Downloads · 30 days
144
5% of all-time downloads
mlfoundations-dev_-_llama3-1_8b_dcft-it-gguf
RichardErkhov/mlfoundations-dev_-_llama3-1_8b_dcft-it-gguf
mlfoundations-dev_-_llama3-1_8b_dcft-it-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
2.8K
Public
Repo size
92.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf108 GB · 100%
At a glance
- Access
- Public
- Created
- May 10, 2025
- Updated
- May 10, 2025
- SHA
- 8737cc30
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
llama3-1_8b_dcft-it - GGUF
- Model creator: https://huggingface.co/mlfoundations-dev/
- Original model: https://huggingface.co/mlfoundations-dev/llama3-1_8b_dcft-it/
| Name | Quant method | Size |
|---|---|---|
| llama3-1_8b_dcft-it.Q2_K.gguf | Q2_K | 2.96GB |
| llama3-1_8b_dcft-it.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| llama3-1_8b_dcft-it.IQ3_S.gguf | IQ3_S | 3.43GB |
| llama3-1_8b_dcft-it.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| llama3-1_8b_dcft-it.IQ3_M.gguf | IQ3_M | 3.52GB |
| llama3-1_8b_dcft-it.Q3_K.gguf | Q3_K | 3.74GB |
| llama3-1_8b_dcft-it.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| llama3-1_8b_dcft-it.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| llama3-1_8b_dcft-it.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| llama3-1_8b_dcft-it.Q4_0.gguf | Q4_0 | 4.34GB |
| llama3-1_8b_dcft-it.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| llama3-1_8b_dcft-it.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| llama3-1_8b_dcft-it.Q4_K.gguf | Q4_K | 4.58GB |
| llama3-1_8b_dcft-it.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| llama3-1_8b_dcft-it.Q4_1.gguf | Q4_1 | 4.78GB |
| llama3-1_8b_dcft-it.Q5_0.gguf | Q5_0 | 5.21GB |
| llama3-1_8b_dcft-it.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| llama3-1_8b_dcft-it.Q5_K.gguf | Q5_K | 5.34GB |
| llama3-1_8b_dcft-it.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| llama3-1_8b_dcft-it.Q5_1.gguf | Q5_1 | 5.65GB |
| llama3-1_8b_dcft-it.Q6_K.gguf | Q6_K | 6.14GB |
| llama3-1_8b_dcft-it.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: llama3-1_8b_dcft-it results: []
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
llama3-1_8b_dcft-it
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the mlfoundations-dev/DCLM-IT-Dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.7122
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: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 32
- total_train_batch_size: 512
- total_eval_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 1738
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7345 | 1.0 | 1555 | 0.7232 |
| 0.686 | 2.0 | 3110 | 0.7126 |
| 0.6421 | 3.0 | 4665 | 0.7122 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1
- Created
- May 10, 2025
- Updated
- May 10, 2025