Downloads · 30 days
4
0% of all-time downloads
mfirth_-_l3t_2-gguf
RichardErkhov/mfirth_-_l3t_2-gguf
mfirth_-_l3t_2-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
951
Public
Repo size
38.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf44.2 GB · 100%
At a glance
- Access
- Public
- Created
- Mar 27, 2025
- Updated
- Mar 27, 2025
- SHA
- 1126db6a
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
l3t_2 - GGUF
- Model creator: https://huggingface.co/mfirth/
- Original model: https://huggingface.co/mfirth/l3t_2/
| Name | Quant method | Size |
|---|---|---|
| l3t_2.Q2_K.gguf | Q2_K | 1.27GB |
| l3t_2.IQ3_XS.gguf | IQ3_XS | 1.38GB |
| l3t_2.IQ3_S.gguf | IQ3_S | 1.44GB |
| l3t_2.Q3_K_S.gguf | Q3_K_S | 1.44GB |
| l3t_2.IQ3_M.gguf | IQ3_M | 1.49GB |
| l3t_2.Q3_K.gguf | Q3_K | 1.57GB |
| l3t_2.Q3_K_M.gguf | Q3_K_M | 1.57GB |
| l3t_2.Q3_K_L.gguf | Q3_K_L | 1.69GB |
| l3t_2.IQ4_XS.gguf | IQ4_XS | 1.71GB |
| l3t_2.Q4_0.gguf | Q4_0 | 1.79GB |
| l3t_2.IQ4_NL.gguf | IQ4_NL | 1.79GB |
| l3t_2.Q4_K_S.gguf | Q4_K_S | 1.8GB |
| l3t_2.Q4_K.gguf | Q4_K | 1.88GB |
| l3t_2.Q4_K_M.gguf | Q4_K_M | 1.88GB |
| l3t_2.Q4_1.gguf | Q4_1 | 1.95GB |
| l3t_2.Q5_0.gguf | Q5_0 | 2.11GB |
| l3t_2.Q5_K_S.gguf | Q5_K_S | 2.11GB |
| l3t_2.Q5_K.gguf | Q5_K | 2.16GB |
| l3t_2.Q5_K_M.gguf | Q5_K_M | 2.16GB |
| l3t_2.Q5_1.gguf | Q5_1 | 2.28GB |
| l3t_2.Q6_K.gguf | Q6_K | 2.46GB |
| l3t_2.Q8_0.gguf | Q8_0 | 3.19GB |
Original model description:
library_name: transformers license: llama3.2 base_model: meta-llama/Llama-3.2-3B-Instruct tags:
- generated_from_trainer datasets:
- axolotl_format_data_llama.json model-index:
- name: models/llama-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. --> <details><summary>See axolotl config</summary>
axolotl version: 0.5.3.dev41+g5e9fa33f
base_model: meta-llama/Llama-3.2-3B-Instruct
datasets:
- path: axolotl_format_data_llama.json
type: input_output
dataset_prepared_path: last_run_prepared
output_dir: ./models/llama-2
sequence_length: 2048
wandb_project: agent-v0
wandb_name: llama-3b
train_on_inputs: false
gradient_checkpointing: true
gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_torch
learning_rate: 2e-5
bf16: true
tf32: false
logging_steps: 5
flash_attention: true
warmup_steps: 10
saves_per_epoch: 1
weight_decay: 0.0
deepspeed: axolotl/deepspeed_configs/zero3_bf16.json
special_tokens:
pad_token: <|end_of_text|>
models/llama-2
This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on the axolotl_format_data_llama.json 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: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- 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_steps: 10
- num_epochs: 3
Training results
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3
- Created
- Mar 27, 2025
- Updated
- Mar 27, 2025