Hugging Face's logo

RichardErkhov
/
mlfoundations-dev_-_OH_DCFT_V3_wo_glaive_code_assistant-gguf

GGUF
conversational
Model card Files
xet
 Community

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

OH_DCFT_V3_wo_glaive_code_assistant - GGUF

Name Quant method Size
OH_DCFT_V3_wo_glaive_code_assistant.Q2_K.gguf Q2_K 2.96GB
OH_DCFT_V3_wo_glaive_code_assistant.IQ3_XS.gguf IQ3_XS 3.28GB
OH_DCFT_V3_wo_glaive_code_assistant.IQ3_S.gguf IQ3_S 3.43GB
OH_DCFT_V3_wo_glaive_code_assistant.Q3_K_S.gguf Q3_K_S 3.41GB
OH_DCFT_V3_wo_glaive_code_assistant.IQ3_M.gguf IQ3_M 3.52GB
OH_DCFT_V3_wo_glaive_code_assistant.Q3_K.gguf Q3_K 3.74GB
OH_DCFT_V3_wo_glaive_code_assistant.Q3_K_M.gguf Q3_K_M 3.74GB
OH_DCFT_V3_wo_glaive_code_assistant.Q3_K_L.gguf Q3_K_L 4.03GB
OH_DCFT_V3_wo_glaive_code_assistant.IQ4_XS.gguf IQ4_XS 4.18GB
OH_DCFT_V3_wo_glaive_code_assistant.Q4_0.gguf Q4_0 4.34GB
OH_DCFT_V3_wo_glaive_code_assistant.IQ4_NL.gguf IQ4_NL 4.38GB
OH_DCFT_V3_wo_glaive_code_assistant.Q4_K_S.gguf Q4_K_S 4.37GB
OH_DCFT_V3_wo_glaive_code_assistant.Q4_K.gguf Q4_K 4.58GB
OH_DCFT_V3_wo_glaive_code_assistant.Q4_K_M.gguf Q4_K_M 4.58GB
OH_DCFT_V3_wo_glaive_code_assistant.Q4_1.gguf Q4_1 4.78GB
OH_DCFT_V3_wo_glaive_code_assistant.Q5_0.gguf Q5_0 5.21GB
OH_DCFT_V3_wo_glaive_code_assistant.Q5_K_S.gguf Q5_K_S 5.21GB
OH_DCFT_V3_wo_glaive_code_assistant.Q5_K.gguf Q5_K 5.34GB
OH_DCFT_V3_wo_glaive_code_assistant.Q5_K_M.gguf Q5_K_M 5.34GB
OH_DCFT_V3_wo_glaive_code_assistant.Q5_1.gguf Q5_1 5.65GB
OH_DCFT_V3_wo_glaive_code_assistant.Q6_K.gguf Q6_K 6.14GB
OH_DCFT_V3_wo_glaive_code_assistant.Q8_0.gguf Q8_0 7.95GB

Original model description:

library_name: transformers license: llama3.1 base_model: meta-llama/Llama-3.1-8B tags: - llama-factory - full - generated_from_trainer model-index: - name: OH_DCFT_V3_wo_glaive_code_assistant results: []

OH_DCFT_V3_wo_glaive_code_assistant

This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the mlfoundations-dev/OH_DCFT_V3_wo_glaive_code_assistant dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6738

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: 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
0.6705 0.9984 312 0.6830
0.6388 2.0 625 0.6723
0.5952 2.9952 936 0.6738

Framework versions

  • Transformers 4.45.2
  • Pytorch 2.3.0
  • Datasets 2.21.0
  • Tokenizers 0.20.1
Downloads last month
172
GGUF
Model size
8B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support