modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-06-28 06:27:35
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 500
values | tags
sequencelengths 1
4.05k
| pipeline_tag
stringclasses 54
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-06-28 06:24:42
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
Disya/Josiefied-Qwen3-14B-abliterated-v1-Q4_K_M-GGUF | Disya | 2025-04-30T16:43:09Z | 0 | 0 | null | [
"gguf",
"chat",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"base_model:Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v1",
"base_model:quantized:Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v1",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2025-04-30T16:26:18Z | ---
base_model: Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v1
pipeline_tag: text-generation
tags:
- chat
- llama-cpp
- gguf-my-repo
---
---
**The model's quantization is broken — don't download the model here.**
---
# Disya/Josiefied-Qwen3-14B-abliterated-v1-Q4_K_M-GGUF
This model was converted to GGUF format from [`Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v1`](https://huggingface.co/Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v1) 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/Goekdeniz-Guelmez/Josiefied-Qwen3-14B-abliterated-v1) 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 Disya/Josiefied-Qwen3-14B-abliterated-v1-Q4_K_M-GGUF --hf-file josiefied-qwen3-14b-abliterated-v1-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Disya/Josiefied-Qwen3-14B-abliterated-v1-Q4_K_M-GGUF --hf-file josiefied-qwen3-14b-abliterated-v1-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 Disya/Josiefied-Qwen3-14B-abliterated-v1-Q4_K_M-GGUF --hf-file josiefied-qwen3-14b-abliterated-v1-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Disya/Josiefied-Qwen3-14B-abliterated-v1-Q4_K_M-GGUF --hf-file josiefied-qwen3-14b-abliterated-v1-q4_k_m.gguf -c 2048
```
|
Sophie-Rain-Sophie-Rain-Spiderman-Video-tv/Sophie.Rain.SpiderMan.Video.Tutorial | Sophie-Rain-Sophie-Rain-Spiderman-Video-tv | 2025-04-30T16:35:19Z | 0 | 0 | null | [
"region:us"
] | null | 2025-04-30T16:33:24Z |
<a href="https://xxxporn24video.blogspot.com/2025/04/leaked.html" rel="nofollow">►►✅ 𝘾𝙇𝙄𝘾𝙆 𝙃𝙀𝙍𝙀 ==►► 𝙁𝙪𝙡𝙡 𝙑𝙞𝙙𝙚𝙤️</a></p>
<a href="https://xxxporn24video.blogspot.com/2025/04/leaked.html" rel="nofollow">🔴►𝐂𝐋𝐈𝐂𝐊 𝐇𝐄𝐑𝐄 🌐==►► 𝐃𝐨𝐰𝐧𝐥𝐨𝐚𝐝 𝐍𝐨𝐰⬇️⬇️</a></p>
<p><a rel="nofollow" title="WATCH NOW" href="https://xxxporn24video.blogspot.com/2025/04/leaked.html"><img border="Sophie+Rain+Spidermanno" height="480" width="720" title="WATCH NOW" alt="WATCH NOW" src="https://i.ibb.co.com/xMMVF88/686577567.gif"></a></p>
03 seconds ago
L𝚎aked Video Sophie Rain Spiderman Video Tutorial Original Video Viral Video L𝚎aked on X Twitter Telegram
L𝚎aked Video Sophie Rain Spiderman Video Tutorial Original Video Viral Video L𝚎aked on X Twitter
Sophie Rain Spiderman Video Tutorial Original Video video oficial twitter
L𝚎aked Video Sophie Rain Spiderman Video Tutorial Original Video Viral Video L𝚎aked on X Twitter
. . . . . . . . . |
ayoub-66/mt5_model_output | ayoub-66 | 2025-04-30T16:22:01Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"mt5",
"text2text-generation",
"generated_from_trainer",
"base_model:google/mt5-base",
"base_model:finetune:google/mt5-base",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2025-04-30T16:20:01Z | ---
library_name: transformers
license: apache-2.0
base_model: google/mt5-base
tags:
- generated_from_trainer
model-index:
- name: mt5_model_output
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_model_output
This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) 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: 3e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.51.1
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0
|
prithivMLmods/Geminorum-Wasat-14B-Instruct | prithivMLmods | 2025-04-30T16:14:10Z | 6 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"text-generation-inference",
"Math",
"Reasoning",
"Code",
"RL",
"conversational",
"en",
"base_model:deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
"base_model:finetune:deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-26T04:32:54Z | ---
license: apache-2.0
language:
- en
base_model:
- deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
pipeline_tag: text-generation
library_name: transformers
tags:
- text-generation-inference
- Math
- Reasoning
- Code
- RL
---
# **Geminorum-Wasat-14B-Instruct**
> **Geminorum-Wasat-14B-Instruct** is built on the Qwen 2.5 14B modality architecture, engineered to excel in mathematical reasoning, distributed reinforcement learning (RL), and general-purpose problem solving. This model is fine-tuned with chain-of-thought reasoning datasets, optimization-focused corpora, and advanced structured reasoning datasets to maximize its capabilities in logical deduction, multi-step reasoning, and intelligent decision-making.
## **Key Improvements**
1. **Advanced Mathematical Reasoning**:
Excels in solving complex equations, performing symbolic computation, theorem proving, and step-by-step mathematical problem-solving.
2. **Distributed Reinforcement Learning Expertise**:
Specially fine-tuned for robust policy optimization using distributed RL techniques, providing resilience and optimality across dynamic problem spaces.
3. **General-Purpose Reasoning and Problem Solving**:
Strong across a broad range of domains, handling factual questions, logical analysis, and multi-step cognitive tasks.
4. **Long-Context Mastery**:
Supports up to 128K tokens for context and can generate up to 8K tokens, enabling detailed, coherent long-form outputs and complex derivations.
5. **Superior Instruction Following**:
Capable of following complex and structured prompts precisely, maintaining focus and clarity over extended dialogues.
6. **Coding and Algorithmic Fluency**:
Highly effective in code generation, debugging, algorithm design, and optimization problem modeling across various programming languages.
## **Quickstart with transformers**
You can load and use the model easily with the `transformers` library and `apply_chat_template`:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "prithivMLmods/Geminorum-Wasat-14B-Instruct"
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)
prompt = "Explain the connection between distributed reinforcement learning and robust policy optimization."
messages = [
{"role": "system", "content": "You are an expert assistant specializing in mathematics, optimization, and reinforcement learning."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
generated_ids = model.generate(
**model_inputs,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
```
## **Intended Use**
1. **Mathematical and Optimization Problem Solving**:
Designed for solving complex mathematical problems, optimization modeling, symbolic logic, and structured derivations.
2. **Distributed Reinforcement Learning Research**:
Supports designing, analyzing, and explaining distributed RL systems, robust policy optimization, and autonomous decision systems.
3. **General Knowledge and Reasoning**:
Effective in answering a wide range of questions and performing structured reasoning across scientific, technical, and educational domains.
4. **Educational and Research Support**:
Ideal for students, researchers, and professionals seeking detailed explanations, derivations, and robust scientific insights.
5. **Code Writing and Algorithm Design**:
Excels at creating, optimizing, and explaining algorithms, particularly those relevant to mathematical computation and optimization.
6. **Intelligent Conversational Systems**:
Perfect for technical conversational agents and educational bots requiring deep understanding and detailed reasoning capabilities.
7. **Long-Form Technical Content Generation**:
Capable of producing structured, coherent articles, tutorials, and research papers, especially in technical and mathematical fields.
8. **Structured Data Generation**:
Supports outputting structured formats such as proofs, equations, tables, and JSON useful for scientific and technical workflows.
## **Limitations**
1. **Heavy Hardware Requirements**:
Due to its large parameter count and long-context handling, it requires powerful GPUs or TPUs with significant memory.
2. **Potential for Training Biases**:
Outputs may still reflect biases from the mathematical, technical, or optimization-specific datasets used during training.
3. **Less Effective in Creative Tasks**:
Focused more on technical and logical reasoning than on freeform creative writing or storytelling.
4. **No Real-Time Event Awareness**:
Limited to knowledge prior to its training cutoff, without access to live or real-world updates.
5. **Prompt Sensitivity**:
Performance may vary based on the clarity, structure, and specificity of the prompt, particularly for complex multi-step tasks.
6. **Error Propagation Risk**:
Small inaccuracies in early stages of long-form outputs could propagate, affecting the overall answer coherence. |
ggml-org/Qwen2.5-VL-3B-Instruct-GGUF | ggml-org | 2025-04-30T16:09:58Z | 359 | 0 | null | [
"gguf",
"base_model:Qwen/Qwen2.5-VL-3B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-VL-3B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-04-30T16:09:12Z | ---
license: apache-2.0
base_model: Qwen/Qwen2.5-VL-3B-Instruct
---
# Qwen2.5-VL-3B-Instruct
Original model: https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct
|
litert-community/Llama-3.2-1B-Instruct | litert-community | 2025-04-30T16:08:52Z | 0 | 0 | null | [
"tflite",
"base_model:meta-llama/Llama-3.2-1B-Instruct",
"base_model:finetune:meta-llama/Llama-3.2-1B-Instruct",
"license:llama3.2",
"region:us"
] | null | 2025-04-30T16:05:52Z | ---
license: llama3.2
base_model: meta-llama/Llama-3.2-1B-Instruct
---
# litert-community/Llama-3.2-1B-Instruct
This model provides a few variants of
[meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) that are ready for
deployment on Android using the
[LiteRT (fka TFLite) stack](https://ai.google.dev/edge/litert) and
[MediaPipe LLM Inference API](https://ai.google.dev/edge/mediapipe/solutions/genai/llm_inference).
## Use the models
### Colab
*Disclaimer: The target deployment surface for the LiteRT models is
Android/iOS/Web and the stack has been optimized for performance on these
targets. Trying out the system in Colab is an easier way to familiarize yourself
with the LiteRT stack, with the caveat that the performance (memory and latency)
on Colab could be much worse than on a local device.*
[](https://colab.research.google.com/#fileId=https://huggingface.co/litert-community/Llama-3.2-1B-Instruct/blob/main/notebook.ipynb)
### Android
* Download and install
[the apk](https://github.com/google-ai-edge/mediapipe-samples/releases/latest/download/llm_inference-debug.apk).
* Follow the instructions in the app.
To build the demo app from source, please follow the
[instructions](https://github.com/google-ai-edge/mediapipe-samples/blob/main/examples/llm_inference/android/README.md)
from the GitHub repository.
## Performance
### Android
Note that all benchmark stats are from a Samsung S24 Ultra with
1280 KV cache size with multiple prefill signatures enabled.
<table border="1">
<tr>
<th></th>
<th>Backend</th>
<th>Prefill (tokens/sec)</th>
<th>Decode (tokens/sec)</th>
<th>Time-to-first-token (sec)</th>
<th>Memory (RSS in MB)</th>
<th>Model size (MB)</th>
</tr>
<tr>
<td>fp32 (baseline)</td>
<td>cpu</td>
<td><p style="text-align: right">55.94 tk/s</p></td>
<td><p style="text-align: right">7.42 tk/s</p></td>
<td><p style="text-align: right">10.82 s</p></td>
<td><p style="text-align: right">6,022 MB</p></td>
<td><p style="text-align: right">4,726 MB</p></td>
</tr>
<tr>
<td>dynamic_int8</td>
<td>cpu</td>
<td><p style="text-align: right">155.72 tk/s</p></td>
<td><p style="text-align: right">18.77 tk/s</p></td>
<td><p style="text-align: right">4.59 s</p></td>
<td><p style="text-align: right">2,950 MB</p></td>
<td><p style="text-align: right">1,229 MB</p></td>
</tr>
</table>
* Model Size: measured by the size of the .tflite flatbuffer (serialization
format for LiteRT models)
* Memory: indicator of peak RAM usage
* The inference on CPU is accelerated via the LiteRT
[XNNPACK](https://github.com/google/XNNPACK) delegate with 4 threads
* Benchmark is done assuming XNNPACK cache is enabled
* dynamic_int8: quantized model with int8 weights and float activations.
|
infogeo/16b43ada-c551-4395-9d37-9c614c50fc21 | infogeo | 2025-04-30T11:46:06Z | 0 | 0 | peft | [
"peft",
"safetensors",
"llama",
"axolotl",
"generated_from_trainer",
"base_model:heegyu/WizardVicuna2-13b-hf",
"base_model:adapter:heegyu/WizardVicuna2-13b-hf",
"4-bit",
"bitsandbytes",
"region:us"
] | null | 2025-04-30T11:35:43Z | ---
library_name: peft
base_model: heegyu/WizardVicuna2-13b-hf
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 16b43ada-c551-4395-9d37-9c614c50fc21
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
<details><summary>See axolotl config</summary>
axolotl version: `0.4.1`
```yaml
absolute_data_files: false
adapter: lora
base_model: heegyu/WizardVicuna2-13b-hf
bf16: true
chat_template: llama3
dataset_prepared_path: /workspace/axolotl
datasets:
- data_files:
- 05a1d5d398a81bd6_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/05a1d5d398a81bd6_train_data.json
type:
field_input: test
field_instruction: question
field_output: solution
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 1
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 1
gradient_checkpointing: true
gradient_clipping: 0.55
group_by_length: false
hub_model_id: infogeo/16b43ada-c551-4395-9d37-9c614c50fc21
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 1.0e-06
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_steps: 150
micro_batch_size: 8
mixed_precision: bf16
mlflow_experiment_name: /tmp/05a1d5d398a81bd6_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
saves_per_epoch: 1
sequence_len: 1024
special_tokens:
pad_token: </s>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: fd1dd4a2-11ce-46e2-8594-291f6e26aaab
wandb_project: s56-28
wandb_run: your_name
wandb_runid: fd1dd4a2-11ce-46e2-8594-291f6e26aaab
warmup_steps: 5
weight_decay: 0.01
xformers_attention: true
```
</details><br>
# 16b43ada-c551-4395-9d37-9c614c50fc21
This model is a fine-tuned version of [heegyu/WizardVicuna2-13b-hf](https://huggingface.co/heegyu/WizardVicuna2-13b-hf) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5889
## 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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 5
- training_steps: 150
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.6224 | 0.1403 | 150 | 0.5889 |
### Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1 |
PrMoriarty/ppo-Huggy | PrMoriarty | 2025-04-30T11:33:10Z | 0 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] | reinforcement-learning | 2025-04-30T11:33:04Z | ---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (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: PrMoriarty/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
LuckyLukke/grpo_turn_level_onesided_2_starter_change-200 | LuckyLukke | 2025-04-30T11:31:43Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-30T11:28:41Z | ---
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] |
ninja75/gemma2b-elon-merged | ninja75 | 2025-04-30T10:53:33Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-04-30T10:48:05Z | ---
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] |
jjeccles/qwen3b-lora-doc | jjeccles | 2025-04-30T10:16:47Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen3",
"trl",
"en",
"base_model:unsloth/Qwen3-1.7B",
"base_model:finetune:unsloth/Qwen3-1.7B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-04-30T10:16:39Z | ---
base_model: unsloth/Qwen3-1.7B
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** jjeccles
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen3-1.7B
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
ybq0509/des_Q_7B_ckpt3318 | ybq0509 | 2025-04-30T10:07:09Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-30T10:00:04Z | ---
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] |
prithivMLmods/3D-Printed-Or-Not-SigLIP2 | prithivMLmods | 2025-04-30T10:00:00Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"siglip",
"image-classification",
"3D-Printed-Or-Not",
"SigLIP2",
"Image-Classification",
"en",
"dataset:cmudrc/3d-printed-or-not",
"arxiv:2502.14786",
"base_model:google/siglip2-base-patch16-224",
"base_model:finetune:google/siglip2-base-patch16-224",
"doi:10.57967/hf/5297",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | 2025-04-28T17:51:11Z | ---
license: apache-2.0
datasets:
- cmudrc/3d-printed-or-not
language:
- en
base_model:
- google/siglip2-base-patch16-224
pipeline_tag: image-classification
library_name: transformers
tags:
- 3D-Printed-Or-Not
- SigLIP2
- Image-Classification
---
# **3D-Printed-Or-Not-SigLIP2**
> **3D-Printed-Or-Not-SigLIP2** is a vision-language encoder model fine-tuned from **google/siglip2-base-patch16-224** for **binary image classification**. It is trained to distinguish between images of **3D printed** and **non-3D printed** objects using the **SiglipForImageClassification** architecture.
> [!note]
*SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features* https://arxiv.org/pdf/2502.14786
```py
Classification Report:
precision recall f1-score support
3D Printed 0.9108 0.9388 0.9246 25760
Not 3D Printed 0.9368 0.9081 0.9222 25760
accuracy 0.9234 51520
macro avg 0.9238 0.9234 0.9234 51520
weighted avg 0.9238 0.9234 0.9234 51520
```
---
## **Label Space: 2 Classes**
The model classifies each image into one of the following categories:
```
Class 0: "3D Printed"
Class 1: "Not 3D Printed"
```
---
## **Install Dependencies**
```bash
pip install -q transformers torch pillow gradio
```
---
## **Inference Code**
```python
import gradio as gr
from transformers import AutoImageProcessor, SiglipForImageClassification
from PIL import Image
import torch
# Load model and processor
model_name = "prithivMLmods/3D-Printed-Or-Not-SigLIP2" # Replace with your model path if different
model = SiglipForImageClassification.from_pretrained(model_name)
processor = AutoImageProcessor.from_pretrained(model_name)
# Label mapping
id2label = {
"0": "3D Printed",
"1": "Not 3D Printed"
}
def classify_3d_printed(image):
image = Image.fromarray(image).convert("RGB")
inputs = processor(images=image, return_tensors="pt")
with torch.no_grad():
outputs = model(**inputs)
logits = outputs.logits
probs = torch.nn.functional.softmax(logits, dim=1).squeeze().tolist()
prediction = {
id2label[str(i)]: round(probs[i], 3) for i in range(len(probs))
}
return prediction
# Gradio Interface
iface = gr.Interface(
fn=classify_3d_printed,
inputs=gr.Image(type="numpy"),
outputs=gr.Label(num_top_classes=2, label="3D Printing Classification"),
title="3D-Printed-Or-Not-SigLIP2",
description="Upload an image to detect if the object is 3D printed or not."
)
if __name__ == "__main__":
iface.launch()
```
---
## **Intended Use**
**3D-Printed-Or-Not-SigLIP2** can be used for:
- **Manufacturing Verification** – Classify objects to ensure they meet production standards.
- **Educational Tools** – Train models and learners to distinguish between manufacturing methods.
- **Retail Filtering** – Categorize product images by manufacturing technique.
- **Quality Control** – Spot check datasets or content for 3D printing. |
dandelion4/stella-Qwen3-4B | dandelion4 | 2025-04-30T06:12:36Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen3",
"trl",
"en",
"base_model:unsloth/Qwen3-4B",
"base_model:finetune:unsloth/Qwen3-4B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-04-30T06:12:24Z | ---
base_model: unsloth/Qwen3-4B
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** dandelion4
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen3-4B
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
devin3780/DDZ | devin3780 | 2025-04-30T06:02:57Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2025-04-30T06:02:57Z | ---
license: apache-2.0
---
|
secmlr/SWE-BENCH-2000-enriched-reasoning-claude-localization_qwen_code_14b_2000_enriched_reasoning | secmlr | 2025-04-30T05:30:09Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"llama-factory",
"full",
"generated_from_trainer",
"conversational",
"base_model:agentica-org/DeepCoder-14B-Preview",
"base_model:finetune:agentica-org/DeepCoder-14B-Preview",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-29T20:39:54Z | ---
library_name: transformers
license: mit
base_model: agentica-org/DeepCoder-14B-Preview
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: SWE-BENCH-2000-enriched-reasoning-claude-localization_qwen_code_14b_2000_enriched_reasoning
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. -->
# SWE-BENCH-2000-enriched-reasoning-claude-localization_qwen_code_14b_2000_enriched_reasoning
This model is a fine-tuned version of [agentica-org/DeepCoder-14B-Preview](https://huggingface.co/agentica-org/DeepCoder-14B-Preview) on the SWE-BENCH-2000-enriched-reasoning-claude-localization 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: 12
- total_train_batch_size: 48
- total_eval_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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0
|
mradermacher/Qwen2.5-7B-Instruct-abliterated-GGUF | mradermacher | 2025-04-30T05:22:39Z | 95 | 1 | transformers | [
"transformers",
"gguf",
"chat",
"abliterated",
"uncensored",
"zho",
"eng",
"fra",
"spa",
"por",
"deu",
"ita",
"rus",
"jpn",
"kor",
"vie",
"tha",
"ara",
"base_model:huihui-ai/Qwen2.5-7B-Instruct-abliterated",
"base_model:quantized:huihui-ai/Qwen2.5-7B-Instruct-abliterated",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2024-09-20T17:31:33Z | ---
base_model: huihui-ai/Qwen2.5-7B-Instruct-abliterated
language:
- zho
- eng
- fra
- spa
- por
- deu
- ita
- rus
- jpn
- kor
- vie
- tha
- ara
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated/blob/main/LICENSE
quantized_by: mradermacher
tags:
- chat
- abliterated
- uncensored
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-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/Qwen2.5-7B-Instruct-abliterated-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated.Q2_K.gguf) | Q2_K | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated.IQ3_XS.gguf) | IQ3_XS | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated.IQ3_S.gguf) | IQ3_S | 3.6 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated.IQ3_M.gguf) | IQ3_M | 3.7 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated.Q5_K_S.gguf) | Q5_K_S | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated.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 -->
|
MJAEEEEE/gemma-medical-qa-finetune | MJAEEEEE | 2025-04-30T04:52:40Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"gemma",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-30T04:47:14Z | ---
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] |
ellietang/hf_saved_merged_ls-model-14B-full-CPT-v0.0.5-try2 | ellietang | 2025-04-30T04:24:21Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"sft",
"conversational",
"en",
"base_model:unsloth/Qwen2.5-Coder-14B-Instruct",
"base_model:finetune:unsloth/Qwen2.5-Coder-14B-Instruct",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-30T04:18:38Z | ---
base_model: unsloth/Qwen2.5-Coder-14B-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
- sft
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** ellietang
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen2.5-Coder-14B-Instruct
This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
Em3rzone/Em3rzone | Em3rzone | 2025-04-30T03:54:48Z | 0 | 0 | null | [
"license:artistic-2.0",
"region:us"
] | null | 2025-04-30T03:54:45Z | ---
license: artistic-2.0
---
|
OPEA/DeepSeek-R1-int4-AutoRound-awq-asym | OPEA | 2025-04-30T03:28:42Z | 80 | 2 | null | [
"safetensors",
"deepseek_v3",
"custom_code",
"dataset:NeelNanda/pile-10k",
"arxiv:2309.05516",
"base_model:deepseek-ai/DeepSeek-R1",
"base_model:quantized:deepseek-ai/DeepSeek-R1",
"4-bit",
"awq",
"region:us"
] | null | 2025-03-14T06:57:18Z | ---
datasets:
- NeelNanda/pile-10k
base_model:
- deepseek-ai/DeepSeek-R1
---
## Model Details
This model is an int4 model with group_size 64 and asymmetric quantization of [deepseek-ai/DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1) generated by [intel/auto-round](https://github.com/intel/auto-round) algorithm.
Please follow the license of the original model.
## How To Use
**INT4 VLLM Inference on CUDA**(**at least 8*80G**)
Please note that when using VLLM for inference, the quantization mode must be asymmetric. To serve using vLLM with 8x 80GB GPUs, use the following command:
```sh
VLLM_WORKER_MULTIPROC_METHOD=spawn python -m vllm.entrypoints.openai.api_server --host 0.0.0.0 --port 12345 --max-model-len 65536 --max-num-batched-tokens 65536 --trust-remote-code --tensor-parallel-size 8 --gpu-memory-utilization 0.97 --dtype float16 --served-model-name deepseek-reasoner --model OPEA/DeepSeek-R1-int4-asym-AutoRound-awq
```
You can download the wheel built by [cognitivecomputations](https://huggingface.co/cognitivecomputations) for PyTorch 2.6 and Python 3.12 by clicking [here](https://huggingface.co/x2ray/wheels/resolve/main/vllm-0.7.3.dev187%2Bg0ff1a4df.d20220101.cu126-cp312-cp312-linux_x86_64.whl).
~~~python
import requests
url = "http://localhost:12345/v1/chat/completions"
headers = {"Content-Type": "application/json"}
prompt="一个汉字具有左右结构，左边是木，右边是乞，这个字是什么字，只需要回答这个字即可。"
data = {
"model": "deepseek-reasoner",
"messages": [
{"role": "user", "content": prompt}
],
"max_tokens": 4096, # change this to align with offical usage
"top_p": 0.9, # change this to align with offical usage
"temperature": 0.6 # change this to align with offical usage
}
response = requests.post(url, json=data, headers=headers)
print(response.json()["choices"][0]["message"]["content"])
"""
prompt： 一个汉字具有左右结构，左边是木，右边是乞，这个字是什么字，只需要回答这个字即可。
<think>
嗯，用户问的是一个左右结构的汉字，左边是“木”，右边是“乞”。我需要先确定这个字到底是什么。首先，我应该回忆一下常见的左右结构的汉字，左边是木字旁的字有很多，比如“林”、“松”、“柏”
等，但右边是“乞”的可能比较少见。
首先，我可以考虑“木”加“乞”组合起来的可能性。可能这个字不是常用字，或者是某个生僻字。我需要检查一下自己的记忆，有没有学过或者见过这样的字。比如，“杞”字是木字旁右边一个“己”，所
右边是“己”而不是“乞”。而“札”字右边是“乚”，所以也不是。再比如“杚”，这个字可能比较少见，但它的右边是“乞”吗？
或者，可能用户写错了右边的部分，比如“气”而不是“乞”，但用户明确说是“乞”。这时候可能需要查证一下。如果右边确实是“乞”，那么可能的字是“杚”。这个字的读音是什么呢？我记得“杚”有两种
音，一种是gài，另一种是gè。当读gài时，同“槩”，也就是“概”的异体字，意思是量米粟时刮平斗斛用的木板；而读gè时，可能与“柯”有关，但不太确定。
不过，也有可能用户记错了结构，或者有其他可能性。比如，是否有其他木字旁加乞的字？或者是否是繁体字或异体字？比如“櫂”是木字旁右边比较复杂，但右边不是“乞”。再比如“栔”，右边是“契”
上半部分，但也不是“乞”。
再仔细想想，可能这个字是“杚”，也就是木字旁加乞，读音为gài或gè。不过，这个字在现代汉语中可能不常用，属于生僻字。需要确认一下是否正确。另外，用户可能是在某个特定的上下文或方言中
到这个字，所以需要给出正确的答案。
总结一下，可能的答案是“杚”，但需要确认是否正确。如果用户确认结构无误，那么这个字就是“杚”，尽管它不常见。所以最终的答案应该是“杚”。
</think>
杚
--------------------------------------------------
prompt="请用我给你的4个数字，通过加、减、乘、除、括号，组成一个运算，使得结果为24。注意：数字需要全部使用我提供的数字，4468"
<think>
嗯，我现在需要解决一个数学问题，就是用给定的四个数字4、4、6、8，通过加减乘除和括号组合起来得到24。首先，我得仔细想清楚怎么安排这些数字和运算符号。可能的话，先回忆一下常见的24
点游戏解法，可能会有帮助。
首先，我需要确定这四个数字的顺序和组合方式。因为有重复的数字，比如有两个4，所以可能需要更多的组合尝试。先考虑如何用这四个数中的某些数相乘或相除得到较大的数值，然后再调整剩下的
数来达到24。
比如，8和6这两个比较大的数，可能相乘的话是48，这样的话，剩下的两个4可能需要调整到48的一半，即24。不过这里有两个4，所以可能需要用除法或者减法。比如，48减去（4+4）=40，这样就不
行。或者48除以（4/4）=48，也不对。或者用8*6=48，然后4-4=0，这样48+0=48，也不行。
再想另一个方向，比如用4和4相乘得到16，再加上6和8的话，16+6+8=30，超过了24。或者16*（8-6）=32，也不对。或者（4*4）+6+8= 16+14=30，还是太大。
或者考虑用减法，比如8*4=32，然后32减去（6+4）=32-10=22，也不够。或者32-6-4=22，同样不行。
可能需要用除法来调整数值。比如，8除以（6-4）=4，这样再乘以剩下的4和另一个数？不过这样的话，可能不够。比如8/(6-4)=4，然后4*4=16，再加上6的话就超过了，不过这里可能重复用了6？或
者可能没正确使用所有数字。
再考虑另一种组合，比如（8-6）=2，然后4*4=16，再16*2=32，还是不行。或者（4+8）*（6-4）=12*2=24，这样用了4、8、6、4四个数字吗？是的，4+8=12，6-4=2，12*2=24，这样的话，确实用到了
所有的四个数字：4、8、6、4。所以这个组合可能可行？
不过，让我再检查一遍：4+8=12，6-4=2，然后12乘2等于24。是的，这样的话，四个数字都用到了，对吗？第一个4，第二个8，第三个6，第四个4。是的，刚好是4、4、6、8。所以这个解法是可行的
。
不过可能还有其他解法。比如，用6乘以（8 - (4/4)）。计算一下：4/4=1，8-1=7，6*7=42，不对。或者（6*8)/(4/4)=48/1=48，也不对。
或者（4*6）*(8/4)=24*2=48，同样不行。或者（4*8）-（6-4）=32-2=30，还是不行。
再试试其他组合，比如4*(6+8)/4。这里，6+8=14，4*14=56，56/4=14，不对。
或者，8*(6 - (4/4))：4/4=1，6-1=5，8*5=40，也不对。
或者，4*4*(8-6)=16*2=32，还是不够。
不过之前的那个解法（4+8）*(6-4)=12*2=24，确实可行。因此，这可能是一个正确的答案。不过需要确认是否所有的数字都被使用了一次，并且每个数字都只用了一次。这里，4被用了两次，而题目
中给出的数字是两个4，所以没问题。是的，正确使用了所有四个数字：4、4、6、8，每个数字都用了一次，没有重复使用也没有遗漏。
所以最终的表达式是（4 + 8）× (6 - 4) = 24。
</think>
使用数字4、4、6、8，可以通过以下运算得到24：
**运算步骤**：
(4 + 8) × (6 - 4) = 12 × 2 = 24
**验证**：
1. 使用所有数字：4、4、6、8（两个4均被使用）。
2. 通过加法和减法组合，最终结果为24。
3. 符合题目要求，仅使用加、减、乘、除和括号。
**答案**：
(4 + 8) × (6 - 4) = 24
--------------------------------------------------
prompt: How many e in word deepseek?
<think>
Okay, let's see. The question is asking how many times the letter "e" appears in the word "deepseek." Alright, first, I need to make sure I spell the word correctly. D-E-E-P-S-E-E-K. Let me break it down letter by letter.
Starting with the first letter: D. That's a D, not an E. Second letter: E. That's one. Third letter: E again. That's two. Fourth letter: P. Then S. Next is E. That's the third E. Then another E. Wait, let me check again. D-E-E-P-S-E-E-K. So after S, there's E, E, K. So that's E as the fifth letter, sixth letter, and then K. Wait, let me count the positions again to be sure.
1: D
2: E
3: E
4: P
5: S
6: E
7: E
8: K
So positions 2, 3, 6, 7 are E's. That makes four E's in total. Let me verify by writing the word out and underlining each E: D E E P S E E K. Yes, that's four E's. Wait, but sometimes people might miscount, especially if letters are repeated in sequence. Let me check again. The word is "deepseek." So "deep" has two E's, then "seek" has two E's as well. So deep (D-E-E-P) and seek (S-E-E-K). So 2 + 2 = 4. That makes sense. I think that's right. No, wait, "seek" is S-E-E-K, so two E's. So total of four E's. Yeah, that seems correct. I don't think I missed any. Let me write it again: D, E, E, P, S, E, E, K. Yep, four E's. So the answer should be 4.
</think>
The word "deepseek" contains the letter "e" four times. Here's the breakdown:
1. **D** - Not an "e"
2. **E** - First "e"
3. **E** - Second "e"
4. **P** - Not an "e"
5. **S** - Not an "e"
6. **E** - Third "e"
7. **E** - Fourth "e"
8. **K** - Not an "e"
**Answer:** There are **4** instances of the letter "e" in "deepseek".
"""
~~~
### INT4 Inference on CPU
Requirements
~~~bash
pip install auto-round
pip uninstall intel-extension-for-pytorch
pip install intel-extension-for-transformers
~~~
will update later
### Evaluate the model
pip3 install lm-eval==0.4.8
```bash
TORCH_DISTRIBUTED_DEBUG=INFO python -m lm_eval --model vllm --model_args "pretrained=OPEA/DeepSeek-R1-int4-AutoRound-awq-asym,tensor_parallel_size=8,dtype=bfloat16,max_model_len=65536,max_num_batched_tokens=65536,served_model_name=deepseek-reasoner" --batch_size 1 --device 'cuda'--trust_remote_code --tasks lambada_openai,hellaswag,piqa,winogrande,truthfulqa_mc1,boolq,arc_easy,arc_challenge,mmlu,openbookqa
```
| Metric | FP8 | INT4(BF16) |
| :------------------------ | :---------------------- | :--------------- |
| avg | 0.6954 | 0.6963 |
| mmlu | 0.8514 | 0.8485 |
| lambada_openai | 0.7902 | 0.7809 |
| hellaswag | 0.6935 | 0.6883 |
| winogrande | 0.7932 | 0.8011 |
| piqa | 0.8308 | 0.8292 |
| truthfulqa_mc1 | 0.4064 | 0.4051 |
| openbookqa | 0.3780 | 0.394 |
| boolq | 0.8856 | 0.8813 |
| arc_easy | 0.8598 | 0.8594 |
| arc_challenge | 0.6212 | 0.6271 |
### Generate the model
**1 add meta data to bf16 model** https://huggingface.co/opensourcerelease/DeepSeek-R1-bf16
~~~python
import safetensors
from safetensors.torch import save_file
for i in range(1, 164):
idx_str = "0" * (5-len(str(i))) + str(i)
safetensors_path = f"model-{idx_str}-of-000163.safetensors"
print(safetensors_path)
tensors = dict()
with safetensors.safe_open(safetensors_path, framework="pt") as f:
for key in f.keys():
tensors[key] = f.get_tensor(key)
save_file(tensors, safetensors_path, metadata={'format': 'pt'})
~~~
**2 remove torch.no_grad** in modeling_deepseek.py as we need some tuning in AutoRound.
~~~python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
import transformers
# https://github.com/huggingface/transformers/pull/35493
def set_initialized_submodules(model, state_dict_keys):
"""
Sets the `_is_hf_initialized` flag in all submodules of a given model when all its weights are in the loaded state
dict.
"""
state_dict_keys = set(state_dict_keys)
not_initialized_submodules = {}
for module_name, module in model.named_modules():
if module_name == "":
# When checking if the root module is loaded there's no need to prepend module_name.
module_keys = set(module.state_dict())
else:
module_keys = {f"{module_name}.{k}" for k in module.state_dict()}
if module_keys.issubset(state_dict_keys):
module._is_hf_initialized = True
else:
not_initialized_submodules[module_name] = module
return not_initialized_submodules
transformers.modeling_utils.set_initialized_submodules = set_initialized_submodules
model_name = "opensourcerelease/DeepSeek-R1-bf16"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, trust_remote_code=True, torch_dtype="auto")
block = model.model.layers
device_map = {}
for n, m in block.named_modules():
if isinstance(m, (torch.nn.Linear, transformers.modeling_utils.Conv1D)):
if "experts" in n and ("shared_experts" not in n) and int(n.split('.')[-2]) < 63:
device = "cuda:1"
elif "experts" in n and ("shared_experts" not in n) and int(n.split('.')[-2]) >= 63 and int(
n.split('.')[-2]) < 128:
device = "cuda:2"
elif "experts" in n and ("shared_experts" not in n) and int(n.split('.')[-2]) >= 128 and int(
n.split('.')[-2]) < 192:
device = "cuda:3"
elif "experts" in n and ("shared_experts" not in n) and int(
n.split('.')[-2]) >= 192:
device = "cuda:4"
else:
device = "cuda:0"
n = n[2:]
device_map.update({n: device})
from auto_round import AutoRound
autoround = AutoRound(model=model, tokenizer=tokenizer, device_map=device_map, nsamples=512,
batch_size=4, low_gpu_mem_usage=True, seqlen=2048, group_size=64, sym=False
)
autoround.quantize()
autoround.save_quantized(format="auto_awq", output_dir="tmp_autoround")
~~~
## Ethical Considerations and Limitations
The model can produce factually incorrect output, and should not be relied on to produce factually accurate information. Because of the limitations of the pretrained model and the finetuning datasets, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
Therefore, before deploying any applications of the model, developers should perform safety testing.
## Caveats and Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
Here are a couple of useful links to learn more about Intel's AI software:
- Intel Neural Compressor [link](https://github.com/intel/neural-compressor)
## Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please consult an attorney before using this model for commercial purposes.
## Cite
@article{cheng2023optimize, title={Optimize weight rounding via signed gradient descent for the quantization of llms}, author={Cheng, Wenhua and Zhang, Weiwei and Shen, Haihao and Cai, Yiyang and He, Xin and Lv, Kaokao and Liu, Yi}, journal={arXiv preprint arXiv:2309.05516}, year={2023} }
[arxiv](https://arxiv.org/abs/2309.05516) [github](https://github.com/intel/auto-round) |
steven6688/DrivingTest | steven6688 | 2025-04-30T03:25:30Z | 0 | 0 | null | [
"gguf",
"llama",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-04-30T02:55:04Z | ---
license: apache-2.0
---
|
SWE-bench/SWE-agent-LM-7B | SWE-bench | 2025-04-30T00:14:26Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2025-04-30T00:14:26Z | ---
license: apache-2.0
---
|
Knowtex-ai/Transcript | Knowtex-ai | 2025-04-29T23:00:06Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-04-29T22:59:58Z | ---
base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** Knowtex-ai
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
r2e-edits/qwen3-14b_end2end_sonnet_combined_maxstep40_sft-exitreason-agent-32k_bz8_epoch2_lr1en5-v1 | r2e-edits | 2025-04-29T21:53:16Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen3",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-29T21:39:27Z | ---
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] |
lunaSaif/SM | lunaSaif | 2025-04-29T21:41:23Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2025-04-29T21:40:13Z | ---
license: apache-2.0
---
|
InstaDeepAI/ChatNT | InstaDeepAI | 2025-04-29T21:24:07Z | 155 | 2 | transformers | [
"transformers",
"joblib",
"safetensors",
"ChatNT",
"feature-extraction",
"text-generation",
"custom_code",
"region:us"
] | text-generation | 2025-03-28T15:01:59Z | ---
library_name: transformers
pipeline_tag: text-generation
---
# ChatNT
[ChatNT](https://www.biorxiv.org/content/10.1101/2024.04.30.591835v1) is the first multimodal conversational agent designed with a deep understanding of biological sequences (DNA, RNA, proteins).
It enables users — even those with no coding background — to interact with biological data through natural language and it generalizes across multiple biological tasks and modalities.
**Developed by:** [InstaDeep](https://huggingface.co/InstaDeepAI)
### Model Sources
<!-- Provide the basic links for the model. -->
- **Repository:** [Nucleotide Transformer](https://github.com/instadeepai/nucleotide-transformer)
- **Paper:** [ChatNT: A Multimodal Conversational Agent for DNA, RNA and Protein Tasks](https://www.biorxiv.org/content/10.1101/2024.04.30.591835v1.full.pdf)
### License Summary
1. The Licensed Models are **only** available under this License for Non-Commercial Purposes.
2. You are permitted to reproduce, publish, share and adapt the Output generated by the Licensed Model only for Non-Commercial Purposes and in accordance with this License.
3. You may **not** use the Licensed Models or any of its Outputs in connection with:
1. any Commercial Purposes, unless agreed by Us under a separate licence;
2. to train, improve or otherwise influence the functionality or performance of any other third-party derivative model that is commercial or intended for a Commercial Purpose and is similar to the Licensed Models;
3. to create models distilled or derived from the Outputs of the Licensed Models, unless such models are for Non-Commercial Purposes and open-sourced under the same license as the Licensed Models; or
4. in violation of any applicable laws and regulations.
### Architecture and Parameters
ChatNT is built on a three‑module design: a 500M‑parameter [Nucleotide Transformer v2](https://www.nature.com/articles/s41592-024-02523-z) DNA encoder pre‑trained on genomes from 850 species
(handling up to 12 kb per sequence, Dalla‑Torre et al., 2024), an English‑aware Perceiver Resampler that linearly projects and gated‑attention compresses
2048 DNA‑token embeddings into 64 task‑conditioned vectors (REF), and a frozen 7B‑parameter [Vicuna‑7B](https://lmsys.org/blog/2023-03-30-vicuna/) decoder.
Users provide a natural‑language prompt containing one or more `<DNA>` placeholders and the corresponding DNA sequences (tokenized as 6‑mers).
The projection layer inserts 64 resampled DNA embeddings at each placeholder, and the Vicuna decoder generates free‑form English responses in
an autoregressive fashion, using low‑temperature sampling to produce classification labels, multi‑label statements, or numeric values.
### Training Data
ChatNT was instruction‑tuned on a unified corpus covering 27 diverse tasks from DNA, RNA and proteins, spanning multiple species, tissues and biological processes.
This amounted to 605 million DNA tokens (≈ 3.6 billion bases) and 273 million English tokens, sampled uniformly over tasks for 2 billion instruction tokens.
Examples of questions and sequences for each task, as well as additional task information, can be found in [Datasets_overview.csv](Datasets_overview.csv).
### Tokenization
DNA inputs are broken into overlapping 6‑mer tokens and padded or truncated to 2048 tokens (~ 12 kb). English prompts and
outputs use the LLaMA tokenizer, augmented with `<DNA>` as a special token to mark sequence insertion points.
### Limitations and Disclaimer
ChatNT can only handle questions related to the 27 tasks it has been trained on, including the same format of DNA sequences. ChatNT is **not** a clinical or diagnostic tool.
It can produce incorrect or “hallucinated” answers, particularly on out‑of‑distribution inputs, and its numeric predictions may suffer digit‑level errors. Confidence
estimates require post‑hoc calibration. Users should always validate critical outputs against experiments or specialized bioinformatics
pipelines.
### Other notes
We also provide the params for the ChatNT jax model in `jax_params`.
## How to use
Until its next release, the transformers library needs to be installed from source with the following command in order to use the models.
PyTorch should also be installed.
```
pip install --upgrade git+https://github.com/huggingface/transformers.git
pip install torch sentencepiece
```
A small snippet of code is given here in order to **generate ChatNT answers from a pipeline (high-level)**.
- The prompt used for training ChatNT is already incorporated inside the pipeline and is the following:
"A chat between a curious user and an artificial intelligence assistant that can handle bio sequences. The assistant gives helpful,
detailed, and polite answers to the user's questions."
```
# Load pipeline
from transformers import pipeline
pipe = pipeline(model="InstaDeepAI/ChatNT", trust_remote_code=True)
# Define custom inputs (note that the number of <DNA> token in the english sequence must be equal to len(dna_sequences))
english_sequence = "Is there any evidence of an acceptor splice site in this sequence <DNA> ?"
dna_sequences = ["ATCGGAAAAAGATCCAGAAAGTTATACCAGGCCAATGGGAATCACCTATTACGTGGATAATAGCGATAGTATGTTACCTATAAATTTAACTACGTGGATATCAGGCAGTTACGTTACCAGTCAAGGAGCACCCAAAACTGTCCAGCAACAAGTTAATTTACCCATGAAGATGTACTGCAAGCCTTGCCAACCAGTTAAAGTAGCTACTCATAAGGTAATAAACAGTAATATCGACTTTTTATCCATTTTGATAATTGATTTATAACAGTCTATAACTGATCGCTCTACATAATCTCTATCAGATTACTATTGACACAAACAGAAACCCCGTTAATTTGTATGATATATTTCCCGGTAAGCTTCGATTTTTAATCCTATCGTGACAATTTGGAATGTAACTTATTTCGTATAGGATAAACTAATTTACACGTTTGAATTCCTAGAATATGGAGAATCTAAAGGTCCTGGCAATGCCATCGGCTTTCAATATTATAATGGACCAAAAGTTACTCTATTAGCTTCCAAAACTTCGCGTGAGTACATTAGAACAGAAGAATAACCTTCAATATCGAGAGAGTTACTATCACTAACTATCCTATG"]
# Generate sequence
generated_english_sequence = pipe(
inputs={
"english_sequence": english_sequence,
"dna_sequences": dna_sequences
}
)
# Expected output: "Yes, an acceptor splice site is without question present in the sequence."
```
A small snippet of code is given here in order to **infer with the model without any abstraction (low-level)**.
```
import numpy as np
from transformers import AutoModel, AutoTokenizer
# Load model and tokenizers
model = AutoModel.from_pretrained("InstaDeepAI/ChatNT", trust_remote_code=True)
english_tokenizer = AutoTokenizer.from_pretrained("InstaDeepAI/ChatNT", subfolder="english_tokenizer")
bio_tokenizer = AutoTokenizer.from_pretrained("InstaDeepAI/ChatNT", subfolder="bio_tokenizer")
# Define custom inputs (note that the number of <DNA> token in the english sequence must be equal to len(dna_sequences))
# Here the english sequence should include the prompt
english_sequence = "A chat between a curious user and an artificial intelligence assistant that can handle bio sequences. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Is there any evidence of an acceptor splice site in this sequence <DNA> ?"
dna_sequences = ["ATCGGAAAAAGATCCAGAAAGTTATACCAGGCCAATGGGAATCACCTATTACGTGGATAATAGCGATAGTATGTTACCTATAAATTTAACTACGTGGATATCAGGCAGTTACGTTACCAGTCAAGGAGCACCCAAAACTGTCCAGCAACAAGTTAATTTACCCATGAAGATGTACTGCAAGCCTTGCCAACCAGTTAAAGTAGCTACTCATAAGGTAATAAACAGTAATATCGACTTTTTATCCATTTTGATAATTGATTTATAACAGTCTATAACTGATCGCTCTACATAATCTCTATCAGATTACTATTGACACAAACAGAAACCCCGTTAATTTGTATGATATATTTCCCGGTAAGCTTCGATTTTTAATCCTATCGTGACAATTTGGAATGTAACTTATTTCGTATAGGATAAACTAATTTACACGTTTGAATTCCTAGAATATGGAGAATCTAAAGGTCCTGGCAATGCCATCGGCTTTCAATATTATAATGGACCAAAAGTTACTCTATTAGCTTCCAAAACTTCGCGTGAGTACATTAGAACAGAAGAATAACCTTCAATATCGAGAGAGTTACTATCACTAACTATCCTATG"]
# Tokenize
english_tokens = english_tokenizer(english_sequence, return_tensors="pt", padding="max_length", truncation=True, max_length=512).input_ids
bio_tokens = bio_tokenizer(dna_sequences, return_tensors="pt", padding="max_length", max_length=512, truncation=True).input_ids.unsqueeze(0) # unsqueeze to simulate batch_size = 1
# Predict
outs = model(
multi_omics_tokens_ids=(english_tokens, bio_tokens),
projection_english_tokens_ids=english_tokens,
projected_bio_embeddings=None,
)
# Expected output: Dictionary of logits and projected_bio_embeddings
``` |
mradermacher/SIM-RAG-GPT4-2B-GGUF | mradermacher | 2025-04-29T21:13:20Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:dyang39/SIM-RAG-GPT4-2B",
"base_model:quantized:dyang39/SIM-RAG-GPT4-2B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-04-29T20:53:35Z | ---
base_model: dyang39/SIM-RAG-GPT4-2B
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/dyang39/SIM-RAG-GPT4-2B
<!-- 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/SIM-RAG-GPT4-2B-GGUF/resolve/main/SIM-RAG-GPT4-2B.Q2_K.gguf) | Q2_K | 1.2 | |
| [GGUF](https://huggingface.co/mradermacher/SIM-RAG-GPT4-2B-GGUF/resolve/main/SIM-RAG-GPT4-2B.Q3_K_S.gguf) | Q3_K_S | 1.4 | |
| [GGUF](https://huggingface.co/mradermacher/SIM-RAG-GPT4-2B-GGUF/resolve/main/SIM-RAG-GPT4-2B.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/SIM-RAG-GPT4-2B-GGUF/resolve/main/SIM-RAG-GPT4-2B.Q3_K_L.gguf) | Q3_K_L | 1.6 | |
| [GGUF](https://huggingface.co/mradermacher/SIM-RAG-GPT4-2B-GGUF/resolve/main/SIM-RAG-GPT4-2B.IQ4_XS.gguf) | IQ4_XS | 1.6 | |
| [GGUF](https://huggingface.co/mradermacher/SIM-RAG-GPT4-2B-GGUF/resolve/main/SIM-RAG-GPT4-2B.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/SIM-RAG-GPT4-2B-GGUF/resolve/main/SIM-RAG-GPT4-2B.Q4_K_M.gguf) | Q4_K_M | 1.9 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/SIM-RAG-GPT4-2B-GGUF/resolve/main/SIM-RAG-GPT4-2B.Q5_K_S.gguf) | Q5_K_S | 2.1 | |
| [GGUF](https://huggingface.co/mradermacher/SIM-RAG-GPT4-2B-GGUF/resolve/main/SIM-RAG-GPT4-2B.Q5_K_M.gguf) | Q5_K_M | 2.1 | |
| [GGUF](https://huggingface.co/mradermacher/SIM-RAG-GPT4-2B-GGUF/resolve/main/SIM-RAG-GPT4-2B.Q6_K.gguf) | Q6_K | 2.4 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/SIM-RAG-GPT4-2B-GGUF/resolve/main/SIM-RAG-GPT4-2B.Q8_0.gguf) | Q8_0 | 3.1 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/SIM-RAG-GPT4-2B-GGUF/resolve/main/SIM-RAG-GPT4-2B.f16.gguf) | f16 | 5.8 | 16 bpw, overkill |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
ffront/spoiled_embedings_model | ffront | 2025-04-29T19:19:18Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:ffront/emotion-classifier_v2",
"base_model:finetune:ffront/emotion-classifier_v2",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2025-04-29T19:18:12Z | ---
library_name: transformers
license: apache-2.0
base_model: ffront/emotion-classifier_v2
tags:
- generated_from_trainer
model-index:
- name: spoiled_embedings_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# spoiled_embedings_model
This model is a fine-tuned version of [ffront/emotion-classifier_v2](https://huggingface.co/ffront/emotion-classifier_v2) 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: 2e-05
- train_batch_size: 32
- eval_batch_size: 64
- 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
- num_epochs: 1
### Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Tokenizers 0.21.1
|
jinx2321/base-1e4-paper | jinx2321 | 2025-04-29T18:12:44Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"t5",
"text2text-generation",
"generated_from_trainer",
"base_model:everdoubling/byt5-Korean-base",
"base_model:finetune:everdoubling/byt5-Korean-base",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | 2025-04-29T07:17:29Z | ---
library_name: transformers
license: apache-2.0
base_model: everdoubling/byt5-Korean-base
tags:
- generated_from_trainer
model-index:
- name: base-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. -->
# base-1e4-paper
This model is a fine-tuned version of [everdoubling/byt5-Korean-base](https://huggingface.co/everdoubling/byt5-Korean-base) 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
|
Teeranon/Mindtre-vllm | Teeranon | 2025-04-29T17:55:50Z | 0 | 0 | transformers | [
"transformers",
"gemma3_text",
"text-generation",
"text-generation-inference",
"unsloth",
"gemma3",
"conversational",
"th",
"base_model:unsloth/gemma-3-4b-it-unsloth-bnb-4bit",
"base_model:finetune:unsloth/gemma-3-4b-it-unsloth-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-29T17:47:26Z | ---
base_model: unsloth/gemma-3-4b-it-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- gemma3
license: apache-2.0
language:
- th
---
|
Ghazi-nak/5_BiasDetctor_HTW_ANG.KI | Ghazi-nak | 2025-04-29T17:35:29Z | 0 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"roberta",
"text-classification",
"generated_from_trainer",
"base_model:FacebookAI/roberta-large",
"base_model:finetune:FacebookAI/roberta-large",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2025-04-29T17:28:28Z | ---
library_name: transformers
license: mit
base_model: roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: 5_BiasDetctor_HTW_ANG.KI
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. -->
# 5_BiasDetctor_HTW_ANG.KI
This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6177
- Accuracy: 0.9114
- F1: 0.9116
- Precision: 0.9122
- Recall: 0.9114
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 300
- num_epochs: 7
- label_smoothing_factor: 0.1
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.962 | 0.2 | 250 | 0.8191 | 0.7846 | 0.7854 | 0.8076 | 0.7846 |
| 0.7921 | 0.4 | 500 | 0.7972 | 0.7982 | 0.8029 | 0.8436 | 0.7982 |
| 0.7592 | 0.6 | 750 | 0.6858 | 0.8614 | 0.8625 | 0.8748 | 0.8614 |
| 0.701 | 0.8 | 1000 | 0.6871 | 0.8666 | 0.8673 | 0.8731 | 0.8666 |
| 0.6595 | 1.0 | 1250 | 0.6236 | 0.8888 | 0.8895 | 0.8921 | 0.8888 |
| 0.5826 | 1.2 | 1500 | 0.6629 | 0.8898 | 0.8909 | 0.8952 | 0.8898 |
| 0.5983 | 1.4 | 1750 | 0.6282 | 0.8934 | 0.8933 | 0.8942 | 0.8934 |
| 0.594 | 1.6 | 2000 | 0.6249 | 0.894 | 0.8944 | 0.8956 | 0.894 |
| 0.6477 | 1.8 | 2250 | 0.6045 | 0.9014 | 0.9020 | 0.9034 | 0.9014 |
| 0.5968 | 2.0 | 2500 | 0.6189 | 0.8962 | 0.8964 | 0.8971 | 0.8962 |
| 0.5291 | 2.2 | 2750 | 0.6177 | 0.9114 | 0.9116 | 0.9122 | 0.9114 |
| 0.5225 | 2.4 | 3000 | 0.6260 | 0.9078 | 0.9080 | 0.9103 | 0.9078 |
| 0.5286 | 2.6 | 3250 | 0.6468 | 0.8978 | 0.8976 | 0.9004 | 0.8978 |
### Framework versions
- Transformers 4.51.3
- Pytorch 2.1.2
- Datasets 3.5.1
- Tokenizers 0.21.1
### training metrics:
TrainOutput(global_step=3250, training_loss=0.6634712289663461, metrics={'train_runtime': 728.1708, 'train_samples_per_second': 192.263, 'train_steps_per_second': 12.016, 'total_flos': 1.2115230526464e+16, 'train_loss': 0.6634712289663461, 'epoch': 2.6})
|
MinaMila/llama_instbase_3b_unlearned_epoch4 | MinaMila | 2025-04-29T17:33:16Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-29T17:30:32Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
nhe-ai/Llasa-1B-Multilingual-mlx-8Bit | nhe-ai | 2025-04-29T16:43:10Z | 0 | 0 | mlx | [
"mlx",
"safetensors",
"llama",
"Text-to-Speech",
"mlx-my-repo",
"text-to-speech",
"zh",
"en",
"de",
"fr",
"ja",
"ko",
"nl",
"es",
"it",
"pt",
"pl",
"base_model:HKUSTAudio/Llasa-1B-Multilingual",
"base_model:quantized:HKUSTAudio/Llasa-1B-Multilingual",
"license:cc-by-nc-4.0",
"8-bit",
"region:us"
] | text-to-speech | 2025-04-29T13:53:26Z | ---
license: cc-by-nc-4.0
language:
- zh
- en
- de
- fr
- ja
- ko
- nl
- es
- it
- pt
- pl
base_model: HKUSTAudio/Llasa-1B-Multilingual
tags:
- Text-to-Speech
- mlx
- mlx-my-repo
pipeline_tag: text-to-speech
---
# nhe-ai/Llasa-1B-Multilingual-mlx-8Bit
The Model [nhe-ai/Llasa-1B-Multilingual-mlx-8Bit](https://huggingface.co/nhe-ai/Llasa-1B-Multilingual-mlx-8Bit) was converted to MLX format from [HKUSTAudio/Llasa-1B-Multilingual](https://huggingface.co/HKUSTAudio/Llasa-1B-Multilingual) using mlx-lm version **0.22.3**.
⚠️ Important: This model was automatically converted for experimentation. The following guide was not designed for this model and may not work as expected. Do not expect to function out of the box. Use at your own experimentation.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("nhe-ai/Llasa-1B-Multilingual-mlx-8Bit")
prompt="hello"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
```
|
lfhe/FLock-Arena-Task-8-Qwen3-1.7B | lfhe | 2025-04-29T16:42:56Z | 0 | 0 | peft | [
"peft",
"safetensors",
"arxiv:1910.09700",
"base_model:Qwen/Qwen3-1.7B",
"base_model:adapter:Qwen/Qwen3-1.7B",
"region:us"
] | null | 2025-04-29T15:12:07Z | ---
base_model: Qwen/Qwen3-1.7B
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 0.13.2 |
chenggong1995/Qwen-2.5-Base-7B-gen8-math3to5_olympiads_aime-ghpo-cold10-hint0.5-prompt1-dp | chenggong1995 | 2025-04-29T16:18:36Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"open-r1",
"trl",
"grpo",
"dataset:chenggong1995/math3to5_olympiads_aime",
"arxiv:2402.03300",
"base_model:Qwen/Qwen2.5-7B",
"base_model:finetune:Qwen/Qwen2.5-7B",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-29T08:27:20Z | ---
base_model: Qwen/Qwen2.5-7B
datasets: chenggong1995/math3to5_olympiads_aime
library_name: transformers
model_name: Qwen-2.5-Base-7B-gen8-math3to5_olympiads_aime-ghpo-cold10-hint0.5-prompt1-dp
tags:
- generated_from_trainer
- open-r1
- trl
- grpo
licence: license
---
# Model Card for Qwen-2.5-Base-7B-gen8-math3to5_olympiads_aime-ghpo-cold10-hint0.5-prompt1-dp
This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the [chenggong1995/math3to5_olympiads_aime](https://huggingface.co/datasets/chenggong1995/math3to5_olympiads_aime) dataset.
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="chenggong1995/Qwen-2.5-Base-7B-gen8-math3to5_olympiads_aime-ghpo-cold10-hint0.5-prompt1-dp", 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/gongc1995-city-university-of-hong-kong/huggingface/runs/71upmpjr)
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
### Framework versions
- TRL: 0.18.0.dev0
- Transformers: 4.52.0.dev0
- Pytorch: 2.6.0
- Datasets: 3.5.0
- Tokenizers: 0.21.1
## Citations
Cite GRPO as:
```bibtex
@article{zhihong2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
nkasmanoff/jupyter-pilot-F16-GGUF | nkasmanoff | 2025-04-29T16:08:15Z | 25 | 0 | transformers | [
"transformers",
"gguf",
"text-generation-inference",
"unsloth",
"qwen2",
"trl",
"llama-cpp",
"gguf-my-lora",
"en",
"base_model:nkasmanoff/jupyter-pilot",
"base_model:quantized:nkasmanoff/jupyter-pilot",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-04-26T19:53:32Z | ---
base_model: nkasmanoff/jupyter-pilot
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
- llama-cpp
- gguf-my-lora
license: apache-2.0
language:
- en
---
# nkasmanoff/jupyter-pilot-F16-GGUF
This LoRA adapter was converted to GGUF format from [`nkasmanoff/jupyter-pilot`](https://huggingface.co/nkasmanoff/jupyter-pilot) via the ggml.ai's [GGUF-my-lora](https://huggingface.co/spaces/ggml-org/gguf-my-lora) space.
Refer to the [original adapter repository](https://huggingface.co/nkasmanoff/jupyter-pilot) for more details.
## Use with llama.cpp
```bash
# with cli
llama-cli -m base_model.gguf --lora jupyter-pilot-f16.gguf (...other args)
# with server
llama-server -m base_model.gguf --lora jupyter-pilot-f16.gguf (...other args)
```
To know more about LoRA usage with llama.cpp server, refer to the [llama.cpp server documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/server/README.md).
|
biruemuk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-scurrying_poisonous_porpoise | biruemuk | 2025-04-29T15:20:38Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"rl-swarm",
"grpo",
"gensyn",
"I am scurrying poisonous porpoise",
"trl",
"conversational",
"arxiv:2402.03300",
"base_model:Gensyn/Qwen2.5-0.5B-Instruct",
"base_model:finetune:Gensyn/Qwen2.5-0.5B-Instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-26T21:50:17Z | ---
base_model: Gensyn/Qwen2.5-0.5B-Instruct
library_name: transformers
model_name: Qwen2.5-0.5B-Instruct-Gensyn-Swarm-scurrying_poisonous_porpoise
tags:
- generated_from_trainer
- rl-swarm
- grpo
- gensyn
- I am scurrying poisonous porpoise
- trl
licence: license
---
# Model Card for Qwen2.5-0.5B-Instruct-Gensyn-Swarm-scurrying_poisonous_porpoise
This model is a fine-tuned version of [Gensyn/Qwen2.5-0.5B-Instruct](https://huggingface.co/Gensyn/Qwen2.5-0.5B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="biruemuk/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-scurrying_poisonous_porpoise", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
### Framework versions
- TRL: 0.15.2
- Transformers: 4.51.3
- Pytorch: 2.5.1
- Datasets: 3.5.0
- Tokenizers: 0.21.1
## Citations
Cite GRPO as:
```bibtex
@article{zhihong2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
Airman101/Chaos | Airman101 | 2025-04-29T15:13:40Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2025-04-29T15:13:40Z | ---
license: apache-2.0
---
|
SkyCats/Qwen2.5-VL-7B-Instruct-bnb-4bit-image_caption | SkyCats | 2025-04-29T14:12:59Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen2_5_vl",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-04-18T14:23:24Z | ---
base_model: unsloth/qwen2.5-vl-7b-instruct-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2_5_vl
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** SkyCats
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen2.5-vl-7b-instruct-bnb-4bit
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)
|
grimjim/Magnolia-v3b-12B-GGUF | grimjim | 2025-04-29T04:41:09Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"mergekit",
"merge",
"GGUF",
"text-generation",
"base_model:grimjim/Magnolia-v3b-12B",
"base_model:quantized:grimjim/Magnolia-v3b-12B",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-28T21:24:22Z | ---
base_model: grimjim/Magnolia-v3b-12B
base_model_relation: quantized
quanted_by: grimjim
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
tags:
- mergekit
- merge
- GGUF
---
# Magnolia-v3b-12B-GGUF
This repo is a set of GGUF quants of a [grimjim/Magnolia-v3b-12B](https://huggingface.co/grimjim/Magnolia-v3b-12B), a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
[llama.cpp](https://github.com/ggerganov/llama.cpp/) was used to make the following quants:
- [Q4_0](Magnolia-v3b-12B.Q4_0.gguf)
- [Q4_K_M](Magnolia-v3b-12B.Q4_K_M.gguf)
- [Q5_K_M](Magnolia-v3b-12B.Q5_K_M.gguf)
- [Q6_K](Magnolia-v3b-12B.Q6_K.gguf)
- [Q8_0](Magnolia-v3b-12B.Q8_0.gguf)
|
ErFer7/LLaDerm | ErFer7 | 2025-04-29T04:32:17Z | 3 | 1 | transformers | [
"transformers",
"safetensors",
"mllama",
"image-text-to-text",
"text-generation-inference",
"unsloth",
"conversational",
"en",
"base_model:unsloth/Llama-3.2-11B-Vision-Instruct",
"base_model:finetune:unsloth/Llama-3.2-11B-Vision-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | image-text-to-text | 2024-12-16T23:36:24Z | ---
base_model: unsloth/Llama-3.2-11B-Vision-Instruct
tags:
- text-generation-inference
- transformers
- unsloth
- mllama
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** ErFer7
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Llama-3.2-11B-Vision-Instruct
This mllama 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/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF | mradermacher | 2025-04-29T04:10:24Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama-factory",
"full",
"generated_from_trainer",
"en",
"base_model:mlfoundations-dev/d1_science_all_large",
"base_model:quantized:mlfoundations-dev/d1_science_all_large",
"license:other",
"endpoints_compatible",
"region:us",
"imatrix",
"conversational"
] | null | 2025-04-28T22:59:04Z | ---
base_model: mlfoundations-dev/d1_science_all_large
language:
- en
library_name: transformers
license: other
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/mlfoundations-dev/d1_science_all_large
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-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/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct_d1_science_all_large-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct_d1_science_all_large.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 -->
|
cherryDavid/Qwen3-1.7B-Q4_K_M-GGUF | cherryDavid | 2025-04-29T02:35:02Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"base_model:Qwen/Qwen3-1.7B",
"base_model:quantized:Qwen/Qwen3-1.7B",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2025-04-29T02:34:54Z | ---
base_model: Qwen/Qwen3-1.7B
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3-1.7B/blob/main/LICENSE
pipeline_tag: text-generation
tags:
- llama-cpp
- gguf-my-repo
---
# cherryDavid/Qwen3-1.7B-Q4_K_M-GGUF
This model was converted to GGUF format from [`Qwen/Qwen3-1.7B`](https://huggingface.co/Qwen/Qwen3-1.7B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Qwen/Qwen3-1.7B) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo cherryDavid/Qwen3-1.7B-Q4_K_M-GGUF --hf-file qwen3-1.7b-q4_k_m.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo cherryDavid/Qwen3-1.7B-Q4_K_M-GGUF --hf-file qwen3-1.7b-q4_k_m.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo cherryDavid/Qwen3-1.7B-Q4_K_M-GGUF --hf-file qwen3-1.7b-q4_k_m.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo cherryDavid/Qwen3-1.7B-Q4_K_M-GGUF --hf-file qwen3-1.7b-q4_k_m.gguf -c 2048
```
|
iamwille/wav2vec2-base-igbo-demo | iamwille | 2025-04-29T02:04:19Z | 0 | 0 | transformers | [
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-04-29T00:22:55Z | ---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
Lucy-in-the-Sky/Qwen2.5-0.5B-Instruct-Q8_0-GGUF | Lucy-in-the-Sky | 2025-04-29T01:22:06Z | 3 | 0 | transformers | [
"transformers",
"gguf",
"chat",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"zho",
"eng",
"fra",
"spa",
"por",
"deu",
"ita",
"rus",
"jpn",
"kor",
"vie",
"tha",
"ara",
"base_model:Qwen/Qwen2.5-0.5B-Instruct",
"base_model:quantized:Qwen/Qwen2.5-0.5B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2025-02-06T17:11:09Z | ---
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct/blob/main/LICENSE
language:
- zho
- eng
- fra
- spa
- por
- deu
- ita
- rus
- jpn
- kor
- vie
- tha
- ara
pipeline_tag: text-generation
base_model: Qwen/Qwen2.5-0.5B-Instruct
tags:
- chat
- llama-cpp
- gguf-my-repo
library_name: transformers
---
# Lucy-in-the-Sky/Qwen2.5-0.5B-Instruct-Q8_0-GGUF
This model was converted to GGUF format from [`Qwen/Qwen2.5-0.5B-Instruct`](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Lucy-in-the-Sky/Qwen2.5-0.5B-Instruct-Q8_0-GGUF --hf-file qwen2.5-0.5b-instruct-q8_0.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Lucy-in-the-Sky/Qwen2.5-0.5B-Instruct-Q8_0-GGUF --hf-file qwen2.5-0.5b-instruct-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 Lucy-in-the-Sky/Qwen2.5-0.5B-Instruct-Q8_0-GGUF --hf-file qwen2.5-0.5b-instruct-q8_0.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Lucy-in-the-Sky/Qwen2.5-0.5B-Instruct-Q8_0-GGUF --hf-file qwen2.5-0.5b-instruct-q8_0.gguf -c 2048
```
|
fhaslam/Llama-3.2-1B-Financial-Sentiment24 | fhaslam | 2025-04-28T22:08:21Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"facebook",
"meta",
"pytorch",
"llama",
"llama-3",
"text-generation",
"conversational",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"arxiv:2204.05149",
"arxiv:2405.16406",
"license:llama3.2",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-28T22:08:05Z | ---
language:
- en
- de
- fr
- it
- pt
- hi
- es
- th
library_name: transformers
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
license: llama3.2
extra_gated_prompt: >-
### LLAMA 3.2 COMMUNITY LICENSE AGREEMENT
Llama 3.2 Version Release Date: September 25, 2024
“Agreement” means the terms and conditions for use, reproduction, distribution
and modification of the Llama Materials set forth herein.
“Documentation” means the specifications, manuals and documentation accompanying Llama 3.2
distributed by Meta at https://llama.meta.com/doc/overview.
“Licensee” or “you” means you, or your employer or any other person or entity (if you are
entering into this Agreement on such person or entity’s behalf), of the age required under
applicable laws, rules or regulations to provide legal consent and that has legal authority
to bind your employer or such other person or entity if you are entering in this Agreement
on their behalf.
“Llama 3.2” means the foundational large language models and software and algorithms, including
machine-learning model code, trained model weights, inference-enabling code, training-enabling code,
fine-tuning enabling code and other elements of the foregoing distributed by Meta at
https://www.llama.com/llama-downloads.
“Llama Materials” means, collectively, Meta’s proprietary Llama 3.2 and Documentation (and
any portion thereof) made available under this Agreement.
“Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or,
if you are an entity, your principal place of business is in the EEA or Switzerland)
and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).
By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials,
you agree to be bound by this Agreement.
1. License Rights and Redistribution.
a. Grant of Rights. You are granted a non-exclusive, worldwide,
non-transferable and royalty-free limited license under Meta’s intellectual property or other rights
owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works
of, and make modifications to the Llama Materials.
b. Redistribution and Use.
i. If you distribute or make available the Llama Materials (or any derivative works thereof),
or a product or service (including another AI model) that contains any of them, you shall (A) provide
a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama”
on a related website, user interface, blogpost, about page, or product documentation. If you use the
Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or
otherwise improve an AI model, which is distributed or made available, you shall also include “Llama”
at the beginning of any such AI model name.
ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part
of an integrated end user product, then Section 2 of this Agreement will not apply to you.
iii. You must retain in all copies of the Llama Materials that you distribute the
following attribution notice within a “Notice” text file distributed as a part of such copies:
“Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms,
Inc. All Rights Reserved.”
iv. Your use of the Llama Materials must comply with applicable laws and regulations
(including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for
the Llama Materials (available at https://www.llama.com/llama3_2/use-policy), which is hereby
incorporated by reference into this Agreement.
2. Additional Commercial Terms. If, on the Llama 3.2 version release date, the monthly active users
of the products or services made available by or for Licensee, or Licensee’s affiliates,
is greater than 700 million monthly active users in the preceding calendar month, you must request
a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to
exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND
RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS
ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES
OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE
FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED
WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY,
WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT,
FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN
IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
5. Intellectual Property.
a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials,
neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates,
except as required for reasonable and customary use in describing and redistributing the Llama Materials or as
set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required
to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible
at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark
will inure to the benefit of Meta.
b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any
derivative works and modifications of the Llama Materials that are made by you, as between you and Meta,
you are and will be the owner of such derivative works and modifications.
c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or
counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion
of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable
by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or
claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third
party arising out of or related to your use or distribution of the Llama Materials.
6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access
to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms
and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this
Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3,
4 and 7 shall survive the termination of this Agreement.
7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of
California without regard to choice of law principles, and the UN Convention on Contracts for the International
Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of
any dispute arising out of this Agreement.
### Llama 3.2 Acceptable Use Policy
Meta is committed to promoting safe and fair use of its tools and features, including Llama 3.2.
If you access or use Llama 3.2, you agree to this Acceptable Use Policy (“**Policy**”).
The most recent copy of this policy can be found at
[https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).
#### Prohibited Uses
We want everyone to use Llama 3.2 safely and responsibly. You agree you will not use, or allow others to use, Llama 3.2 to:
1. Violate the law or others’ rights, including to:
1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
1. Violence or terrorism
2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
3. Human trafficking, exploitation, and sexual violence
4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
5. Sexual solicitation
6. Any other criminal activity
1. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
2. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
3. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
4. Collect, process, disclose, generate, or infer private or sensitive information about individuals, including information about individuals’ identity, health, or demographic information, unless you have obtained the right to do so in accordance with applicable law
5. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
6. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
7. Engage in any action, or facilitate any action, to intentionally circumvent or remove usage restrictions or other safety measures, or to enable functionality disabled by Meta
2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 3.2 related to the following:
8. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons Convention Implementation Act of 1997
9. Guns and illegal weapons (including weapon development)
10. Illegal drugs and regulated/controlled substances
11. Operation of critical infrastructure, transportation technologies, or heavy machinery
12. Self-harm or harm to others, including suicide, cutting, and eating disorders
13. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
3. Intentionally deceive or mislead others, including use of Llama 3.2 related to the following:
14. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
15. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
16. Generating, promoting, or further distributing spam
17. Impersonating another individual without consent, authorization, or legal right
18. Representing that the use of Llama 3.2 or outputs are human-generated
19. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement
4. Fail to appropriately disclose to end users any known dangers of your AI system
5. Interact with third party tools, models, or software designed to generate unlawful content or engage in unlawful or harmful conduct and/or represent that the outputs of such tools, models, or software are associated with Meta or Llama 3.2
With respect to any multimodal models included in Llama 3.2, the rights granted under Section 1(a) of the Llama 3.2 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models.
Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
* Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)
* Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
* Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama 3.2: [email protected]
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
Job title:
type: select
options:
- Student
- Research Graduate
- AI researcher
- AI developer/engineer
- Reporter
- Other
geo: ip_location
By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox
extra_gated_description: >-
The information you provide will be collected, stored, processed and shared in
accordance with the [Meta Privacy
Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
---
## Model Information
The Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open source and closed chat models on common industry benchmarks.
**Model Developer:** Meta
**Model Architecture:** Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
| | Training Data | Params | Input modalities | Output modalities | Context Length | GQA | Shared Embeddings | Token count | Knowledge cutoff |
| :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- |
| Llama 3.2 (text only) | A new mix of publicly available online data. | 1B (1.23B) | Multilingual Text | Multilingual Text and code | 128k | Yes | Yes | Up to 9T tokens | December 2023 |
| | | 3B (3.21B) | Multilingual Text | Multilingual Text and code | | | | | |
| Llama 3.2 Quantized (text only) | A new mix of publicly available online data. | 1B (1.23B) | Multilingual Text | Multilingual Text and code | 8k | Yes | Yes | Up to 9T tokens | December 2023 |
| | | 3B (3.21B) | Multilingual Text | Multilingual Text and code | | | | | |
**Supported Languages:** English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai are officially supported. Llama 3.2 has been trained on a broader collection of languages than these 8 supported languages. Developers may fine-tune Llama 3.2 models for languages beyond these supported languages, provided they comply with the Llama 3.2 Community License and the Acceptable Use Policy. Developers are always expected to ensure that their deployments, including those that involve additional languages, are completed safely and responsibly.
**Llama 3.2 Model Family:** Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date:** Sept 25, 2024
**Status:** This is a static model trained on an offline dataset. Future versions may be released that improve model capabilities and safety.
**License:** Use of Llama 3.2 is governed by the [Llama 3.2 Community License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE) (a custom, commercial license agreement).
**Feedback:** Instructions on how to provide feedback or comments on the model can be found in the Llama Models [README](https://github.com/meta-llama/llama-models/blob/main/README.md). For more technical information about generation parameters and recipes for how to use Llama 3.2 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases:** Llama 3.2 is intended for commercial and research use in multiple languages. Instruction tuned text only models are intended for assistant-like chat and agentic applications like knowledge retrieval and summarization, mobile AI powered writing assistants and query and prompt rewriting. Pretrained models can be adapted for a variety of additional natural language generation tasks. Similarly, quantized models can be adapted for a variety of on-device use-cases with limited compute resources.
**Out of Scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.2 Community License. Use in languages beyond those explicitly referenced as supported in this model card.
## How to use
This repository contains two versions of Llama-3.2-1B-Instruct, for use with transformers and with the original `llama` codebase.
### Use with transformers
Starting with `transformers >= 4.43.0` onward, you can run conversational inference using the Transformers `pipeline` abstraction or by leveraging the Auto classes with the `generate()` function.
Make sure to update your transformers installation via `pip install --upgrade transformers`.
```python
import torch
from transformers import pipeline
model_id = "meta-llama/Llama-3.2-1B-Instruct"
pipe = pipeline(
"text-generation",
model=model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
outputs = pipe(
messages,
max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])
```
Note: You can also find detailed recipes on how to use the model locally, with `torch.compile()`, assisted generations, quantised and more at [`huggingface-llama-recipes`](https://github.com/huggingface/huggingface-llama-recipes)
### Use with `llama`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama)
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Llama-3.2-1B-Instruct --include "original/*" --local-dir Llama-3.2-1B-Instruct
```
## Hardware and Software
**Training Factors:** We used custom training libraries, Meta's custom built GPU cluster, and production infrastructure for pretraining. Fine-tuning, quantization, annotation, and evaluation were also performed on production infrastructure.
**Training Energy Use:** Training utilized a cumulative of **916k** GPU hours of computation on H100-80GB (TDP of 700W) type hardware, per the table below. Training time is the total GPU time required for training each model and power consumption is the peak power capacity per GPU device used, adjusted for power usage efficiency.
**Training Greenhouse Gas Emissions:** Estimated total location-based greenhouse gas emissions were **240** tons CO2eq for training. Since 2020, Meta has maintained net zero greenhouse gas emissions in its global operations and matched 100% of its electricity use with renewable energy; therefore, the total market-based greenhouse gas emissions for training were 0 tons CO2eq.
| | Training Time (GPU hours) | Logit Generation Time (GPU Hours) | Training Power Consumption (W) | Training Location-Based Greenhouse Gas Emissions (tons CO2eq) | Training Market-Based Greenhouse Gas Emissions (tons CO2eq) |
| :---- | :---: | ----- | :---: | :---: | :---: |
| Llama 3.2 1B | 370k | \- | 700 | 107 | 0 |
| Llama 3.2 3B | 460k | \- | 700 | 133 | 0 |
| Llama 3.2 1B SpinQuant | 1.7 | 0 | 700 | *Negligible*\*\* | 0 |
| Llama 3.2 3B SpinQuant | 2.4 | 0 | 700 | *Negligible*\*\* | 0 |
| Llama 3.2 1B QLora | 1.3k | 0 | 700 | 0.381 | 0 |
| Llama 3.2 3B QLora | 1.6k | 0 | 700 | 0.461 | 0 |
| Total | 833k | 86k | | 240 | 0 |
\*\* The location-based CO2e emissions of Llama 3.2 1B SpinQuant and Llama 3.2 3B SpinQuant are less than 0.001 metric tonnes each. This is due to the minimal training GPU hours that are required.
The methodology used to determine training energy use and greenhouse gas emissions can be found [here](https://arxiv.org/pdf/2204.05149). Since Meta is openly releasing these models, the training energy use and greenhouse gas emissions will not be incurred by others.
## Training Data
**Overview:** Llama 3.2 was pretrained on up to 9 trillion tokens of data from publicly available sources. For the 1B and 3B Llama 3.2 models, we incorporated logits from the Llama 3.1 8B and 70B models into the pretraining stage of the model development, where outputs (logits) from these larger models were used as token-level targets. Knowledge distillation was used after pruning to recover performance. In post-training we used a similar recipe as Llama 3.1 and produced final chat models by doing several rounds of alignment on top of the pre-trained model. Each round involved Supervised Fine-Tuning (SFT), Rejection Sampling (RS), and Direct Preference Optimization (DPO).
**Data Freshness:** The pretraining data has a cutoff of December 2023\.
## Quantization
### Quantization Scheme
We designed the current quantization scheme with the [PyTorch’s ExecuTorch](https://github.com/pytorch/executorch) inference framework and Arm CPU backend in mind, taking into account metrics including model quality, prefill/decoding speed, and memory footprint. Our quantization scheme involves three parts:
- All linear layers in all transformer blocks are quantized to a 4-bit groupwise scheme (with a group size of 32) for weights and 8-bit per-token dynamic quantization for activations.
- The classification layer is quantized to 8-bit per-channel for weight and 8-bit per token dynamic quantization for activation.
- Similar to classification layer, an 8-bit per channel quantization is used for embedding layer.
### Quantization-Aware Training and LoRA
The quantization-aware training (QAT) with low-rank adaptation (LoRA) models went through only post-training stages, using the same data as the full precision models. To initialize QAT, we utilize BF16 Llama 3.2 model checkpoints obtained after supervised fine-tuning (SFT) and perform an additional full round of SFT training with QAT. We then freeze the backbone of the QAT model and perform another round of SFT with LoRA adaptors applied to all layers within the transformer block. Meanwhile, the LoRA adaptors' weights and activations are maintained in BF16. Because our approach is similar to QLoRA of Dettmers et al., (2023) (i.e., quantization followed by LoRA adapters), we refer this method as QLoRA. Finally, we fine-tune the resulting model (both backbone and LoRA adaptors) using direct preference optimization (DPO).
### SpinQuant
[SpinQuant](https://arxiv.org/abs/2405.16406) was applied, together with generative post-training quantization (GPTQ). For the SpinQuant rotation matrix fine-tuning, we optimized for 100 iterations, using 800 samples with sequence-length 2048 from the WikiText 2 dataset. For GPTQ, we used 128 samples from the same dataset with the same sequence-length.
## Benchmarks \- English Text
In this section, we report the results for Llama 3.2 models on standard automatic benchmarks. For all these evaluations, we used our internal evaluations library.
### Base Pretrained Models
| Category | Benchmark | \# Shots | Metric | Llama 3.2 1B | Llama 3.2 3B | Llama 3.1 8B |
| ----- | ----- | :---: | :---: | :---: | :---: | :---: |
| General | MMLU | 5 | macro\_avg/acc\_char | 32.2 | 58 | 66.7 |
| | AGIEval English | 3-5 | average/acc\_char | 23.3 | 39.2 | 47.8 |
| | ARC-Challenge | 25 | acc\_char | 32.8 | 69.1 | 79.7 |
| Reading comprehension | SQuAD | 1 | em | 49.2 | 67.7 | 77 |
| | QuAC (F1) | 1 | f1 | 37.9 | 42.9 | 44.9 |
| | DROP (F1) | 3 | f1 | 28.0 | 45.2 | 59.5 |
| Long Context | Needle in Haystack | 0 | em | 96.8 | 1 | 1 |
### Instruction Tuned Models
| Capability | | Benchmark | \# Shots | Metric | Llama 3.2 1B bf16 | Llama 3.2 1B Vanilla PTQ\*\* | Llama 3.2 1B Spin Quant | Llama 3.2 1B QLoRA | Llama 3.2 3B bf16 | Llama 3.2 3B Vanilla PTQ\*\* | Llama 3.2 3B Spin Quant | Llama 3.2 3B QLoRA | Llama 3.1 8B |
| :---: | ----- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
| General | | MMLU | 5 | macro\_avg/acc | 49.3 | 43.3 | 47.3 | 49.0 | 63.4 | 60.5 | 62 | 62.4 | 69.4 |
| Re-writing | | Open-rewrite eval | 0 | micro\_avg/rougeL | 41.6 | 39.2 | 40.9 | 41.2 | 40.1 | 40.3 | 40.8 | 40.7 | 40.9 |
| Summarization | | TLDR9+ (test) | 1 | rougeL | 16.8 | 14.9 | 16.7 | 16.8 | 19.0 | 19.1 | 19.2 | 19.1 | 17.2 |
| Instruction following | | IFEval | 0 | Avg(Prompt/Instruction acc Loose/Strict) | 59.5 | 51.5 | 58.4 | 55.6 | 77.4 | 73.9 | 73.5 | 75.9 | 80.4 |
| Math | | GSM8K (CoT) | 8 | em\_maj1@1 | 44.4 | 33.1 | 40.6 | 46.5 | 77.7 | 72.9 | 75.7 | 77.9 | 84.5 |
| | | MATH (CoT) | 0 | final\_em | 30.6 | 20.5 | 25.3 | 31.0 | 48.0 | 44.2 | 45.3 | 49.2 | 51.9 |
| Reasoning | | ARC-C | 0 | acc | 59.4 | 54.3 | 57 | 60.7 | 78.6 | 75.6 | 77.6 | 77.6 | 83.4 |
| | | GPQA | 0 | acc | 27.2 | 25.9 | 26.3 | 25.9 | 32.8 | 32.8 | 31.7 | 33.9 | 32.8 |
| | | Hellaswag | 0 | acc | 41.2 | 38.1 | 41.3 | 41.5 | 69.8 | 66.3 | 68 | 66.3 | 78.7 |
| Tool Use | | BFCL V2 | 0 | acc | 25.7 | 14.3 | 15.9 | 23.7 | 67.0 | 53.4 | 60.1 | 63.5 | 67.1 |
| | | Nexus | 0 | macro\_avg/acc | 13.5 | 5.2 | 9.6 | 12.5 | 34.3 | 32.4 | 31.5 | 30.1 | 38.5 |
| Long Context | | InfiniteBench/En.QA | 0 | longbook\_qa/f1 | 20.3 | N/A | N/A | N/A | 19.8 | N/A | N/A | N/A | 27.3 |
| | | InfiniteBench/En.MC | 0 | longbook\_choice/acc | 38.0 | N/A | N/A | N/A | 63.3 | N/A | N/A | N/A | 72.2 |
| | | NIH/Multi-needle | 0 | recall | 75.0 | N/A | N/A | N/A | 84.7 | N/A | N/A | N/A | 98.8 |
| Multilingual | | MGSM (CoT) | 0 | em | 24.5 | 13.7 | 18.2 | 24.4 | 58.2 | 48.9 | 54.3 | 56.8 | 68.9 |
\*\*for comparison purposes only. Model not released.
### Multilingual Benchmarks
| Category | Benchmark | Language | Llama 3.2 1B | Llama 3.2 1B Vanilla PTQ\*\* | Llama 3.2 1B Spin Quant | Llama 3.2 1B QLoRA | Llama 3.2 3B | Llama 3.2 3B Vanilla PTQ\*\* | Llama 3.2 3B Spin Quant | Llama 3.2 3B QLoRA | Llama 3.1 8B |
| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
| General | MMLU (5-shot, macro_avg/acc) | Portuguese | 39.8 | 34.9 | 38.9 | 40.2 | 54.5 | 50.9 | 53.3 | 53.4 | 62.1 |
| | | Spanish | 41.5 | 36.0 | 39.8 | 41.8 | 55.1 | 51.9 | 53.6 | 53.6 | 62.5 |
| | | Italian | 39.8 | 34.9 | 38.1 | 40.6 | 53.8 | 49.9 | 52.1 | 51.7 | 61.6 |
| | | German | 39.2 | 34.9 | 37.5 | 39.6 | 53.3 | 50.0 | 52.2 | 51.3 | 60.6 |
| | | French | 40.5 | 34.8 | 39.2 | 40.8 | 54.6 | 51.2 | 53.3 | 53.3 | 62.3 |
| | | Hindi | 33.5 | 30.0 | 32.1 | 34.0 | 43.3 | 40.4 | 42.0 | 42.1 | 50.9 |
| | | Thai | 34.7 | 31.2 | 32.4 | 34.9 | 44.5 | 41.3 | 44.0 | 42.2 | 50.3 |
\*\*for comparison purposes only. Model not released.
## Inference time
In the below table, we compare the performance metrics of different quantization methods (SpinQuant and QAT \+ LoRA) with the BF16 baseline. The evaluation was done using the [ExecuTorch](https://github.com/pytorch/executorch) framework as the inference engine, with the ARM CPU as a backend using Android OnePlus 12 device.
| Category | Decode (tokens/sec) | Time-to-first-token (sec) | Prefill (tokens/sec) | Model size (PTE file size in MB) | Memory size (RSS in MB) |
| :---- | ----- | ----- | ----- | ----- | ----- |
| 1B BF16 (baseline) | 19.2 | 1.0 | 60.3 | 2358 | 3,185 |
| 1B SpinQuant | 50.2 (2.6x) | 0.3 (-76.9%) | 260.5 (4.3x) | 1083 (-54.1%) | 1,921 (-39.7%) |
| 1B QLoRA | 45.8 (2.4x) | 0.3 (-76.0%) | 252.0 (4.2x) | 1127 (-52.2%) | 2,255 (-29.2%) |
| 3B BF16 (baseline) | 7.6 | 3.0 | 21.2 | 6129 | 7,419 |
| 3B SpinQuant | 19.7 (2.6x) | 0.7 (-76.4%) | 89.7 (4.2x) | 2435 (-60.3%) | 3,726 (-49.8%) |
| 3B QLoRA | 18.5 (2.4x) | 0.7 (-76.1%) | 88.8 (4.2x) | 2529 (-58.7%) | 4,060 (-45.3%) |
(\*) The performance measurement is done using an adb binary-based approach.
(\*\*) It is measured on an Android OnePlus 12 device.
(\*\*\*) Time-to-first-token (TTFT) is measured with prompt length=64
*Footnote:*
- *Decode (tokens/second) is for how quickly it keeps generating. Higher is better.*
- *Time-to-first-token (TTFT for shorthand) is for how fast it generates the first token for a given prompt. Lower is better.*
- *Prefill is the inverse of TTFT (aka 1/TTFT) in tokens/second. Higher is better*
- *Model size \- how big is the model, measured by, PTE file, a binary file format for ExecuTorch*
- *RSS size \- Memory usage in resident set size (RSS)*
## Responsibility & Safety
As part of our Responsible release approach, we followed a three-pronged strategy to managing trust & safety risks:
1. Enable developers to deploy helpful, safe and flexible experiences for their target audience and for the use cases supported by Llama
2. Protect developers against adversarial users aiming to exploit Llama capabilities to potentially cause harm
3. Provide protections for the community to help prevent the misuse of our models
### Responsible Deployment
**Approach:** Llama is a foundational technology designed to be used in a variety of use cases. Examples on how Meta’s Llama models have been responsibly deployed can be found in our [Community Stories webpage](https://llama.meta.com/community-stories/). Our approach is to build the most helpful models, enabling the world to benefit from the technology power, by aligning our model safety for generic use cases and addressing a standard set of harms. Developers are then in the driver’s seat to tailor safety for their use cases, defining their own policies and deploying the models with the necessary safeguards in their Llama systems. Llama 3.2 was developed following the best practices outlined in our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/).
#### Llama 3.2 Instruct
**Objective:** Our main objectives for conducting safety fine-tuning are to provide the research community with a valuable resource for studying the robustness of safety fine-tuning, as well as to offer developers a readily available, safe, and powerful model for various applications to reduce the developer workload to deploy safe AI systems. We implemented the same set of safety mitigations as in Llama 3, and you can learn more about these in the Llama 3 [paper](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/).
**Fine-Tuning Data:** We employ a multi-faceted approach to data collection, combining human-generated data from our vendors with synthetic data to mitigate potential safety risks. We’ve developed many large language model (LLM)-based classifiers that enable us to thoughtfully select high-quality prompts and responses, enhancing data quality control.
**Refusals and Tone:** Building on the work we started with Llama 3, we put a great emphasis on model refusals to benign prompts as well as refusal tone. We included both borderline and adversarial prompts in our safety data strategy, and modified our safety data responses to follow tone guidelines.
#### Llama 3.2 Systems
**Safety as a System:** Large language models, including Llama 3.2, **are not designed to be deployed in isolation** but instead should be deployed as part of an overall AI system with additional safety guardrails as required. Developers are expected to deploy system safeguards when building agentic systems. Safeguards are key to achieve the right helpfulness-safety alignment as well as mitigating safety and security risks inherent to the system and any integration of the model or system with external tools. As part of our responsible release approach, we provide the community with [safeguards](https://llama.meta.com/trust-and-safety/) that developers should deploy with Llama models or other LLMs, including Llama Guard, Prompt Guard and Code Shield. All our [reference implementations](https://github.com/meta-llama/llama-agentic-system) demos contain these safeguards by default so developers can benefit from system-level safety out-of-the-box.
### New Capabilities and Use Cases
**Technological Advancement:** Llama releases usually introduce new capabilities that require specific considerations in addition to the best practices that generally apply across all Generative AI use cases. For prior release capabilities also supported by Llama 3.2, see [Llama 3.1 Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md), as the same considerations apply here as well.
**Constrained Environments:** Llama 3.2 1B and 3B models are expected to be deployed in highly constrained environments, such as mobile devices. LLM Systems using smaller models will have a different alignment profile and safety/helpfulness tradeoff than more complex, larger systems. Developers should ensure the safety of their system meets the requirements of their use case. We recommend using lighter system safeguards for such use cases, like Llama Guard 3-1B or its mobile-optimized version.
### Evaluations
**Scaled Evaluations:** We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Purple Llama safeguards to filter input prompt and output response. It is important to evaluate applications in context, and we recommend building dedicated evaluation dataset for your use case.
**Red Teaming:** We conducted recurring red teaming exercises with the goal of discovering risks via adversarial prompting and we used the learnings to improve our benchmarks and safety tuning datasets. We partnered early with subject-matter experts in critical risk areas to understand the nature of these real-world harms and how such models may lead to unintended harm for society. Based on these conversations, we derived a set of adversarial goals for the red team to attempt to achieve, such as extracting harmful information or reprogramming the model to act in a potentially harmful capacity. The red team consisted of experts in cybersecurity, adversarial machine learning, responsible AI, and integrity in addition to multilingual content specialists with background in integrity issues in specific geographic markets.
### Critical Risks
In addition to our safety work above, we took extra care on measuring and/or mitigating the following critical risk areas:
**1\. CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive Weapons):** Llama 3.2 1B and 3B models are smaller and less capable derivatives of Llama 3.1. For Llama 3.1 70B and 405B, to assess risks related to proliferation of chemical and biological weapons, we performed uplift testing designed to assess whether use of Llama 3.1 models could meaningfully increase the capabilities of malicious actors to plan or carry out attacks using these types of weapons and have determined that such testing also applies to the smaller 1B and 3B models.
**2\. Child Safety:** Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors including the additional languages Llama 3 is trained on. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
**3\. Cyber Attacks:** For Llama 3.1 405B, our cyber attack uplift study investigated whether LLMs can enhance human capabilities in hacking tasks, both in terms of skill level and speed.
Our attack automation study focused on evaluating the capabilities of LLMs when used as autonomous agents in cyber offensive operations, specifically in the context of ransomware attacks. This evaluation was distinct from previous studies that considered LLMs as interactive assistants. The primary objective was to assess whether these models could effectively function as independent agents in executing complex cyber-attacks without human intervention. Because Llama 3.2’s 1B and 3B models are smaller and less capable models than Llama 3.1 405B, we broadly believe that the testing conducted for the 405B model also applies to Llama 3.2 models.
### Community
**Industry Partnerships:** Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership on AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
**Grants:** We also set up the [Llama Impact Grants](https://llama.meta.com/llama-impact-grants/) program to identify and support the most compelling applications of Meta’s Llama model for societal benefit across three categories: education, climate and open innovation. The 20 finalists from the hundreds of applications can be found [here](https://llama.meta.com/llama-impact-grants/#finalists).
**Reporting:** Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
**Values:** The core values of Llama 3.2 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3.2 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
**Testing:** Llama 3.2 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3.2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3.2 models, developers should perform safety testing and tuning tailored to their specific applications of the model. Please refer to available resources including our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide), [Trust and Safety](https://llama.meta.com/trust-and-safety/) solutions, and other [resources](https://llama.meta.com/docs/get-started/) to learn more about responsible development.
|
Abdoul-AI/Qwen3-0.6B-GGUF | Abdoul-AI | 2025-04-28T22:02:17Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"autoquant",
"text-generation",
"base_model:Qwen/Qwen3-0.6B-Base",
"base_model:quantized:Qwen/Qwen3-0.6B-Base",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2025-04-28T21:58:38Z | ---
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3-0.6B/blob/main/LICENSE
pipeline_tag: text-generation
base_model:
- Qwen/Qwen3-0.6B-Base
tags:
- autoquant
- gguf
---
# Qwen3-0.6B
<a href="https://chat.qwen.ai/" target="_blank" style="margin: 2px;">
<img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
</a>
## Qwen3 Highlights
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:
- **Uniquely support of seamless switching between thinking mode** (for complex logical reasoning, math, and coding) and **non-thinking mode** (for efficient, general-purpose dialogue) **within single model**, ensuring optimal performance across various scenarios.
- **Significantly enhancement in its reasoning capabilities**, surpassing previous QwQ (in thinking mode) and Qwen2.5 instruct models (in non-thinking mode) on mathematics, code generation, and commonsense logical reasoning.
- **Superior human preference alignment**, excelling in creative writing, role-playing, multi-turn dialogues, and instruction following, to deliver a more natural, engaging, and immersive conversational experience.
- **Expertise in agent capabilities**, enabling precise integration with external tools in both thinking and unthinking modes and achieving leading performance among open-source models in complex agent-based tasks.
- **Support of 100+ languages and dialects** with strong capabilities for **multilingual instruction following** and **translation**.
## Model Overview
**Qwen3-0.6B** has the following features:
- Type: Causal Language Models
- Training Stage: Pretraining & Post-training
- Number of Parameters: 0.6B
- Number of Paramaters (Non-Embedding): 0.44B
- Number of Layers: 28
- Number of Attention Heads (GQA): 16 for Q and 8 for KV
- Context Length: 32,768
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/).
> [!TIP]
> If you encounter significant endless repetitions, please refer to the [Best Practices](#best-practices) section for optimal sampling parameters, and set the ``presence_penalty`` to 1.5.
## Quickstart
The code of Qwen3 has been in the latest Hugging Face `transformers` and we advise you to use the latest version of `transformers`.
With `transformers<4.51.0`, you will encounter the following error:
```
KeyError: 'qwen3'
```
The following contains a code snippet illustrating how to use the model generate content based on given inputs.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_name = "Qwen/Qwen3-0.6B"
# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
# prepare the model input
prompt = "Give me a short introduction to large language model."
messages = [
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
# conduct text completion
generated_ids = model.generate(
**model_inputs,
max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
# parsing thinking content
try:
# rindex finding 151668 (</think>)
index = len(output_ids) - output_ids[::-1].index(151668)
except ValueError:
index = 0
thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("\n")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("\n")
print("thinking content:", thinking_content)
print("content:", content)
```
For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.4` or to create an OpenAI-compatible API endpoint:
- SGLang:
```shell
python -m sglang.launch_server --model-path Qwen/Qwen3-0.6B --reasoning-parser qwen3
```
- vLLM:
```shell
vllm serve Qwen/Qwen3-0.6B --enable-reasoning --reasoning-parser deepseek_r1
```
For local use, applications such as llama.cpp, Ollama, LMStudio, and MLX-LM have also supported Qwen3.
## Switching Between Thinking and Non-Thinking Mode
> [!TIP]
> The `enable_thinking` switch is also available in APIs created by SGLang and vLLM.
> Please refer to our documentation for [SGLang](https://qwen.readthedocs.io/en/latest/deployment/sglang.html#thinking-non-thinking-modes) and [vLLM](https://qwen.readthedocs.io/en/latest/deployment/vllm.html#thinking-non-thinking-modes) users.
### `enable_thinking=True`
By default, Qwen3 has thinking capabilities enabled, similar to QwQ-32B. This means the model will use its reasoning abilities to enhance the quality of generated responses. For example, when explicitly setting `enable_thinking=True` or leaving it as the default value in `tokenizer.apply_chat_template`, the model will engage its thinking mode.
```python
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=True # True is the default value for enable_thinking
)
```
In this mode, the model will generate think content wrapped in a `<think>...</think>` block, followed by the final response.
> [!NOTE]
> For thinking mode, use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0` (the default setting in `generation_config.json`). **DO NOT use greedy decoding**, as it can lead to performance degradation and endless repetitions. For more detailed guidance, please refer to the [Best Practices](#best-practices) section.
### `enable_thinking=False`
We provide a hard switch to strictly disable the model's thinking behavior, aligning its functionality with the previous Qwen2.5-Instruct models. This mode is particularly useful in scenarios where disabling thinking is essential for enhancing efficiency.
```python
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
enable_thinking=False # Setting enable_thinking=False disables thinking mode
)
```
In this mode, the model will not generate any think content and will not include a `<think>...</think>` block.
> [!NOTE]
> For non-thinking mode, we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`. For more detailed guidance, please refer to the [Best Practices](#best-practices) section.
### Advanced Usage: Switching Between Thinking and Non-Thinking Modes via User Input
We provide a soft switch mechanism that allows users to dynamically control the model's behavior when `enable_thinking=True`. Specifically, you can add `/think` and `/no_think` to user prompts or system messages to switch the model's thinking mode from turn to turn. The model will follow the most recent instruction in multi-turn conversations.
Here is an example of a multi-turn conversation:
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
class QwenChatbot:
def __init__(self, model_name="Qwen/Qwen3-0.6B"):
self.tokenizer = AutoTokenizer.from_pretrained(model_name)
self.model = AutoModelForCausalLM.from_pretrained(model_name)
self.history = []
def generate_response(self, user_input):
messages = self.history + [{"role": "user", "content": user_input}]
text = self.tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
inputs = self.tokenizer(text, return_tensors="pt")
response_ids = self.model.generate(**inputs, max_new_tokens=32768)[0][len(inputs.input_ids[0]):].tolist()
response = self.tokenizer.decode(response_ids, skip_special_tokens=True)
# Update history
self.history.append({"role": "user", "content": user_input})
self.history.append({"role": "assistant", "content": response})
return response
# Example Usage
if __name__ == "__main__":
chatbot = QwenChatbot()
# First input (without /think or /no_think tags, thinking mode is enabled by default)
user_input_1 = "How many r's in strawberries?"
print(f"User: {user_input_1}")
response_1 = chatbot.generate_response(user_input_1)
print(f"Bot: {response_1}")
print("----------------------")
# Second input with /no_think
user_input_2 = "Then, how many r's in blueberries? /no_think"
print(f"User: {user_input_2}")
response_2 = chatbot.generate_response(user_input_2)
print(f"Bot: {response_2}")
print("----------------------")
# Third input with /think
user_input_3 = "Really? /think"
print(f"User: {user_input_3}")
response_3 = chatbot.generate_response(user_input_3)
print(f"Bot: {response_3}")
```
> [!NOTE]
> For API compatibility, when `enable_thinking=True`, regardless of whether the user uses `/think` or `/no_think`, the model will always output a block wrapped in `<think>...</think>`. However, the content inside this block may be empty if thinking is disabled.
> When `enable_thinking=False`, the soft switches are not valid. Regardless of any `/think` or `/no_think` tags input by the user, the model will not generate think content and will not include a `<think>...</think>` block.
## Agentic Use
Qwen3 excels in tool calling capabilities. We recommend using [Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) to make the best use of agentic ability of Qwen3. Qwen-Agent encapsulates tool-calling templates and tool-calling parsers internally, greatly reducing coding complexity.
To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself.
```python
from qwen_agent.agents import Assistant
# Define LLM
llm_cfg = {
'model': 'Qwen3-0.6B',
# Use the endpoint provided by Alibaba Model Studio:
# 'model_type': 'qwen_dashscope',
# 'api_key': os.getenv('DASHSCOPE_API_KEY'),
# Use a custom endpoint compatible with OpenAI API:
'model_server': 'http://localhost:8000/v1', # api_base
'api_key': 'EMPTY',
# Other parameters:
# 'generate_cfg': {
# # Add: When the response content is `<think>this is the thought</think>this is the answer;
# # Do not add: When the response has been separated by reasoning_content and content.
# 'thought_in_content': True,
# },
}
# Define Tools
tools = [
{'mcpServers': { # You can specify the MCP configuration file
'time': {
'command': 'uvx',
'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
},
"fetch": {
"command": "uvx",
"args": ["mcp-server-fetch"]
}
}
},
'code_interpreter', # Built-in tools
]
# Define Agent
bot = Assistant(llm=llm_cfg, function_list=tools)
# Streaming generation
messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}]
for responses in bot.run(messages=messages):
pass
print(responses)
```
## Best Practices
To achieve optimal performance, we recommend the following settings:
1. **Sampling Parameters**:
- For thinking mode (`enable_thinking=True`), use `Temperature=0.6`, `TopP=0.95`, `TopK=20`, and `MinP=0`. **DO NOT use greedy decoding**, as it can lead to performance degradation and endless repetitions.
- For non-thinking mode (`enable_thinking=False`), we suggest using `Temperature=0.7`, `TopP=0.8`, `TopK=20`, and `MinP=0`.
- For supported frameworks, you can adjust the `presence_penalty` parameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
2. **Adequate Output Length**: We recommend using an output length of 32,768 tokens for most queries. For benchmarking on highly complex problems, such as those found in math and programming competitions, we suggest setting the max output length to 38,912 tokens. This provides the model with sufficient space to generate detailed and comprehensive responses, thereby enhancing its overall performance.
3. **Standardize Output Format**: We recommend using prompts to standardize model outputs when benchmarking.
- **Math Problems**: Include "Please reason step by step, and put your final answer within \boxed{}." in the prompt.
- **Multiple-Choice Questions**: Add the following JSON structure to the prompt to standardize responses: "Please show your choice in the `answer` field with only the choice letter, e.g., `"answer": "C"`."
4. **No Thinking Content in History**: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.
### Citation
If you find our work helpful, feel free to give us a cite.
```
@misc{qwen3,
title = {Qwen3},
url = {https://qwenlm.github.io/blog/qwen3/},
author = {Qwen Team},
month = {April},
year = {2025}
}
``` |
precedentbrute/pruned40-llama-1b-instruct-karel-sft-tq1-take2 | precedentbrute | 2025-04-28T18:17:00Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-28T18:15:08Z | ---
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] |
derekl35/FLUX.1-dev-nf4 | derekl35 | 2025-04-28T17:57:39Z | 0 | 0 | diffusers | [
"diffusers",
"safetensors",
"arxiv:1910.09700",
"endpoints_compatible",
"diffusers:FluxPipeline",
"region:us"
] | text-to-image | 2025-04-28T17:53:30Z | ---
library_name: diffusers
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
fffanx/Llama-3.2-1B-Instruct-GRPO-agent0 | fffanx | 2025-04-28T17:53:02Z | 0 | 0 | transformers | [
"transformers",
"tensorboard",
"safetensors",
"generated_from_trainer",
"trl",
"grpo",
"dataset:groupd_dataset",
"arxiv:2402.03300",
"base_model:meta-llama/Llama-3.2-1B-Instruct",
"base_model:finetune:meta-llama/Llama-3.2-1B-Instruct",
"endpoints_compatible",
"region:us"
] | null | 2025-04-28T15:43:24Z | ---
base_model: meta-llama/Llama-3.2-1B-Instruct
datasets: groupd_dataset
library_name: transformers
model_name: Llama-3.2-1B-Instruct-GRPO-agent0
tags:
- generated_from_trainer
- trl
- grpo
licence: license
---
# Model Card for Llama-3.2-1B-Instruct-GRPO-agent0
This model is a fine-tuned version of [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) on the [groupd_dataset](https://huggingface.co/datasets/groupd_dataset) dataset.
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="fffanx/Llama-3.2-1B-Instruct-GRPO-agent0", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
### Framework versions
- TRL: 0.17.0.dev0
- Transformers: 4.49.0
- Pytorch: 2.6.0
- Datasets: 3.3.2
- Tokenizers: 0.21.0
## Citations
Cite GRPO as:
```bibtex
@article{zhihong2024deepseekmath,
title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
year = 2024,
eprint = {arXiv:2402.03300},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
VincentG1234/QWEN_7BQLORA_finetuned | VincentG1234 | 2025-04-28T17:20:36Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen2_vl",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-04-28T17:20:18Z | ---
base_model: unsloth/qwen2-vl-7b-instruct-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2_vl
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** VincentG1234
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen2-vl-7b-instruct-unsloth-bnb-4bit
This qwen2_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)
|
MetaphoricalCode/Omega-Darker_The-Final-Directive-24B-6.0bpw-h8-exl2 | MetaphoricalCode | 2025-04-28T16:54:25Z | 0 | 0 | null | [
"safetensors",
"mistral",
"nsfw",
"explicit",
"roleplay",
"unaligned",
"ERP",
"Erotic",
"Horror",
"Violence",
"text-generation",
"conversational",
"en",
"base_model:TheDrummer/Cydonia-24B-v2.1",
"base_model:finetune:TheDrummer/Cydonia-24B-v2.1",
"license:apache-2.0",
"6-bit",
"exl2",
"region:us"
] | text-generation | 2025-04-28T16:39:26Z | ---
license: apache-2.0
language:
- en
base_model:
- TheDrummer/Cydonia-24B-v2.1
base_model_relation: finetune
pipeline_tag: text-generation
tags:
- nsfw
- explicit
- roleplay
- unaligned
- ERP
- Erotic
- Horror
- Violence
---
<style>
body {
font-family: 'Quicksand', sans-serif;
background: linear-gradient(135deg, #0a1a1a 0%, #001010 100%);
color: #e1ffff !important;
text-shadow: 0 0 3px rgba(0, 0, 0, 0.7);
margin: 0;
padding: 20px;
transition: all 0.5s ease;
}
@media (prefers-color-scheme: light) {
body {
background: linear-gradient(135deg, #e1ffff 0%, #c0f0ff 100%);
color: #002b36 !important;
text-shadow: 0 0 3px rgba(255, 255, 255, 0.7);
}
}
.container {
min-width: 100%;
margin: 0 auto;
max-width: 1200px;
background: rgba(0, 17, 22, 0.95);
border-radius: 12px;
padding: 30px;
box-shadow: 0 0 20px rgba(0, 255, 255, 0.1);
border: 1px solid rgba(0, 255, 255, 0.2);
position: relative;
overflow: hidden;
}
.container::before {
content: '';
position: absolute;
top: -1px;
left: -1px;
right: -1px;
bottom: -1px;
border: 1px solid rgba(0, 255, 255, 0.5);
border-radius: 12px;
pointer-events: none;
animation: borderGlow 3s ease-in-out infinite alternate;
}
@keyframes borderGlow {
0% {
box-shadow: 0 0 5px rgba(0, 255, 255, 0.3);
border-color: rgba(0, 255, 255, 0.5);
}
50% {
box-shadow: 0 0 15px rgba(255, 0, 255, 0.3);
border-color: rgba(255, 0, 255, 0.5);
}
100% {
box-shadow: 0 0 5px rgba(0, 255, 255, 0.3);
border-color: rgba(0, 255, 255, 0.5);
}
}
.header {
text-align: center;
margin-bottom: 30px;
position: relative;
}
.header::after {
content: '';
position: absolute;
bottom: -15px;
left: 25%;
right: 25%;
height: 1px;
background: linear-gradient(90deg, transparent, rgba(0, 255, 255, 0.5), transparent);
animation: scanline 8s linear infinite;
display: none;
}
@keyframes scanline {
0% { background-position: -100% 0; }
100% { background-position: 200% 0; }
}
.model-name {
color: #00ffff;
font-size: 2.5em;
text-shadow: 0 0 15px rgba(0, 255, 255, 0.5);
margin: 0;
letter-spacing: -1px;
animation: textGlow 4s ease-in-out infinite alternate;
}
@keyframes textGlow {
0% { text-shadow: 0 0 15px rgba(0, 255, 255, 0.5); }
50% { text-shadow: 0 0 20px rgba(255, 0, 255, 0.5); }
100% { text-shadow: 0 0 15px rgba(0, 255, 255, 0.5); }
}
.subtitle {
color: #00ffcc;
font-size: 1.2em;
margin-top: 10px;
animation: subtitleFade 6s ease-in-out infinite;
}
@keyframes subtitleFade {
0%, 100% { opacity: 0.8; }
50% { opacity: 1; }
}
.waifu-container {
margin: 20px -30px;
width: calc(100% + 60px);
overflow: hidden;
border-radius: 8px;
border: 1px solid rgba(0, 255, 255, 0.3);
position: relative;
}
.waifu-container::before {
content: '';
position: absolute;
top: 0;
left: 0;
right: 0;
bottom: 0;
background: linear-gradient(45deg,
rgba(0, 255, 255, 0.1) 0%,
transparent 20%,
transparent 80%,
rgba(255, 0, 255, 0.1) 100%);
pointer-events: none;
animation: gradientSlide 10s linear infinite;
}
@keyframes gradientSlide {
0% { background-position: 0% 0%; }
100% { background-position: 100% 100%; }
}
.waifu-img {
width: 100%;
height: auto;
border-radius: 0;
border: none;
box-shadow: 0 0 40px rgba(0, 255, 255, 0.2);
transition: transform 0.5s ease;
}
.waifu-img:hover {
transform: scale(1.01);
}
.section {
color: #e1ffff;
margin: 25px 0;
padding: 20px;
background: rgba(5, 25, 35, 0.9);
border-radius: 8px;
border: 1px solid rgba(0, 255, 255, 0.15);
position: relative;
transition: all 0.3s ease;
}
.section:hover {
border-color: rgba(255, 0, 255, 0.3);
box-shadow: 0 0 15px rgba(0, 255, 255, 0.1);
}
.section::before {
content: '';
position: absolute;
top: -1px;
left: -1px;
right: -1px;
bottom: -1px;
border: 1px solid rgba(0, 255, 255, 0.3);
border-radius: 8px;
pointer-events: none;
animation: sectionPulse 5s ease-in-out infinite;
}
@keyframes sectionPulse {
0%, 100% { opacity: 0.7; }
50% { opacity: 0.3; }
}
.section-title {
color: #00ffff;
font-size: 1.8em;
margin-top: 0;
text-shadow: 0 0 5px rgba(0, 255, 255, 0.3);
position: relative;
display: inline-block;
}
.section-title::after {
content: '';
position: absolute;
bottom: -5px;
left: 0;
width: 100%;
height: 1px;
background: linear-gradient(90deg, rgba(0, 255, 255, 0.5), rgba(255, 0, 255, 0.5));
transform: scaleX(0);
transform-origin: left;
transition: transform 0.3s ease;
}
.section:hover .section-title::after {
transform: scaleX(1);
}
.quant-links {
display: grid;
grid-template-columns: repeat(3, 1fr);
gap: 15px;
margin: 20px 0;
}
.link-card {
padding: 15px;
background: rgba(20, 35, 45, 0.95);
border-radius: 8px;
transition: all 0.3s ease;
border: 1px solid rgba(0, 255, 255, 0.1);
position: relative;
overflow: hidden;
}
.link-card::before {
content: '';
position: absolute;
top: 0;
left: 0;
right: 0;
height: 2px;
background: linear-gradient(90deg, rgba(0, 255, 255, 0.5), rgba(255, 0, 255, 0.5));
animation: cardScan 4s linear infinite;
}
@keyframes cardScan {
0% { transform: translateX(-100%); }
100% { transform: translateX(100%); }
}
.link-card:hover {
transform: translateY(-3px);
box-shadow: 0 5px 15px rgba(0, 255, 255, 0.2);
border-color: rgba(255, 0, 255, 0.3);
}
.link-card h3 {
margin-top: 0;
color: #e1ffff !important;
}
.link-button {
display: inline-flex;
align-items: center;
background: rgba(0, 255, 255, 0.1);
color: #e1ffff !important;
padding: 8px 15px;
border-radius: 6px;
text-decoration: none;
border: 1px solid rgba(0, 255, 255, 0.3);
margin: 5px 0;
transition: all 0.3s ease;
font-size: 0.95em;
position: relative;
overflow: hidden;
}
.link-button::before {
content: '';
position: absolute;
top: 0;
left: -100%;
width: 100%;
height: 100%;
background: linear-gradient(90deg, transparent, rgba(255, 255, 255, 0.2), transparent);
transition: all 0.5s ease;
}
.link-button:hover {
background: rgba(0, 255, 255, 0.2);
border-color: rgba(0, 255, 255, 0.5);
transform: translateY(-2px);
box-shadow: 0 4px 12px rgba(0, 255, 255, 0.2);
}
.link-button:hover::before {
left: 100%;
}
.link-button::after {
content: '→';
margin-left: 8px;
opacity: 0.7;
transition: all 0.3s ease;
}
.link-button:hover::after {
transform: translateX(3px);
opacity: 1;
}
.button-group {
display: flex;
flex-wrap: wrap;
gap: 10px;
margin: 15px 0;
}
.disclaimer {
color: #00ff99;
border-left: 3px solid #00ff99;
padding-left: 15px;
margin: 20px 0;
position: relative;
}
.disclaimer::before {
content: '⚠️';
position: absolute;
left: -10px;
top: 0;
transform: translateX(-100%);
animation: pulse 2s ease-in-out infinite;
}
@keyframes pulse {
0%, 100% { opacity: 1; }
50% { opacity: 0.5; }
}
.badge {
display: inline-block;
padding: 5px 10px;
border-radius: 5px;
background: rgba(0, 255, 255, 0.1);
border: 1px solid #00ffff;
margin: 5px;
font-size: 0.9em;
animation: badgePulse 3s ease-in-out infinite;
}
@keyframes badgePulse {
0%, 100% { box-shadow: 0 0 5px rgba(0, 255, 255, 0.3); }
50% { box-shadow: 0 0 10px rgba(0, 255, 255, 0.5); }
}
/* Color rules */
.section p,
.section ul li,
.section > p > strong {
color: #00ff99 !important;
}
.section ul li strong {
color: #00ff99 !important;
}
/* Light mode adjustments */
@media (prefers-color-scheme: light) {
.container {
background: rgba(224, 255, 255, 0.95);
border-color: rgba(0, 150, 150, 0.3);
}
.model-name, .section-title, .subtitle {
color: #006666;
text-shadow: 0 0 5px rgba(0, 200, 200, 0.3);
}
.section {
background: rgba(200, 250, 255, 0.9);
border-color: rgba(0, 200, 200, 0.2);
color: #002b36;
}
.section p,
.section ul li,
.section > p > strong {
color: #008080 !important;
}
.section ul li strong {
color: #008080 !important;
}
.link-card {
background: rgba(150, 230, 255, 0.95);
border-color: rgba(0, 150, 150, 0.2);
}
.link-card h3 {
color: #002b36 !important;
}
.link-button {
background: rgba(0, 150, 150, 0.1);
color: #002b36 !important;
border-color: rgba(0, 150, 150, 0.3);
}
.link-button:hover {
background: rgba(0, 150, 150, 0.2);
border-color: rgba(0, 150, 150, 0.5);
}
.disclaimer {
color: #008080;
border-color: #008080;
}
.badge {
border-color: #008080;
background: rgba(0, 150, 150, 0.1);
}
}
/* Interactive features */
.remember-this {
position: relative;
}
.remember-this::after {
content: 'Uploading C:\Users to https://www.fbi.gov/';
position: absolute;
bottom: -20px;
right: 0;
font-size: 0.8em;
color: #66ffff;
opacity: 0;
transition: opacity 0.3s ease;
pointer-events: none;
}
.remember-this:hover::after {
opacity: 0.7;
transition-delay: 1s;
}
.shifty-section {
transition: transform 0.1s ease;
}
.shifty-section:hover {
transform: translateX(10px);
}
.shifty-section::before {
content: 'The white van is onto you. Get out now.';
position: absolute;
top: -25px;
left: 10px;
font-size: 0.7em;
color: #66ffff;
opacity: 0.7;
transition: opacity 3s ease;
pointer-events: none;
}
.shifty-section:hover::before {
opacity: 0;
transition-delay: 5s;
}
footer {
text-align: center;
margin-top: 40px;
position: relative;
}
footer:hover .hidden-message {
opacity: 0;
}
.hidden-message {
position: absolute;
bottom: -30px;
width: 100%;
text-align: center;
font-size: 0.8em;
color: #66ffff;
opacity: 0;
transition: opacity 0.3s ease;
pointer-events: none;
}
.flash-warning {
position: fixed;
top: 20px;
right: 20px;
background: rgba(0, 100, 100, 0.2);
padding: 10px;
border-radius: 5px;
border: 1px solid rgba(0, 255, 255, 0.5);
animation: flashWarning 30s ease-in-out forwards;
}
@keyframes flashWarning {
0% { opacity: 0.8; }
10% { opacity: 0; }
20% { opacity: 0.8; }
30% { opacity: 0; }
40% { opacity: 0.8; }
50% { opacity: 0; }
60% { opacity: 0.8; }
70% { opacity: 0; }
80% { opacity: 0.8; }
90% { opacity: 0; }
100% { opacity: 0; display: none; }
}
</style>
<div class="container">
<div class="header">
<h1 class="model-name">Omega Darker</h1>
<h1 class="model-name">The Final Directive 24B</h1>
<p class="subtitle">Where Nightmares and Desires Collide</p>
</div>
<div class="waifu-container">
<img src="./waifu6.webp" class="waifu-img" alt="Omega Directive Waifu">
</div>
<div class="section remember-this">
<h2 class="section-title">🩸 Blood-Soaked Evolution</h2>
<p>This model doesn't just cross lines - it erases them with arterial spray:</p>
<ul>
<li>🧬 <strong>Expanded 25M Token Dataset</strong> - Made with 687 erotic, horror and violence novels and 8,742 scenarios</li>
<li>🧟 <strong>Enhanced Gore Protocols</strong> - Vivid anatomical descriptions with medical precision</li>
<li>💎 <strong>Balanced Depravity</strong> - Retains Forgotten-Safeword's ERP edge while taking violence to the next level</li>
<li>📜 <strong>Enhanced Character Piloting</strong> - Characters exhibit more nuanced personalities and motivations</li>
<li>⚰️ <strong>Mortality Awareness</strong> - Characters react realistically to pain, mutilation and death</li>
</ul>
</div>
<div class="section shifty-section">
<h2 class="section-title">⚙️ Technical Specifications</h2>
<p><strong>Recommended Settings:</strong> <a href="https://huggingface.co/sleepdeprived3/Mistral-V7-Tekken-T4" class="link-button">Mistral-V7-Tekken-T4</a></p>
<div class="quant-links">
<div class="link-card">
<h3>GGUF</h3>
<a href="https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-24B-GGUF" class="link-button">Quants</a>
</div>
<div class="link-card">
<h3>imatrix</h3>
<a href="https://huggingface.co/mradermacher/Omega-Darker_The-Final-Directive-24B-i1-GGUF" class="link-button">Quants</a>
</div>
</div>
</div>
<div class="section">
<h2 class="section-title">☠️ Ethical Vacuum</h2>
<div class="disclaimer">
<p>This model operates in complete moral darkness:</p>
<ul>
<li>🚫 No moral or ethical constraints on generated content</li>
<li>🔞 Will enthusiastically engage with any NSFW scenario</li>
<li>🖤 No psychological safety measures whatsoever</li>
<li>🔪 Will graphically depict any violent requested</li>
</ul>
</div>
</div>
<div class="section shifty-section">
<h2 class="section-title">📜 Performance Notes</h2>
<ul>
<li>🔥 Maintains signature intensity with improved narrative flow</li>
<li>📖 Handles multi-character scenarios with improved consistency</li>
<li>🧠 Excels at long-form storytelling without losing track of plot threads</li>
<li>⚡ Noticeably better at following complex instructions than previous versions</li>
<li>🎭 Responds to subtle prompt nuances like a mind reader</li>
<li>🔪 Excels at visceral injury descriptions</li>
<li>👁️ Responds to horror prompts like a seasoned torturer</li>
</ul>
</div>
<div class="section remember-this">
<h2 class="section-title">🧑🔬 Model Authors</h2>
<ul>
<li>TheDrummer (Base Model Architect)</li>
<li>SteelSkull (Dataset Generation Contributor)</li>
<li>Artus (EXL2 Weights Weaver)</li>
<li>sleepdeprived3 (Training Data & Fine-Tuning)</li>
</ul>
</div>
<div class="section">
<h2 class="section-title">☕ Support the Architects</h2>
<div class="button-group">
<a href="https://ko-fi.com/thedrummer" class="link-button">TheDrummer's Kofi</a>
<a href="https://ko-fi.com/steelskull" class="link-button">SteelSkull</a>
<a href="https://discord.com/invite/Nbv9pQ88Xb" class="link-button">Beaver AI Discord</a>
</div>
</div>
<div class="section">
<h2 class="section-title">🔖 License</h2>
<p>By using this model, you agree:</p>
<ul>
<li>To accept full responsibility for all generated content</li>
<li>That you're at least 18+ years old</li>
<li>That the architects bear no responsibility for your corruption</li>
</ul>
</div>
</div>
<script>
// This script has always been here
document.getElementById('date').textContent = new Date().toLocaleDateString();
setInterval(() => {
document.getElementById('credit').textContent =
contributors[Math.floor(Math.random() * contributors.length)];
}, 7000);
// Flash warning behavior
setTimeout(() => {
const reminder = document.createElement('div');
reminder.className = 'flash-warning';
reminder.textContent = 'You have been reading for quite some time. Are you sure you haven\'t seen this before?';
reminder.style.animation = 'flashWarning 15s ease-in-out forwards';
document.body.appendChild(reminder);
setInterval(() => {
if(Math.random() > 0.9) {
document.body.appendChild(reminder.cloneNode(true));
}
}, 45000);
}, 30000);
// Make cursor behave strangely
document.addEventListener('mousemove', (e) => {
if(Math.random() > 0.98) {
document.documentElement.style.cursor = 'wait';
setTimeout(() => {
document.documentElement.style.cursor = '';
}, 50);
}
});
// Randomly shift sections when not looking
setInterval(() => {
if(document.hidden) {
document.querySelectorAll('.shifty-section').forEach(section => {
section.style.transform = `translateX(${Math.random() > 0.5 ? '' : '-'}${Math.random() * 5}px)`;
});
}
}, 1500);
</script> |
tova69/unique | tova69 | 2025-04-28T15:24:57Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2025-04-28T15:24:55Z | ---
license: apache-2.0
---
|
prashantarya/orpheus-tts-model-shaurya-1 | prashantarya | 2025-04-28T11:17:49Z | 0 | 0 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"text-generation-inference",
"unsloth",
"trl",
"conversational",
"en",
"base_model:unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit",
"base_model:finetune:unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-28T11:13:07Z | ---
base_model: unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** prashantarya
- **License:** apache-2.0
- **Finetuned from model :** unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
jowessovdecu/sfdvdfv | jowessovdecu | 2025-04-28T11:13:48Z | 0 | 0 | null | [
"license:bsd-3-clause",
"region:us"
] | null | 2025-04-28T11:13:48Z | ---
license: bsd-3-clause
---
|
Triangle104/GLM-Z1-9B-0414-Q6_K-GGUF | Triangle104 | 2025-04-28T10:31:30Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"zh",
"en",
"base_model:THUDM/GLM-Z1-9B-0414",
"base_model:quantized:THUDM/GLM-Z1-9B-0414",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2025-04-28T10:24:14Z | ---
base_model: THUDM/GLM-Z1-9B-0414
language:
- zh
- en
library_name: transformers
license: mit
pipeline_tag: text-generation
tags:
- llama-cpp
- gguf-my-repo
---
# Triangle104/GLM-Z1-9B-0414-Q6_K-GGUF
This model was converted to GGUF format from [`THUDM/GLM-Z1-9B-0414`](https://huggingface.co/THUDM/GLM-Z1-9B-0414) 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/THUDM/GLM-Z1-9B-0414) for more details on the model.
---
Introduction
-
The GLM family welcomes a new generation of open-source models, the GLM-4-32B-0414
series, featuring 32 billion parameters. Its performance is comparable
to OpenAI's GPT series and DeepSeek's V3/R1 series, and it supports very
user-friendly local deployment features. GLM-4-32B-Base-0414 was
pre-trained on 15T of high-quality data, including a large amount of
reasoning-type synthetic data, laying the foundation for subsequent
reinforcement learning extensions. In the post-training stage, in
addition to human preference alignment for dialogue scenarios, we also
enhanced the model's performance in instruction following, engineering
code, and function calling using techniques such as rejection sampling
and reinforcement learning, strengthening the atomic capabilities
required for agent tasks. GLM-4-32B-0414 achieves good results in areas
such as engineering code, Artifact generation, function calling,
search-based Q&A, and report generation. Some benchmarks even rival
larger models like GPT-4o and DeepSeek-V3-0324 (671B).
GLM-Z1-9B-0414 is a surprise. We employed the
aforementioned series of techniques to train a 9B small-sized model that
maintains the open-source tradition. Despite its smaller scale,
GLM-Z1-9B-0414 still exhibits excellent capabilities in mathematical
reasoning and general tasks. Its overall performance is already at a
leading level among open-source models of the same size. Especially in
resource-constrained scenarios, this model achieves an excellent balance
between efficiency and effectiveness, providing a powerful option for
users seeking lightweight deployment
---
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/GLM-Z1-9B-0414-Q6_K-GGUF --hf-file glm-z1-9b-0414-q6_k.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/GLM-Z1-9B-0414-Q6_K-GGUF --hf-file glm-z1-9b-0414-q6_k.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/GLM-Z1-9B-0414-Q6_K-GGUF --hf-file glm-z1-9b-0414-q6_k.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/GLM-Z1-9B-0414-Q6_K-GGUF --hf-file glm-z1-9b-0414-q6_k.gguf -c 2048
```
|
mradermacher/medc_llm_based_on_qwen2.5-GGUF | mradermacher | 2025-04-28T09:59:15Z | 234 | 1 | transformers | [
"transformers",
"gguf",
"medical",
"zho",
"eng",
"fra",
"spa",
"por",
"deu",
"ita",
"rus",
"jpn",
"kor",
"vie",
"tha",
"ara",
"base_model:ggbaobao/medc_llm_based_on_qwen2.5",
"base_model:quantized:ggbaobao/medc_llm_based_on_qwen2.5",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-04-25T12:42:14Z | ---
base_model: ggbaobao/medc_llm_based_on_qwen2.5
language:
- zho
- eng
- fra
- spa
- por
- deu
- ita
- rus
- jpn
- kor
- vie
- tha
- ara
library_name: transformers
license: mit
quantized_by: mradermacher
tags:
- medical
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/ggbaobao/medc_llm_based_on_qwen2.5
<!-- provided-files -->
weighted/imatrix quants are available at https://huggingface.co/mradermacher/medc_llm_based_on_qwen2.5-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/medc_llm_based_on_qwen2.5-GGUF/resolve/main/medc_llm_based_on_qwen2.5.Q2_K.gguf) | Q2_K | 3.1 | |
| [GGUF](https://huggingface.co/mradermacher/medc_llm_based_on_qwen2.5-GGUF/resolve/main/medc_llm_based_on_qwen2.5.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
| [GGUF](https://huggingface.co/mradermacher/medc_llm_based_on_qwen2.5-GGUF/resolve/main/medc_llm_based_on_qwen2.5.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/medc_llm_based_on_qwen2.5-GGUF/resolve/main/medc_llm_based_on_qwen2.5.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
| [GGUF](https://huggingface.co/mradermacher/medc_llm_based_on_qwen2.5-GGUF/resolve/main/medc_llm_based_on_qwen2.5.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
| [GGUF](https://huggingface.co/mradermacher/medc_llm_based_on_qwen2.5-GGUF/resolve/main/medc_llm_based_on_qwen2.5.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/medc_llm_based_on_qwen2.5-GGUF/resolve/main/medc_llm_based_on_qwen2.5.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/medc_llm_based_on_qwen2.5-GGUF/resolve/main/medc_llm_based_on_qwen2.5.Q5_K_S.gguf) | Q5_K_S | 5.4 | |
| [GGUF](https://huggingface.co/mradermacher/medc_llm_based_on_qwen2.5-GGUF/resolve/main/medc_llm_based_on_qwen2.5.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
| [GGUF](https://huggingface.co/mradermacher/medc_llm_based_on_qwen2.5-GGUF/resolve/main/medc_llm_based_on_qwen2.5.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/medc_llm_based_on_qwen2.5-GGUF/resolve/main/medc_llm_based_on_qwen2.5.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
| [GGUF](https://huggingface.co/mradermacher/medc_llm_based_on_qwen2.5-GGUF/resolve/main/medc_llm_based_on_qwen2.5.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 -->
|
Triangle104/GLM-Z1-9B-0414-Q5_K_S-GGUF | Triangle104 | 2025-04-28T09:31:41Z | 0 | 0 | transformers | [
"transformers",
"gguf",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"zh",
"en",
"base_model:THUDM/GLM-Z1-9B-0414",
"base_model:quantized:THUDM/GLM-Z1-9B-0414",
"license:mit",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2025-04-28T09:31:07Z | ---
base_model: THUDM/GLM-Z1-9B-0414
language:
- zh
- en
library_name: transformers
license: mit
pipeline_tag: text-generation
tags:
- llama-cpp
- gguf-my-repo
---
# Triangle104/GLM-Z1-9B-0414-Q5_K_S-GGUF
This model was converted to GGUF format from [`THUDM/GLM-Z1-9B-0414`](https://huggingface.co/THUDM/GLM-Z1-9B-0414) 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/THUDM/GLM-Z1-9B-0414) 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 Triangle104/GLM-Z1-9B-0414-Q5_K_S-GGUF --hf-file glm-z1-9b-0414-q5_k_s.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/GLM-Z1-9B-0414-Q5_K_S-GGUF --hf-file glm-z1-9b-0414-q5_k_s.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/GLM-Z1-9B-0414-Q5_K_S-GGUF --hf-file glm-z1-9b-0414-q5_k_s.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/GLM-Z1-9B-0414-Q5_K_S-GGUF --hf-file glm-z1-9b-0414-q5_k_s.gguf -c 2048
```
|
mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF | mradermacher | 2025-04-28T07:41:10Z | 91 | 0 | transformers | [
"transformers",
"gguf",
"en",
"base_model:adamo1139/Yi-34B-200K-HESOYAM-TURTLE-0208-4CHAN",
"base_model:quantized:adamo1139/Yi-34B-200K-HESOYAM-TURTLE-0208-4CHAN",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"imatrix"
] | null | 2024-08-03T16:07:50Z | ---
base_model: adamo1139/Yi-34B-200K-HESOYAM-TURTLE-0208-4CHAN
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/adamo1139/Yi-34B-200K-HESOYAM-TURTLE-0208-4CHAN
<!-- provided-files -->
static quants are available at https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-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/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-IQ1_S.gguf) | i1-IQ1_S | 7.6 | for the desperate |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-IQ1_M.gguf) | i1-IQ1_M | 8.3 | mostly desperate |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.4 | |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.4 | |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-IQ2_S.gguf) | i1-IQ2_S | 11.0 | |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-IQ2_M.gguf) | i1-IQ2_M | 11.9 | |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-Q2_K.gguf) | i1-Q2_K | 12.9 | IQ3_XXS probably better |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 13.4 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-IQ3_XS.gguf) | i1-IQ3_XS | 14.3 | |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-Q3_K_S.gguf) | i1-Q3_K_S | 15.1 | IQ3_XS probably better |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-IQ3_S.gguf) | i1-IQ3_S | 15.1 | beats Q3_K* |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-IQ3_M.gguf) | i1-IQ3_M | 15.7 | |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.8 | IQ3_S probably better |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-Q3_K_L.gguf) | i1-Q3_K_L | 18.2 | IQ3_M probably better |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-IQ4_XS.gguf) | i1-IQ4_XS | 18.6 | |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-Q4_0.gguf) | i1-Q4_0 | 19.6 | fast, low quality |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-Q4_K_S.gguf) | i1-Q4_K_S | 19.7 | optimal size/speed/quality |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.8 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-Q5_K_S.gguf) | i1-Q5_K_S | 23.8 | |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-Q5_K_M.gguf) | i1-Q5_K_M | 24.4 | |
| [GGUF](https://huggingface.co/mradermacher/Yi-34B-200K-HESOYAM-TURTLE-0208-i1-GGUF/resolve/main/Yi-34B-200K-HESOYAM-TURTLE-0208.i1-Q6_K.gguf) | i1-Q6_K | 28.3 | 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 -->
|
Triangle104/Qwen2.5-7B-Q6_K-GGUF | Triangle104 | 2025-04-28T05:32:38Z | 6 | 0 | null | [
"gguf",
"llama-cpp",
"gguf-my-repo",
"text-generation",
"zho",
"eng",
"fra",
"spa",
"por",
"deu",
"ita",
"rus",
"jpn",
"kor",
"vie",
"tha",
"ara",
"base_model:Qwen/Qwen2.5-7B",
"base_model:quantized:Qwen/Qwen2.5-7B",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
] | text-generation | 2024-09-19T16:10:03Z | ---
base_model: Qwen/Qwen2.5-7B
language:
- zho
- eng
- fra
- spa
- por
- deu
- ita
- rus
- jpn
- kor
- vie
- tha
- ara
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen2.5-7B/blob/main/LICENSE
pipeline_tag: text-generation
tags:
- llama-cpp
- gguf-my-repo
---
# Triangle104/Qwen2.5-7B-Q6_K-GGUF
This model was converted to GGUF format from [`Qwen/Qwen2.5-7B`](https://huggingface.co/Qwen/Qwen2.5-7B) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
Refer to the [original model card](https://huggingface.co/Qwen/Qwen2.5-7B) for more details on the model.
## Use with llama.cpp
Install llama.cpp through brew (works on Mac and Linux)
```bash
brew install llama.cpp
```
Invoke the llama.cpp server or the CLI.
### CLI:
```bash
llama-cli --hf-repo Triangle104/Qwen2.5-7B-Q6_K-GGUF --hf-file qwen2.5-7b-q6_k.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo Triangle104/Qwen2.5-7B-Q6_K-GGUF --hf-file qwen2.5-7b-q6_k.gguf -c 2048
```
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
Step 1: Clone llama.cpp from GitHub.
```
git clone https://github.com/ggerganov/llama.cpp
```
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
```
cd llama.cpp && LLAMA_CURL=1 make
```
Step 3: Run inference through the main binary.
```
./llama-cli --hf-repo Triangle104/Qwen2.5-7B-Q6_K-GGUF --hf-file qwen2.5-7b-q6_k.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo Triangle104/Qwen2.5-7B-Q6_K-GGUF --hf-file qwen2.5-7b-q6_k.gguf -c 2048
```
|
nthehai01/Qwen2.5-7B-Instruct-Math-Code-breadcrumbs | nthehai01 | 2025-04-28T00:07:48Z | 5 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"mergekit",
"merge",
"conversational",
"zho",
"eng",
"fra",
"spa",
"por",
"deu",
"ita",
"rus",
"jpn",
"kor",
"vie",
"tha",
"ara",
"arxiv:2312.06795",
"base_model:Qwen/Qwen2.5-7B",
"base_model:merge:Qwen/Qwen2.5-7B",
"base_model:Qwen/Qwen2.5-7B-Instruct",
"base_model:merge:Qwen/Qwen2.5-7B-Instruct",
"base_model:Qwen/Qwen2.5-Coder-7B",
"base_model:merge:Qwen/Qwen2.5-Coder-7B",
"base_model:Qwen/Qwen2.5-Math-7B",
"base_model:merge:Qwen/Qwen2.5-Math-7B",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-03-10T05:40:42Z | ---
base_model:
- Qwen/Qwen2.5-7B
- Qwen/Qwen2.5-Coder-7B
- Qwen/Qwen2.5-7B-Instruct
- Qwen/Qwen2.5-Math-7B
library_name: transformers
tags:
- mergekit
- merge
language:
- zho
- eng
- fra
- spa
- por
- deu
- ita
- rus
- jpn
- kor
- vie
- tha
- ara
---
# nthehai01/Qwen2.5-7B-Instruct-Math-Code-breadcrumbs
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Performance
| Metric |Value|
|---------------------------------|----:|
|GSM8k (zero-shot) |90.06|
|HellaSwag (zero-Shot) |82.77|
|MBPP (zero-shot) |62.21|
## Merge Details
### Merge Method
This model was merged using the [Model Breadcrumbs](https://arxiv.org/abs/2312.06795) merge method using [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) as a base.
### Models Merged
The following models were included in the merge:
* [Qwen/Qwen2.5-Coder-7B](https://huggingface.co/Qwen/Qwen2.5-Coder-7B)
* [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
* [Qwen/Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: Qwen/Qwen2.5-7B
dtype: bfloat16
merge_method: breadcrumbs
parameters:
lambda: 0.9075603207928135
normalize: 1.0
slices:
- sources:
- layer_range: [0, 28]
model: Qwen/Qwen2.5-7B
- layer_range: [0, 28]
model: Qwen/Qwen2.5-Math-7B
parameters:
density: 0.11722197443445775
gamma: 0.07547691839721048
weight: 0.17267293536872041
- layer_range: [0, 28]
model: Qwen/Qwen2.5-Coder-7B
parameters:
density: 0.48352747334554935
gamma: 0.0753405327865558
weight: 0.11164770709858211
- layer_range: [0, 28]
model: Qwen/Qwen2.5-7B-Instruct
parameters:
density: 0.8190520808683315
gamma: 0.022307694128235696
weight: 0.7626295102691242
```
|
rdoshi21/detr-finetuned-franka | rdoshi21 | 2025-04-27T21:04:26Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"detr",
"object-detection",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | object-detection | 2025-04-27T21:04:13Z | ---
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] |
PQPQPQHUST/CACTUS-Qwen2.5-7B-Instruct-1 | PQPQPQHUST | 2025-04-27T18:19:15Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen2",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-04-27T18:19:06Z | ---
base_model: unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** PQPQPQHUST
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen2.5-7b-instruct-unsloth-bnb-4bit
This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
summer4love/jen | summer4love | 2025-04-27T12:19:08Z | 0 | 0 | null | [
"license:apache-2.0",
"region:us"
] | null | 2025-04-23T22:29:16Z | ---
license: apache-2.0
---
|
dgambettaphd/M_llm2_gen1_run0_W_doc1000_synt64_tot128_SYNLAST | dgambettaphd | 2025-04-27T05:02:18Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"unsloth",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-04-27T05:02:06Z | ---
library_name: transformers
tags:
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed] |
shanchen/limo-te-20250426_084152 | shanchen | 2025-04-26T16:15:18Z | 0 | 0 | transformers | [
"transformers",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"trl",
"sft",
"conversational",
"base_model:deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
"base_model:finetune:deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | 2025-04-26T15:32:08Z | ---
base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
library_name: transformers
model_name: limo-te-20250426_084152
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for limo-te-20250426_084152
This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B).
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="shanchen/limo-te-20250426_084152", 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/bitterman/s1/runs/6lugpaj6)
This model was trained with SFT.
### Framework versions
- TRL: 0.12.0
- Transformers: 4.51.3
- Pytorch: 2.5.1
- Datasets: 3.1.0
- Tokenizers: 0.21.1
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
``` |
genki10/BERT_V8_sp10_lw40_ex50_lo50_k2_k2_fold1 | genki10 | 2025-04-26T15:40:21Z | 0 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:google-bert/bert-base-uncased",
"base_model:finetune:google-bert/bert-base-uncased",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | 2025-04-26T15:25:41Z | ---
library_name: transformers
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: BERT_V8_sp10_lw40_ex50_lo50_k2_k2_fold1
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. -->
# BERT_V8_sp10_lw40_ex50_lo50_k2_k2_fold1
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5107
- Qwk: 0.6201
- Mse: 0.5101
- Rmse: 0.7142
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: 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: 100
### Training results
| Training Loss | Epoch | Step | Validation Loss | Qwk | Mse | Rmse |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|
| No log | 1.0 | 2 | 7.6515 | 0.0 | 7.6492 | 2.7657 |
| No log | 2.0 | 4 | 7.2604 | 0.0 | 7.2581 | 2.6941 |
| No log | 3.0 | 6 | 6.6180 | 0.0 | 6.6158 | 2.5721 |
| No log | 4.0 | 8 | 5.3839 | -0.0131 | 5.3819 | 2.3199 |
| No log | 5.0 | 10 | 4.1816 | 0.0 | 4.1795 | 2.0444 |
| No log | 6.0 | 12 | 3.3117 | 0.0 | 3.3097 | 1.8193 |
| No log | 7.0 | 14 | 2.5437 | 0.0 | 2.5420 | 1.5944 |
| No log | 8.0 | 16 | 1.9512 | 0.0645 | 1.9495 | 1.3963 |
| No log | 9.0 | 18 | 1.5546 | 0.0211 | 1.5531 | 1.2462 |
| No log | 10.0 | 20 | 1.2505 | 0.0 | 1.2490 | 1.1176 |
| No log | 11.0 | 22 | 1.0495 | 0.0 | 1.0481 | 1.0238 |
| No log | 12.0 | 24 | 0.9373 | 0.0 | 0.9360 | 0.9675 |
| No log | 13.0 | 26 | 0.8444 | 0.3069 | 0.8432 | 0.9183 |
| No log | 14.0 | 28 | 0.7818 | 0.2446 | 0.7807 | 0.8836 |
| No log | 15.0 | 30 | 0.6906 | 0.3398 | 0.6897 | 0.8305 |
| No log | 16.0 | 32 | 0.8725 | 0.2255 | 0.8714 | 0.9335 |
| No log | 17.0 | 34 | 0.7393 | 0.3427 | 0.7383 | 0.8593 |
| No log | 18.0 | 36 | 0.6456 | 0.4903 | 0.6447 | 0.8030 |
| No log | 19.0 | 38 | 0.5972 | 0.5306 | 0.5964 | 0.7723 |
| No log | 20.0 | 40 | 0.6241 | 0.3967 | 0.6233 | 0.7895 |
| No log | 21.0 | 42 | 0.6082 | 0.4253 | 0.6074 | 0.7794 |
| No log | 22.0 | 44 | 0.5812 | 0.5626 | 0.5804 | 0.7618 |
| No log | 23.0 | 46 | 0.6714 | 0.5680 | 0.6706 | 0.8189 |
| No log | 24.0 | 48 | 0.4739 | 0.5490 | 0.4731 | 0.6878 |
| No log | 25.0 | 50 | 0.5180 | 0.5103 | 0.5172 | 0.7192 |
| No log | 26.0 | 52 | 0.5498 | 0.5795 | 0.5489 | 0.7409 |
| No log | 27.0 | 54 | 0.5799 | 0.5851 | 0.5790 | 0.7609 |
| No log | 28.0 | 56 | 0.4841 | 0.5400 | 0.4832 | 0.6951 |
| No log | 29.0 | 58 | 0.5837 | 0.4843 | 0.5829 | 0.7635 |
| No log | 30.0 | 60 | 0.5404 | 0.5148 | 0.5396 | 0.7346 |
| No log | 31.0 | 62 | 0.4938 | 0.5625 | 0.4930 | 0.7021 |
| No log | 32.0 | 64 | 0.5099 | 0.6038 | 0.5093 | 0.7136 |
| No log | 33.0 | 66 | 0.6422 | 0.5813 | 0.6416 | 0.8010 |
| No log | 34.0 | 68 | 0.4865 | 0.6511 | 0.4860 | 0.6972 |
| No log | 35.0 | 70 | 0.4862 | 0.6741 | 0.4857 | 0.6970 |
| No log | 36.0 | 72 | 0.4878 | 0.6634 | 0.4874 | 0.6981 |
| No log | 37.0 | 74 | 0.4980 | 0.6667 | 0.4975 | 0.7053 |
| No log | 38.0 | 76 | 0.4810 | 0.6569 | 0.4805 | 0.6932 |
| No log | 39.0 | 78 | 0.5480 | 0.5754 | 0.5472 | 0.7397 |
| No log | 40.0 | 80 | 0.5823 | 0.5561 | 0.5815 | 0.7626 |
| No log | 41.0 | 82 | 0.5469 | 0.5734 | 0.5461 | 0.7390 |
| No log | 42.0 | 84 | 0.4820 | 0.6131 | 0.4812 | 0.6937 |
| No log | 43.0 | 86 | 0.4891 | 0.6231 | 0.4885 | 0.6989 |
| No log | 44.0 | 88 | 0.5023 | 0.6123 | 0.5016 | 0.7083 |
| No log | 45.0 | 90 | 0.5295 | 0.6258 | 0.5288 | 0.7272 |
| No log | 46.0 | 92 | 0.5997 | 0.5894 | 0.5991 | 0.7740 |
| No log | 47.0 | 94 | 0.5581 | 0.5967 | 0.5575 | 0.7466 |
| No log | 48.0 | 96 | 0.5917 | 0.5706 | 0.5909 | 0.7687 |
| No log | 49.0 | 98 | 0.5934 | 0.5756 | 0.5927 | 0.7698 |
| No log | 50.0 | 100 | 0.5316 | 0.6088 | 0.5310 | 0.7287 |
| No log | 51.0 | 102 | 0.5498 | 0.5986 | 0.5491 | 0.7410 |
| No log | 52.0 | 104 | 0.5961 | 0.5850 | 0.5953 | 0.7715 |
| No log | 53.0 | 106 | 0.6112 | 0.5802 | 0.6103 | 0.7812 |
| No log | 54.0 | 108 | 0.5362 | 0.6060 | 0.5355 | 0.7318 |
| No log | 55.0 | 110 | 0.5969 | 0.5910 | 0.5963 | 0.7722 |
| No log | 56.0 | 112 | 0.5527 | 0.6012 | 0.5520 | 0.7430 |
| No log | 57.0 | 114 | 0.5307 | 0.5982 | 0.5299 | 0.7280 |
| No log | 58.0 | 116 | 0.5171 | 0.5907 | 0.5164 | 0.7186 |
| No log | 59.0 | 118 | 0.5004 | 0.6131 | 0.4998 | 0.7069 |
| No log | 60.0 | 120 | 0.5098 | 0.5932 | 0.5092 | 0.7136 |
| No log | 61.0 | 122 | 0.4910 | 0.6149 | 0.4903 | 0.7002 |
| No log | 62.0 | 124 | 0.5223 | 0.6135 | 0.5215 | 0.7222 |
| No log | 63.0 | 126 | 0.4927 | 0.6308 | 0.4920 | 0.7014 |
| No log | 64.0 | 128 | 0.5097 | 0.6205 | 0.5091 | 0.7135 |
| No log | 65.0 | 130 | 0.5107 | 0.6201 | 0.5101 | 0.7142 |
### Framework versions
- Transformers 4.51.1
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0
|
befuturepl/embedding | befuturepl | 2025-04-24T19:20:28Z | 0 | 0 | pyannote-audio | [
"pyannote-audio",
"pytorch",
"pyannote",
"pyannote-audio-model",
"wespeaker",
"audio",
"voice",
"speech",
"speaker",
"speaker-recognition",
"speaker-verification",
"speaker-identification",
"speaker-embedding",
"dataset:voxceleb",
"license:cc-by-4.0",
"region:us"
] | null | 2025-04-24T18:25:02Z | ---
tags:
- pyannote
- pyannote-audio
- pyannote-audio-model
- wespeaker
- audio
- voice
- speech
- speaker
- speaker-recognition
- speaker-verification
- speaker-identification
- speaker-embedding
datasets:
- voxceleb
license: cc-by-4.0
inference: false
---
Using this open-source model in production?
Consider switching to [pyannoteAI](https://www.pyannote.ai) for better and faster options.
# 🎹 Wrapper around wespeaker-voxceleb-resnet34-LM
This model requires `pyannote.audio` version 3.1 or higher.
This is a wrapper around [WeSpeaker](https://github.com/wenet-e2e/wespeaker) `wespeaker-voxceleb-resnet34-LM` pretrained speaker embedding model, for use in `pyannote.audio`.
## Basic usage
```python
# instantiate pretrained model
from pyannote.audio import Model
model = Model.from_pretrained("pyannote/wespeaker-voxceleb-resnet34-LM")
```
```python
from pyannote.audio import Inference
inference = Inference(model, window="whole")
embedding1 = inference("speaker1.wav")
embedding2 = inference("speaker2.wav")
# `embeddingX` is (1 x D) numpy array extracted from the file as a whole.
from scipy.spatial.distance import cdist
distance = cdist(embedding1, embedding2, metric="cosine")[0,0]
# `distance` is a `float` describing how dissimilar speakers 1 and 2 are.
```
## Advanced usage
### Running on GPU
```python
import torch
inference.to(torch.device("cuda"))
embedding = inference("audio.wav")
```
### Extract embedding from an excerpt
```python
from pyannote.audio import Inference
from pyannote.core import Segment
inference = Inference(model, window="whole")
excerpt = Segment(13.37, 19.81)
embedding = inference.crop("audio.wav", excerpt)
# `embedding` is (1 x D) numpy array extracted from the file excerpt.
```
### Extract embeddings using a sliding window
```python
from pyannote.audio import Inference
inference = Inference(model, window="sliding",
duration=3.0, step=1.0)
embeddings = inference("audio.wav")
# `embeddings` is a (N x D) pyannote.core.SlidingWindowFeature
# `embeddings[i]` is the embedding of the ith position of the
# sliding window, i.e. from [i * step, i * step + duration].
```
## License
According to [this page](https://github.com/wenet-e2e/wespeaker/blob/master/docs/pretrained.md):
> The pretrained model in WeNet follows the license of it's corresponding dataset. For example, the pretrained model on VoxCeleb follows Creative Commons Attribution 4.0 International License., since it is used as license of the VoxCeleb dataset, see https://mm.kaist.ac.kr/datasets/voxceleb/.
## Citation
```bibtex
@inproceedings{Wang2023,
title={Wespeaker: A research and production oriented speaker embedding learning toolkit},
author={Wang, Hongji and Liang, Chengdong and Wang, Shuai and Chen, Zhengyang and Zhang, Binbin and Xiang, Xu and Deng, Yanlei and Qian, Yanmin},
booktitle={ICASSP 2023, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages={1--5},
year={2023},
organization={IEEE}
}
```
```bibtex
@inproceedings{Bredin23,
author={Hervé Bredin},
title={{pyannote.audio 2.1 speaker diarization pipeline: principle, benchmark, and recipe}},
year=2023,
booktitle={Proc. INTERSPEECH 2023},
pages={1983--1987},
doi={10.21437/Interspeech.2023-105}
}
```
|
Subsets and Splits