Downloads · 30 days
147
6% of all-time downloads
hyperdemocracy_-_usclm-phi-mk1-gguf
RichardErkhov/hyperdemocracy_-_usclm-phi-mk1-gguf
hyperdemocracy_-_usclm-phi-mk1-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
2.6K
Public
Repo size
2.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf2.4 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 23, 2024
- Updated
- Oct 23, 2024
- SHA
- 137ea0fc
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
usclm-phi-mk1 - GGUF
- Model creator: https://huggingface.co/hyperdemocracy/
- Original model: https://huggingface.co/hyperdemocracy/usclm-phi-mk1/
| Name | Quant method | Size |
|---|---|---|
| usclm-phi-mk1.Q2_K.gguf | Q2_K | 0.07GB |
| usclm-phi-mk1.IQ3_XS.gguf | IQ3_XS | 0.08GB |
| usclm-phi-mk1.IQ3_S.gguf | IQ3_S | 0.08GB |
| usclm-phi-mk1.Q3_K_S.gguf | Q3_K_S | 0.08GB |
| usclm-phi-mk1.IQ3_M.gguf | IQ3_M | 0.08GB |
| usclm-phi-mk1.Q3_K.gguf | Q3_K | 0.09GB |
| usclm-phi-mk1.Q3_K_M.gguf | Q3_K_M | 0.09GB |
| usclm-phi-mk1.Q3_K_L.gguf | Q3_K_L | 0.09GB |
| usclm-phi-mk1.IQ4_XS.gguf | IQ4_XS | 0.09GB |
| usclm-phi-mk1.Q4_0.gguf | Q4_0 | 0.1GB |
| usclm-phi-mk1.IQ4_NL.gguf | IQ4_NL | 0.1GB |
| usclm-phi-mk1.Q4_K_S.gguf | Q4_K_S | 0.1GB |
| usclm-phi-mk1.Q4_K.gguf | Q4_K | 0.1GB |
| usclm-phi-mk1.Q4_K_M.gguf | Q4_K_M | 0.1GB |
| usclm-phi-mk1.Q4_1.gguf | Q4_1 | 0.1GB |
| usclm-phi-mk1.Q5_0.gguf | Q5_0 | 0.11GB |
| usclm-phi-mk1.Q5_K_S.gguf | Q5_K_S | 0.11GB |
| usclm-phi-mk1.Q5_K.gguf | Q5_K | 0.11GB |
| usclm-phi-mk1.Q5_K_M.gguf | Q5_K_M | 0.11GB |
| usclm-phi-mk1.Q5_1.gguf | Q5_1 | 0.12GB |
| usclm-phi-mk1.Q6_K.gguf | Q6_K | 0.13GB |
| usclm-phi-mk1.Q8_0.gguf | Q8_0 | 0.16GB |
Original model description:
tags:
- generated_from_trainer datasets:
- hyperdemocracy/usc-llm-text metrics:
- accuracy model-index:
- name: usclm-phi-mk1
results:
- task:
name: Causal Language Modeling
type: text-generation
dataset:
name: hyperdemocracy/usc-llm-text
type: hyperdemocracy/usc-llm-text
metrics:
- name: Accuracy type: accuracy value: 0.5483453834880313
- task:
name: Causal Language Modeling
type: text-generation
dataset:
name: hyperdemocracy/usc-llm-text
type: hyperdemocracy/usc-llm-text
metrics:
<!-- 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. -->
usclm-phi-mk1
This model is a fine-tuned version of on the hyperdemocracy/usc-llm-text dataset. It achieves the following results on the evaluation set:
- Loss: 2.4198
- Accuracy: 0.5483
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-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- total_train_batch_size: 8
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
- mixed_precision_training: Native AMP
Training results
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Created
- Oct 23, 2024
- Updated
- Oct 23, 2024