Downloads · 30 days
35
3% of all-time downloads
nlpguy_-_amdchess-v2-gguf
RichardErkhov/nlpguy_-_amdchess-v2-gguf
nlpguy_-_amdchess-v2-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
1K
Public
Repo size
3.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf4.5 GB · 100%
At a glance
- Access
- Public
- Created
- Mar 14, 2025
- Updated
- Mar 14, 2025
- SHA
- 7175603f
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
amdchess-v2 - GGUF
- Model creator: https://huggingface.co/nlpguy/
- Original model: https://huggingface.co/nlpguy/amdchess-v2/
| Name | Quant method | Size |
|---|---|---|
| amdchess-v2.Q2_K.gguf | Q2_K | 0.12GB |
| amdchess-v2.IQ3_XS.gguf | IQ3_XS | 0.14GB |
| amdchess-v2.IQ3_S.gguf | IQ3_S | 0.14GB |
| amdchess-v2.Q3_K_S.gguf | Q3_K_S | 0.14GB |
| amdchess-v2.IQ3_M.gguf | IQ3_M | 0.15GB |
| amdchess-v2.Q3_K.gguf | Q3_K | 0.16GB |
| amdchess-v2.Q3_K_M.gguf | Q3_K_M | 0.16GB |
| amdchess-v2.Q3_K_L.gguf | Q3_K_L | 0.17GB |
| amdchess-v2.IQ4_XS.gguf | IQ4_XS | 0.17GB |
| amdchess-v2.Q4_0.gguf | Q4_0 | 0.18GB |
| amdchess-v2.IQ4_NL.gguf | IQ4_NL | 0.18GB |
| amdchess-v2.Q4_K_S.gguf | Q4_K_S | 0.18GB |
| amdchess-v2.Q4_K.gguf | Q4_K | 0.19GB |
| amdchess-v2.Q4_K_M.gguf | Q4_K_M | 0.19GB |
| amdchess-v2.Q4_1.gguf | Q4_1 | 0.2GB |
| amdchess-v2.Q5_0.gguf | Q5_0 | 0.22GB |
| amdchess-v2.Q5_K_S.gguf | Q5_K_S | 0.22GB |
| amdchess-v2.Q5_K.gguf | Q5_K | 0.22GB |
| amdchess-v2.Q5_K_M.gguf | Q5_K_M | 0.22GB |
| amdchess-v2.Q5_1.gguf | Q5_1 | 0.23GB |
| amdchess-v2.Q6_K.gguf | Q6_K | 0.25GB |
| amdchess-v2.Q8_0.gguf | Q8_0 | 0.33GB |
Original model description:
library_name: transformers license: apache-2.0 base_model: reflex-ai/AMD-Llama-350M-Upgraded tags:
- generated_from_trainer model-index:
- name: amdchess-v2 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. -->
amdchess-v2
This model is a fine-tuned version of reflex-ai/AMD-Llama-350M-Upgraded on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7890
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 0.25
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.881 | 0.0030 | 5 | 7.5739 |
| 7.2662 | 0.0059 | 10 | 7.0051 |
| 6.8098 | 0.0089 | 15 | 6.7687 |
| 6.5801 | 0.0118 | 20 | 6.4508 |
| 6.0821 | 0.0148 | 25 | 6.0083 |
| 5.676 | 0.0177 | 30 | 5.6640 |
| 5.3014 | 0.0207 | 35 | 5.3851 |
| 5.1438 | 0.0236 | 40 | 5.0677 |
| 4.81 | 0.0266 | 45 | 4.8327 |
| 4.6369 | 0.0295 | 50 | 4.6192 |
| 4.5722 | 0.0325 | 55 | 4.3942 |
| 4.2333 | 0.0354 | 60 | 4.2079 |
| 4.1333 | 0.0384 | 65 | 4.0590 |
| 3.9003 | 0.0413 | 70 | 3.9275 |
| 3.7871 | 0.0443 | 75 | 3.8163 |
| 3.7472 | 0.0472 | 80 | 3.7052 |
| 3.5998 | 0.0502 | 85 | 3.6333 |
| 3.5839 | 0.0531 | 90 | 3.5451 |
| 3.4021 | 0.0561 | 95 | 3.4627 |
| 3.5244 | 0.0590 | 100 | 3.3776 |
| 3.3366 | 0.0620 | 105 | 3.2479 |
| 3.132 | 0.0649 | 110 | 3.1422 |
| 3.1709 | 0.0679 | 115 | 3.0535 |
| 3.0326 | 0.0708 | 120 | 2.9746 |
| 2.9901 | 0.0738 | 125 | 2.8892 |
| 2.7284 | 0.0767 | 130 | 2.8250 |
| 2.7125 | 0.0797 | 135 | 2.7152 |
| 2.7271 | 0.0826 | 140 | 2.6612 |
| 2.568 | 0.0856 | 145 | 2.5891 |
| 2.5652 | 0.0885 | 150 | 2.5402 |
| 2.5192 | 0.0915 | 155 | 2.4705 |
| 2.5085 | 0.0945 | 160 | 2.4344 |
| 2.4132 | 0.0974 | 165 | 2.4072 |
| 2.4028 | 0.1004 | 170 | 2.3522 |
| 2.2912 | 0.1033 | 175 | 2.3617 |
| 2.3289 | 0.1063 | 180 | 2.3058 |
| 2.2414 | 0.1092 | 185 | 2.2653 |
| 2.3884 | 0.1122 | 190 | 2.2534 |
| 2.2284 | 0.1151 | 195 | 2.2314 |
| 2.312 | 0.1181 | 200 | 2.1855 |
| 2.2398 | 0.1210 | 205 | 2.1578 |
| 2.0852 | 0.1240 | 210 | 2.1418 |
| 2.0324 | 0.1269 | 215 | 2.1151 |
| 2.1423 | 0.1299 | 220 | 2.1034 |
| 2.1088 | 0.1328 | 225 | 2.0716 |
| 2.1024 | 0.1358 | 230 | 2.0702 |
| 1.979 | 0.1387 | 235 | 2.0425 |
| 1.9784 | 0.1417 | 240 | 2.0265 |
| 2.0505 | 0.1446 | 245 | 2.0018 |
| 2.0258 | 0.1476 | 250 | 1.9822 |
| 1.9377 | 0.1505 | 255 | 1.9653 |
| 2.0453 | 0.1535 | 260 | 1.9555 |
| 1.9542 | 0.1564 | 265 | 1.9502 |
| 1.9549 | 0.1594 | 270 | 1.9284 |
| 1.9209 | 0.1623 | 275 | 1.9187 |
| 1.9262 | 0.1653 | 280 | 1.9016 |
| 1.9373 | 0.1682 | 285 | 1.8991 |
| 2.0095 | 0.1712 | 290 | 1.8975 |
| 1.9144 | 0.1741 | 295 | 1.8801 |
| 1.888 | 0.1771 | 300 | 1.8833 |
| 1.963 | 0.1800 | 305 | 1.8753 |
| 1.8349 | 0.1830 | 310 | 1.8722 |
| 1.872 | 0.1860 | 315 | 1.8508 |
| 1.7128 | 0.1889 | 320 | 1.8443 |
| 1.8132 | 0.1919 | 325 | 1.8342 |
| 1.842 | 0.1948 | 330 | 1.8299 |
| 1.8079 | 0.1978 | 335 | 1.8220 |
| 1.7931 | 0.2007 | 340 | 1.8203 |
| 2.028 | 0.2037 | 345 | 1.8179 |
| 1.7255 | 0.2066 | 350 | 1.8124 |
| 1.8479 | 0.2096 | 355 | 1.8061 |
| 1.7466 | 0.2125 | 360 | 1.8032 |
| 1.7946 | 0.2155 | 365 | 1.8021 |
| 1.8123 | 0.2184 | 370 | 1.7984 |
| 1.94 | 0.2214 | 375 | 1.7968 |
| 1.7952 | 0.2243 | 380 | 1.7943 |
| 1.7571 | 0.2273 | 385 | 1.7943 |
| 1.7723 | 0.2302 | 390 | 1.7927 |
| 1.7123 | 0.2332 | 395 | 1.7954 |
| 1.7593 | 0.2361 | 400 | 1.7911 |
| 1.9268 | 0.2391 | 405 | 1.7895 |
| 1.8277 | 0.2420 | 410 | 1.7892 |
| 1.777 | 0.2450 | 415 | 1.7890 |
| 1.721 | 0.2479 | 420 | 1.7890 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1
- Created
- Mar 14, 2025
- Updated
- Mar 14, 2025