RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
main
mlfoundations-dev_-_hp_abla…/README.md
ModelHub XC 2eeb271b1c 初始化项目，由ModelHub XC社区提供模型 
Model: RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf
Source: Original Platform
2026-06-04 00:02:17 +08:00

116 lines
7.2 KiB
Markdown
Raw Permalink Blame History

Quantization made by Richard Erkhov.
[Github](https://github.com/RichardErkhov)
[Discord](https://discord.gg/pvy7H8DZMG)
[Request more models](https://github.com/RichardErkhov/quant_request)
hp_ablations_llama3_epoch4_dcftv1.2 - GGUF
- Model creator: https://huggingface.co/mlfoundations-dev/
- Original model: https://huggingface.co/mlfoundations-dev/hp_ablations_llama3_epoch4_dcftv1.2/
| Name | Quant method | Size |
| ---- | ---- | ---- |
| [hp_ablations_llama3_epoch4_dcftv1.2.Q2_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.Q2_K.gguf) | Q2_K | 2.96GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.IQ3_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.IQ3_S.gguf) | IQ3_S | 3.43GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.IQ3_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.IQ3_M.gguf) | IQ3_M | 3.52GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.Q3_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.Q3_K.gguf) | Q3_K | 3.74GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.Q4_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.Q4_0.gguf) | Q4_0 | 4.34GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.Q4_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.Q4_K.gguf) | Q4_K | 4.58GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.Q4_1.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.Q4_1.gguf) | Q4_1 | 4.78GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.Q5_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.Q5_0.gguf) | Q5_0 | 5.21GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.Q5_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.Q5_K.gguf) | Q5_K | 5.34GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.Q5_1.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.Q5_1.gguf) | Q5_1 | 5.65GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.Q6_K.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.Q6_K.gguf) | Q6_K | 6.14GB |
| [hp_ablations_llama3_epoch4_dcftv1.2.Q8_0.gguf](https://huggingface.co/RichardErkhov/mlfoundations-dev_-_hp_ablations_llama3_epoch4_dcftv1.2-gguf/blob/main/hp_ablations_llama3_epoch4_dcftv1.2.Q8_0.gguf) | Q8_0 | 7.95GB |
Original model description:
---
library_name: transformers
license: llama3.1
base_model: meta-llama/Meta-Llama-3.1-8B
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: hp_ablations_llama3_epoch4_dcftv1.2
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. -->
# hp_ablations_llama3_epoch4_dcftv1.2
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/oh-dcft-v1.2_no-curation_gpt-4o-mini dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6648
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- total_eval_batch_size: 128
- 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: constant
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 1738
- num_epochs: 4.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.658 | 1.0 | 329 | 0.6595 |
| 0.6098 | 2.0 | 658 | 0.6488 |
| 0.5698 | 3.0 | 987 | 0.6519 |
| 0.5357 | 4.0 | 1316 | 0.6648 |
### Framework versions
- Transformers 4.46.1
- Pytorch 2.3.0
- Datasets 3.0.2
- Tokenizers 0.20.3
Reference in New Issue View Git Blame Copy Permalink