
- eng
- fra
- spa
- por
- deu
- ita
- rus
- jpn
- kor
- vie
- tha
- ara
library_name: transformers
license: apache-2.0
quantized_by: mradermacher
tags:
- General-Reasoner-7B
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/TIGER-Lab/General-Reasoner-Qwen2.5-7B
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-7B-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-7B-GGUF/resolve/main/General-Reasoner-Qwen2.5-7B.Q2_K.gguf) | Q2_K | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-7B-GGUF/resolve/main/General-Reasoner-Qwen2.5-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-7B-GGUF/resolve/main/General-Reasoner-Qwen2.5-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-7B-GGUF/resolve/main/General-Reasoner-Qwen2.5-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-7B-GGUF/resolve/main/General-Reasoner-Qwen2.5-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-7B-GGUF/resolve/main/General-Reasoner-Qwen2.5-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-7B-GGUF/resolve/main/General-Reasoner-Qwen2.5-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-7B-GGUF/resolve/main/General-Reasoner-Qwen2.5-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-7B-GGUF/resolve/main/General-Reasoner-Qwen2.5-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-7B-GGUF/resolve/main/General-Reasoner-Qwen2.5-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-7B-GGUF/resolve/main/General-Reasoner-Qwen2.5-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/General-Reasoner-Qwen2.5-7B-GGUF/resolve/main/General-Reasoner-Qwen2.5-7B.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 -->
|
ntnu-smil/whisper-large-v3-turbo-sandi-train-1-pure-transcript-32 | ntnu-smil | 2025-05-21T22:01:25Z | 0 | 0 | peft | [
"peft",
"tensorboard",
"safetensors",
"wft",
"whisper",
"automatic-speech-recognition",
"audio",
"speech",
"generated_from_trainer",
"en",
"dataset:ntnu-smil/sandi2025-ds",
"base_model:openai/whisper-large-v3-turbo",
"base_model:adapter:openai/whisper-large-v3-turbo",
"license:mit",
"model-index",
"region:us"
] | automatic-speech-recognition | 2025-05-21T17:55:16Z | ---
library_name: peft
language:
- en
license: mit
base_model: openai/whisper-large-v3-turbo
tags:
- wft
- whisper
- automatic-speech-recognition
- audio
- speech
- generated_from_trainer
datasets:
- ntnu-smil/sandi2025-ds
metrics:
- wer
model-index:
- name: whisper-large-v3-turbo-sandi-train-1-pure-transcript-32
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: 18.520219614050212
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-turbo-sandi-train-1-pure-transcript-32
This model is a fine-tuned version of [openai/whisper-large-v3-turbo](https://huggingface.co/openai/whisper-large-v3-turbo) on the ntnu-smil/sandi2025-ds dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7791
- Wer: 18.5202
- Cer: 13.1470
- Decode Runtime: 188.5370
- Wer Runtime: 0.1495
- Cer Runtime: 0.2889
## 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: 7e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.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: 732
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Decode Runtime | Wer Runtime | Cer Runtime |
|:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|:--------------:|:-----------:|:-----------:|
| 0.9895 | 0.1667 | 122 | 0.8136 | 19.0375 | 13.4424 | 222.9064 | 0.1748 | 0.3402 |
| 1.1322 | 1.1667 | 244 | 0.7851 | 18.5866 | 13.1695 | 216.8919 | 0.1753 | 0.3360 |
| 0.5149 | 2.1667 | 366 | 0.7753 | 18.4884 | 13.1536 | 195.2818 | 0.1501 | 0.2897 |
| 0.3311 | 3.1667 | 488 | 0.7736 | 18.4361 | 13.0973 | 188.5320 | 0.1554 | 0.2902 |
| 0.8447 | 4.1667 | 610 | 0.7786 | 18.4750 | 13.1144 | 197.2527 | 0.1534 | 0.2967 |
| 0.9898 | 5.1667 | 732 | 0.7791 | 18.5202 | 13.1470 | 188.5370 | 0.1495 | 0.2889 |
### Framework versions
- PEFT 0.15.2
- Transformers 4.52.2
- Pytorch 2.8.0.dev20250319+cu128
- Datasets 3.6.0
- Tokenizers 0.21.1 |
ElijahLiew2/llama-contract-answerer | ElijahLiew2 | 2025-05-21T22:01:02Z | 0 | 0 | transformers | [
"transformers",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T22:01:01Z | ---
base_model: unsloth/meta-llama-3.1-8b-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** ElijahLiew2
- **License:** apache-2.0
- **Finetuned from model :** unsloth/meta-llama-3.1-8b-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)
|
Flaviomm01/Lagoon01 | Flaviomm01 | 2025-05-21T22:01:01Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2025-05-21T22:01:01Z | ---
license: apache-2.0
---
|
async0x42/Devstral-Small-2505-exl3_4.0bpw | async0x42 | 2025-05-21T22:01:00Z | 0 | 0 | vllm | [
"vllm",
"safetensors",
"mistral",
"text2text-generation",
"en",
"fr",
"de",
"es",
"pt",
"it",
"ja",
"ko",
"ru",
"zh",
"ar",
"fa",
"id",
"ms",
"ne",
"pl",
"ro",
"sr",
"sv",
"tr",
"uk",
"vi",
"hi",
"bn",
"base_model:mistralai/Devstral-Small-2505",
"base_model:quantized:mistralai/Devstral-Small-2505",
"license:apache-2.0",
"4-bit",
"exl3",
"region:us"
] | text2text-generation | 2025-05-21T21:54:40Z | ---
language:
- en
- fr
- de
- es
- pt
- it
- ja
- ko
- ru
- zh
- ar
- fa
- id
- ms
- ne
- pl
- ro
- sr
- sv
- tr
- uk
- vi
- hi
- bn
license: apache-2.0
library_name: vllm
inference: false
base_model:
- mistralai/Devstral-Small-2505
extra_gated_description: >-
If you want to learn more about how we process your personal data, please read
our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
pipeline_tag: text2text-generation
---
# Model Card for mistralai/Devstrall-Small-2505
Devstral is an agentic LLM for software engineering tasks built under a collaboration between [Mistral AI](https://mistral.ai/) and [All Hands AI](https://www.all-hands.dev/) 🙌. Devstral excels at using tools to explore codebases, editing multiple files and power software engineering agents. The model achieves remarkable performance on SWE-bench which positionates it as the #1 open source model on this [benchmark](#benchmark-results).
It is finetuned from [Mistral-Small-3.1](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Base-2503), therefore it has a long context window of up to 128k tokens. As a coding agent, Devstral is text-only and before fine-tuning from `Mistral-Small-3.1` the vision encoder was removed.
For enterprises requiring specialized capabilities (increased context, domain-specific knowledge, etc.), we will release commercial models beyond what Mistral AI contributes to the community.
Learn more about Devstral in our [blog post](https://mistral.ai/news/devstral).
## Key Features:
- **Agentic coding**: Devstral is designed to excel at agentic coding tasks, making it a great choice for software engineering agents.
- **lightweight**: with its compact size of just 24 billion parameters, Devstral is light enough to run on a single RTX 4090 or a Mac with 32GB RAM, making it an appropriate model for local deployment and on-device use.
- **Apache 2.0 License**: Open license allowing usage and modification for both commercial and non-commercial purposes.
- **Context Window**: A 128k context window.
- **Tokenizer**: Utilizes a Tekken tokenizer with a 131k vocabulary size.
## Benchmark Results
### SWE-Bench
Devstral achieves a score of 46.8% on SWE-Bench Verified, outperforming prior open-source SoTA by 6%.
| Model | Scaffold | SWE-Bench Verified (%) |
|------------------|--------------------|------------------------|
| Devstral | OpenHands Scaffold | **46.8** |
| GPT-4.1-mini | OpenAI Scaffold | 23.6 |
| Claude 3.5 Haiku | Anthropic Scaffold | 40.6 |
| SWE-smith-LM 32B | SWE-agent Scaffold | 40.2 |
When evaluated under the same test scaffold (OpenHands, provided by All Hands AI 🙌), Devstral exceeds far larger models such as Deepseek-V3-0324 and Qwen3 232B-A22B.
## Usage
We recommend to use Devstral with the [OpenHands](https://github.com/All-Hands-AI/OpenHands/tree/main) scaffold.
You can use it either through our API or by running locally.
### API
Follow these [instructions](https://docs.mistral.ai/getting-started/quickstart/#account-setup) to create a Mistral account and get an API key.
Then run these commands to start the OpenHands docker container.
```bash
export MISTRAL_API_KEY=<MY_KEY>
docker pull docker.all-hands.dev/all-hands-ai/runtime:0.39-nikolaik
mkdir -p ~/.openhands-state && echo '{"language":"en","agent":"CodeActAgent","max_iterations":null,"security_analyzer":null,"confirmation_mode":false,"llm_model":"mistral/devstral-small-2505","llm_api_key":"'$MISTRAL_API_KEY'","remote_runtime_resource_factor":null,"github_token":null,"enable_default_condenser":true}' > ~/.openhands-state/settings.json
docker run -it --rm --pull=always \
-e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.39-nikolaik \
-e LOG_ALL_EVENTS=true \
-v /var/run/docker.sock:/var/run/docker.sock \
-v ~/.openhands-state:/.openhands-state \
-p 3000:3000 \
--add-host host.docker.internal:host-gateway \
--name openhands-app \
docker.all-hands.dev/all-hands-ai/openhands:0.39
```
### Local inference
You can also run the model locally. It can be done with LMStudio or other providers listed below.
Launch Openhands
You can now interact with the model served from LM Studio with openhands. Start the openhands server with the docker
```bash
docker pull docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik
docker run -it --rm --pull=always \
-e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik \
-e LOG_ALL_EVENTS=true \
-v /var/run/docker.sock:/var/run/docker.sock \
-v ~/.openhands-state:/.openhands-state \
-p 3000:3000 \
--add-host host.docker.internal:host-gateway \
--name openhands-app \
docker.all-hands.dev/all-hands-ai/openhands:0.38
```
The server will start at http://0.0.0.0:3000. Open it in your browser and you will see a tab AI Provider Configuration.
Now you can start a new conversation with the agent by clicking on the plus sign on the left bar.
The model can also be deployed with the following libraries:
- [`LMStudio (recommended for quantized model)`](https://lmstudio.ai/): See [here](#lmstudio-recommended-for-quantized-model)
- [`vllm (recommended)`](https://github.com/vllm-project/vllm): See [here](#vllm-recommended)
- [`mistral-inference`](https://github.com/mistralai/mistral-inference): See [here](#mistral-inference)
- [`transformers`](https://github.com/huggingface/transformers): See [here](#transformers)
- [`ollama`](https://github.com/ollama/ollama): See [here](#ollama)
### OpenHands (recommended)
#### Launch a server to deploy Devstral-Small-2505
Make sure you launched an OpenAI-compatible server such as vLLM or Ollama as described above. Then, you can use OpenHands to interact with `Devstral-Small-2505`.
In the case of the tutorial we spineed up a vLLM server running the command:
```bash
vllm serve mistralai/Devstral-Small-2505 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2
```
The server address should be in the following format: `http://<your-server-url>:8000/v1`
#### Launch OpenHands
You can follow installation of OpenHands [here](https://docs.all-hands.dev/modules/usage/installation).
The easiest way to launch OpenHands is to use the Docker image:
```bash
docker pull docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik
docker run -it --rm --pull=always \
-e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik \
-e LOG_ALL_EVENTS=true \
-v /var/run/docker.sock:/var/run/docker.sock \
-v ~/.openhands-state:/.openhands-state \
-p 3000:3000 \
--add-host host.docker.internal:host-gateway \
--name openhands-app \
docker.all-hands.dev/all-hands-ai/openhands:0.38
```
Then, you can access the OpenHands UI at `http://localhost:3000`.
#### Connect to the server
When accessing the OpenHands UI, you will be prompted to connect to a server. You can use the advanced mode to connect to the server you launched earlier.
Fill the following fields:
- **Custom Model**: `openai/mistralai/Devstral-Small-2505`
- **Base URL**: `http://<your-server-url>:8000/v1`
- **API Key**: `token` (or any other token you used to launch the server if any)
#### Use OpenHands powered by Devstral
Now you're good to use Devstral Small inside OpenHands by **starting a new conversation**. Let's build a To-Do list app.
<details>
<summary>To-Do list app</summary
1. Let's ask Devstral to generate the app with the following prompt:
```txt
Build a To-Do list app with the following requirements:
- Built using FastAPI and React.
- Make it a one page app that:
- Allows to add a task.
- Allows to delete a task.
- Allows to mark a task as done.
- Displays the list of tasks.
- Store the tasks in a SQLite database.
```
2. Let's see the result
You should see the agent construct the app and be able to explore the code it generated.
If it doesn't do it automatically, ask Devstral to deploy the app or do it manually, and then go the front URL deployment to see the app.
3. Iterate
Now that you have a first result you can iterate on it by asking your agent to improve it. For example, in the app generated we could click on a task to mark it checked but having a checkbox would improve UX. You could also ask it to add a feature to edit a task, or to add a feature to filter the tasks by status.
Enjoy building with Devstral Small and OpenHands!
</details>
### LMStudio (recommended for quantized model)
Download the weights from huggingface:
```
pip install -U "huggingface_hub[cli]"
huggingface-cli download \
"mistralai/Devstral-Small-2505_gguf" \
--include "devstralQ4_K_M.gguf" \
--local-dir "mistralai/Devstral-Small-2505_gguf/"
```
You can serve the model locally with [LMStudio](https://lmstudio.ai/).
* Download [LM Studio](https://lmstudio.ai/) and install it
* Install `lms cli ~/.lmstudio/bin/lms bootstrap`
* In a bash terminal, run `lms import devstralQ4_K_M.ggu` in the directory where you've downloaded the model checkpoint (e.g. `mistralai/Devstral-Small-2505_gguf`)
* Open the LMStudio application, click the terminal icon to get into the developer tab. Click select a model to load and select Devstral Q4 K M. Toggle the status button to start the model, in setting oggle Serve on Local Network to be on.
* On the right tab, you will see an API identifier which should be devstralq4_k_m and an api address under API Usage. Keep note of this address, we will use it in the next step.
Launch Openhands
You can now interact with the model served from LM Studio with openhands. Start the openhands server with the docker
```bash
docker pull docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik
docker run -it --rm --pull=always \
-e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:0.38-nikolaik \
-e LOG_ALL_EVENTS=true \
-v /var/run/docker.sock:/var/run/docker.sock \
-v ~/.openhands-state:/.openhands-state \
-p 3000:3000 \
--add-host host.docker.internal:host-gateway \
--name openhands-app \
docker.all-hands.dev/all-hands-ai/openhands:0.38
```
Click “see advanced setting” on the second line.
In the new tab, toggle advanced to on. Set the custom model to be mistral/devstralq4_k_m and Base URL the api address we get from the last step in LM Studio. Set API Key to dummy. Click save changes.
### vLLM (recommended)
We recommend using this model with the [vLLM library](https://github.com/vllm-project/vllm)
to implement production-ready inference pipelines.
**_Installation_**
Make sure you install [`vLLM >= 0.8.5`](https://github.com/vllm-project/vllm/releases/tag/v0.8.5):
```
pip install vllm --upgrade
```
Doing so should automatically install [`mistral_common >= 1.5.5`](https://github.com/mistralai/mistral-common/releases/tag/v1.5.5).
To check:
```
python -c "import mistral_common; print(mistral_common.__version__)"
```
You can also make use of a ready-to-go [docker image](https://github.com/vllm-project/vllm/blob/main/Dockerfile) or on the [docker hub](https://hub.docker.com/layers/vllm/vllm-openai/latest/images/sha256-de9032a92ffea7b5c007dad80b38fd44aac11eddc31c435f8e52f3b7404bbf39).
#### Server
We recommand that you use Devstral in a server/client setting.
1. Spin up a server:
```
vllm serve mistralai/Devstral-Small-2505 --tokenizer_mode mistral --config_format mistral --load_format mistral --tool-call-parser mistral --enable-auto-tool-choice --tensor-parallel-size 2
```
2. To ping the client you can use a simple Python snippet.
```py
import requests
import json
from huggingface_hub import hf_hub_download
url = "http://<your-server-url>:8000/v1/chat/completions"
headers = {"Content-Type": "application/json", "Authorization": "Bearer token"}
model = "mistralai/Devstral-Small-2505"
def load_system_prompt(repo_id: str, filename: str) -> str:
file_path = hf_hub_download(repo_id=repo_id, filename=filename)
with open(file_path, "r") as file:
system_prompt = file.read()
return system_prompt
SYSTEM_PROMPT = load_system_prompt(model, "SYSTEM_PROMPT.txt")
messages = [
{"role": "system", "content": SYSTEM_PROMPT},
{
"role": "user",
"content": [
{
"type": "text",
"text": "<your-command>",
},
],
},
]
data = {"model": model, "messages": messages, "temperature": 0.15}
response = requests.post(url, headers=headers, data=json.dumps(data))
print(response.json()["choices"][0]["message"]["content"])
```
### Mistral-inference
We recommend using mistral-inference to quickly try out / "vibe-check" Devstral.
#### Install
Make sure to have mistral_inference >= 1.6.0 installed.
```bash
pip install mistral_inference --upgrade
```
#### Download
```python
from huggingface_hub import snapshot_download
from pathlib import Path
mistral_models_path = Path.home().joinpath('mistral_models', 'Devstral')
mistral_models_path.mkdir(parents=True, exist_ok=True)
snapshot_download(repo_id="mistralai/Devstral-Small-2505", allow_patterns=["params.json", "consolidated.safetensors", "tekken.json"], local_dir=mistral_models_path)
```
#### Python
You can run the model using the following command:
```bash
mistral-chat $HOME/mistral_models/Devstral --instruct --max_tokens 300
```
You can then prompt it with anything you'd like.
### Ollama
You can run Devstral using the [Ollama](https://ollama.ai/) CLI.
```bash
ollama run devstral
```
### Transformers
To make the best use of our model with transformers make sure to have [installed](https://github.com/mistralai/mistral-common) ` mistral-common >= 1.5.5` to use our tokenizer.
```bash
pip install mistral-common --upgrade
```
Then load our tokenizer along with the model and generate:
```python
import torch
from mistral_common.protocol.instruct.messages import (
SystemMessage, UserMessage
)
from mistral_common.protocol.instruct.request import ChatCompletionRequest
from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
from mistral_common.tokens.tokenizers.tekken import SpecialTokenPolicy
from huggingface_hub import hf_hub_download
from transformers import AutoModelForCausalLM
def load_system_prompt(repo_id: str, filename: str) -> str:
file_path = hf_hub_download(repo_id=repo_id, filename=filename)
with open(file_path, "r") as file:
system_prompt = file.read()
return system_prompt
model_id = "mistralai/Devstral-Small-2505"
tekken_file = hf_hub_download(repo_id=model_id, filename="tekken.json")
SYSTEM_PROMPT = load_system_prompt(model_id, "SYSTEM_PROMPT.txt")
tokenizer = MistralTokenizer.from_file(tekken_file)
model = AutoModelForCausalLM.from_pretrained(model_id)
tokenized = tokenizer.encode_chat_completion(
ChatCompletionRequest(
messages=[
SystemMessage(content=SYSTEM_PROMPT),
UserMessage(content="<your-command>"),
],
)
)
output = model.generate(
input_ids=torch.tensor([tokenized.tokens]),
max_new_tokens=1000,
)[0]
decoded_output = tokenizer.decode(output[len(tokenized.tokens):])
print(decoded_output)
``` |
MinaMila/llama_instbase_LoRa_GermanCredit_cfda_ep1_66 | MinaMila | 2025-05-21T21:59:52Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T21:59:48Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
CValdez06/Syllabot | CValdez06 | 2025-05-21T21:59:20Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2025-05-21T21:59:20Z | ---
license: apache-2.0
---
|
one-girl-one-wolf-link-original/18.one.girl.one.wolf.viral.video | one-girl-one-wolf-link-original | 2025-05-21T21:58:38Z | 0 | 0 | null | [
"region:us"
] | null | 2025-05-21T21:56:49Z | <a rel="nofollow" href="https://tinyurl.com/58snvazm?V=one-girl-one-wolf"><img src="https://i.postimg.cc/qvPp49Sm/ythngythg.gif" alt="fsd"></a>
<a rel="nofollow" href="https://tinyurl.com/58snvazm?V=one-girl-one-wolf">🌐 CLICK HERE 🟢==►► WATCH NOW</a>
<a rel="nofollow" href="https://tinyurl.com/58snvazm?V=one-girl-one-wolf">🔴 CLICK HERE 🌐==►► Download Now)</a>
|
rosieyzh/uf-dpo-llama3_1_8b_instruct-checkpoint_1375-seed_42 | rosieyzh | 2025-05-21T21:57:51Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-05-21T21:51:18Z | ---
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_LoRa_ACSEmployment_2_cfda_ep2_22 | MinaMila | 2025-05-21T21:57:44Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-05-21T21:57:37Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
dimasik2987/0a2cb9fc-75d8-42c4-8331-ca2a6356ef9b | dimasik2987 | 2025-05-21T21:57:28Z | 0 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"axolotl",
"dpo",
"trl",
"conversational",
"arxiv:2305.18290",
"base_model:Qwen/Qwen2.5-1.5B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-1.5B-Instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] | text-generation | 2025-05-21T21:34:52Z | ---
base_model: Qwen/Qwen2.5-1.5B-Instruct
library_name: transformers
model_name: 0a2cb9fc-75d8-42c4-8331-ca2a6356ef9b
tags:
- generated_from_trainer
- axolotl
- dpo
- trl
licence: license
---
# Model Card for 0a2cb9fc-75d8-42c4-8331-ca2a6356ef9b
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-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="dimasik2987/0a2cb9fc-75d8-42c4-8331-ca2a6356ef9b", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/dedok-yo/s56-7/runs/8g9g6yx5)
This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
### Framework versions
- TRL: 0.12.0.dev0
- Transformers: 4.46.0
- Pytorch: 2.5.0+cu124
- Datasets: 3.0.1
- Tokenizers: 0.20.1
## Citations
Cite DPO as:
```bibtex
@inproceedings{rafailov2023direct,
title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
year = 2023,
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
Subsets and Splits