Downloads · 30 days
94
8% of all-time downloads
Locutusque_-_lr-experiment1-7B-gguf
RichardErkhov/Locutusque_-_lr-experiment1-7B-gguf
Locutusque_-_lr-experiment1-7B-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
1.2K
Public
Repo size
82.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf95.2 GB · 100%
At a glance
- Access
- Public
- Created
- Sep 12, 2024
- Updated
- Sep 13, 2024
- SHA
- e17d56ae
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
lr-experiment1-7B - GGUF
- Model creator: https://huggingface.co/Locutusque/
- Original model: https://huggingface.co/Locutusque/lr-experiment1-7B/
| Name | Quant method | Size |
|---|---|---|
| lr-experiment1-7B.Q2_K.gguf | Q2_K | 2.53GB |
| lr-experiment1-7B.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| lr-experiment1-7B.IQ3_S.gguf | IQ3_S | 2.96GB |
| lr-experiment1-7B.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| lr-experiment1-7B.IQ3_M.gguf | IQ3_M | 3.06GB |
| lr-experiment1-7B.Q3_K.gguf | Q3_K | 3.28GB |
| lr-experiment1-7B.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| lr-experiment1-7B.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| lr-experiment1-7B.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| lr-experiment1-7B.Q4_0.gguf | Q4_0 | 3.83GB |
| lr-experiment1-7B.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| lr-experiment1-7B.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| lr-experiment1-7B.Q4_K.gguf | Q4_K | 4.07GB |
| lr-experiment1-7B.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| lr-experiment1-7B.Q4_1.gguf | Q4_1 | 4.24GB |
| lr-experiment1-7B.Q5_0.gguf | Q5_0 | 4.65GB |
| lr-experiment1-7B.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| lr-experiment1-7B.Q5_K.gguf | Q5_K | 4.78GB |
| lr-experiment1-7B.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| lr-experiment1-7B.Q5_1.gguf | Q5_1 | 5.07GB |
| lr-experiment1-7B.Q6_K.gguf | Q6_K | 5.53GB |
| lr-experiment1-7B.Q8_0.gguf | Q8_0 | 7.17GB |
Original model description:
library_name: transformers license: apache-2.0 datasets:
- Locutusque/hercules-v2.0
- CollectiveCognition/chats-data-2023-09-22 language:
- en
lr-experiment1-7B
The lr-experiment model series is a research project I'm conducting that I will be using to determine the best learning rate to use while fine-tuning Mistral. This model uses a learning rate of 2e-5 with a cosine scheduler and no warmup steps.
I used Locutusque/Hercules-2.0-Mistral-7B as a base model, and further fine-tuned it on CollectiveCognition/chats-data-2023-09-22 using QLoRA for 3 epochs. I will be keeping track of evaluation results, and will comparing it to upcoming models.
Evals
| Tasks | Version | Filter | n-shot | Metric | Value | Stderr | |
|---|---|---|---|---|---|---|---|
| agieval_nous | N/A | none | None | acc | 0.3645 | ± | 0.0093 |
| none | None | acc_norm | 0.3468 | ± | 0.0092 | ||
| - agieval_aqua_rat | 1 | none | None | acc | 0.2283 | ± | 0.0264 |
| none | None | acc_norm | 0.2283 | ± | 0.0264 | ||
| - agieval_logiqa_en | 1 | none | None | acc | 0.2965 | ± | 0.0179 |
| none | None | acc_norm | 0.3303 | ± | 0.0184 | ||
| - agieval_lsat_ar | 1 | none | None | acc | 0.2217 | ± | 0.0275 |
| none | None | acc_norm | 0.1783 | ± | 0.0253 | ||
| - agieval_lsat_lr | 1 | none | None | acc | 0.4039 | ± | 0.0217 |
| none | None | acc_norm | 0.3686 | ± | 0.0214 | ||
| - agieval_lsat_rc | 1 | none | None | acc | 0.4870 | ± | 0.0305 |
| none | None | acc_norm | 0.4424 | ± | 0.0303 | ||
| - agieval_sat_en | 1 | none | None | acc | 0.6408 | ± | 0.0335 |
| none | None | acc_norm | 0.5971 | ± | 0.0343 | ||
| - agieval_sat_en_without_passage | 1 | none | None | acc | 0.3932 | ± | 0.0341 |
| none | None | acc_norm | 0.3835 | ± | 0.0340 | ||
| - agieval_sat_math | 1 | none | None | acc | 0.3455 | ± | 0.0321 |
| none | None | acc_norm | 0.2727 | ± | 0.0301 |
| Groups | Version | Filter | n-shot | Metric | Value | Stderr | |
|---|---|---|---|---|---|---|---|
| agieval_nous | N/A | none | None | acc | 0.3645 | ± | 0.0093 |
| none | None | acc_norm | 0.3468 | ± | 0.0092 |
- Created
- Sep 12, 2024
- Updated
- Sep 13, 2024