Downloads · 30 days
270
18% of all-time downloads
argsearch_-_llama-7b-sft-float32-gguf
RichardErkhov/argsearch_-_llama-7b-sft-float32-gguf
argsearch_-_llama-7b-sft-float32-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
1.5K
Public
Repo size
76.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf88.7 GB · 100%
At a glance
- Access
- Public
- Created
- Jun 5, 2024
- Updated
- Jun 5, 2024
- SHA
- 837837ee
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
llama-7b-sft-float32 - GGUF
- Model creator: https://huggingface.co/argsearch/
- Original model: https://huggingface.co/argsearch/llama-7b-sft-float32/
| Name | Quant method | Size |
|---|---|---|
| llama-7b-sft-float32.Q2_K.gguf | Q2_K | 2.36GB |
| llama-7b-sft-float32.IQ3_XS.gguf | IQ3_XS | 2.6GB |
| llama-7b-sft-float32.IQ3_S.gguf | IQ3_S | 2.75GB |
| llama-7b-sft-float32.Q3_K_S.gguf | Q3_K_S | 2.75GB |
| llama-7b-sft-float32.IQ3_M.gguf | IQ3_M | 2.9GB |
| llama-7b-sft-float32.Q3_K.gguf | Q3_K | 3.07GB |
| llama-7b-sft-float32.Q3_K_M.gguf | Q3_K_M | 3.07GB |
| llama-7b-sft-float32.Q3_K_L.gguf | Q3_K_L | 3.35GB |
| llama-7b-sft-float32.IQ4_XS.gguf | IQ4_XS | 3.4GB |
| llama-7b-sft-float32.Q4_0.gguf | Q4_0 | 3.56GB |
| llama-7b-sft-float32.IQ4_NL.gguf | IQ4_NL | 3.58GB |
| llama-7b-sft-float32.Q4_K_S.gguf | Q4_K_S | 3.59GB |
| llama-7b-sft-float32.Q4_K.gguf | Q4_K | 3.8GB |
| llama-7b-sft-float32.Q4_K_M.gguf | Q4_K_M | 3.8GB |
| llama-7b-sft-float32.Q4_1.gguf | Q4_1 | 3.95GB |
| llama-7b-sft-float32.Q5_0.gguf | Q5_0 | 4.33GB |
| llama-7b-sft-float32.Q5_K_S.gguf | Q5_K_S | 4.33GB |
| llama-7b-sft-float32.Q5_K.gguf | Q5_K | 4.45GB |
| llama-7b-sft-float32.Q5_K_M.gguf | Q5_K_M | 4.45GB |
| llama-7b-sft-float32.Q5_1.gguf | Q5_1 | 4.72GB |
| llama-7b-sft-float32.Q6_K.gguf | Q6_K | 5.15GB |
| llama-7b-sft-float32.Q8_0.gguf | Q8_0 | 6.67GB |
Original model description:
tags:
- generated_from_trainer model-index:
- name: tmp_trainer 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. -->
tmp_trainer
This model was trained from scratch on an unknown 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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Created
- Jun 5, 2024
- Updated
- Jun 5, 2024