Hugging Face's logo

RichardErkhov
/
utter-project_-_EuroLLM-1.7B-Instruct-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

EuroLLM-1.7B-Instruct - GGUF

Name Quant method Size
EuroLLM-1.7B-Instruct.Q2_K.gguf Q2_K 0.67GB
EuroLLM-1.7B-Instruct.IQ3_XS.gguf IQ3_XS 0.74GB
EuroLLM-1.7B-Instruct.IQ3_S.gguf IQ3_S 0.76GB
EuroLLM-1.7B-Instruct.Q3_K_S.gguf Q3_K_S 0.76GB
EuroLLM-1.7B-Instruct.IQ3_M.gguf IQ3_M 0.78GB
EuroLLM-1.7B-Instruct.Q3_K.gguf Q3_K 0.82GB
EuroLLM-1.7B-Instruct.Q3_K_M.gguf Q3_K_M 0.82GB
EuroLLM-1.7B-Instruct.Q3_K_L.gguf Q3_K_L 0.86GB
EuroLLM-1.7B-Instruct.IQ4_XS.gguf IQ4_XS 0.9GB
EuroLLM-1.7B-Instruct.Q4_0.gguf Q4_0 0.93GB
EuroLLM-1.7B-Instruct.IQ4_NL.gguf IQ4_NL 0.94GB
EuroLLM-1.7B-Instruct.Q4_K_S.gguf Q4_K_S 0.94GB
EuroLLM-1.7B-Instruct.Q4_K.gguf Q4_K 0.97GB
EuroLLM-1.7B-Instruct.Q4_K_M.gguf Q4_K_M 0.97GB
EuroLLM-1.7B-Instruct.Q4_1.gguf Q4_1 1.02GB
EuroLLM-1.7B-Instruct.Q5_0.gguf Q5_0 1.1GB
EuroLLM-1.7B-Instruct.Q5_K_S.gguf Q5_K_S 1.1GB
EuroLLM-1.7B-Instruct.Q5_K.gguf Q5_K 1.12GB
EuroLLM-1.7B-Instruct.Q5_K_M.gguf Q5_K_M 1.12GB
EuroLLM-1.7B-Instruct.Q5_1.gguf Q5_1 1.18GB
EuroLLM-1.7B-Instruct.Q6_K.gguf Q6_K 1.27GB
EuroLLM-1.7B-Instruct.Q8_0.gguf Q8_0 1.64GB

Original model description:

library_name: transformers base_model: Unbabel/EuroLLM-1B-annealed-fw tags: - generated_from_trainer model-index: - name: experiments/EuroLLM/EuroLLM-1B-annealed-fw-euroblocks-v0.1 results: []

Built with Axolotl

experiments/EuroLLM/EuroLLM-1B-annealed-fw-euroblocks-v0.1

This model is a fine-tuned version of Unbabel/EuroLLM-1B-annealed-fw 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: 7e-06
  • train_batch_size: 2
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 24
  • total_train_batch_size: 96
  • total_eval_batch_size: 2
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 300
  • num_epochs: 4

Training results

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.2.2+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
100
GGUF
Model size
2B 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