Downloads · 30 days
3
0% of all-time downloads
nlpguy_-_amdchess-v3-gguf
RichardErkhov/nlpguy_-_amdchess-v3-gguf
nlpguy_-_amdchess-v3-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
937
Public
Repo size
3.7 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
- 409fe5e3
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
amdchess-v3 - GGUF
- Model creator: https://huggingface.co/nlpguy/
- Original model: https://huggingface.co/nlpguy/amdchess-v3/
| Name | Quant method | Size |
|---|---|---|
| amdchess-v3.Q2_K.gguf | Q2_K | 0.12GB |
| amdchess-v3.IQ3_XS.gguf | IQ3_XS | 0.14GB |
| amdchess-v3.IQ3_S.gguf | IQ3_S | 0.14GB |
| amdchess-v3.Q3_K_S.gguf | Q3_K_S | 0.14GB |
| amdchess-v3.IQ3_M.gguf | IQ3_M | 0.15GB |
| amdchess-v3.Q3_K.gguf | Q3_K | 0.16GB |
| amdchess-v3.Q3_K_M.gguf | Q3_K_M | 0.16GB |
| amdchess-v3.Q3_K_L.gguf | Q3_K_L | 0.17GB |
| amdchess-v3.IQ4_XS.gguf | IQ4_XS | 0.17GB |
| amdchess-v3.Q4_0.gguf | Q4_0 | 0.18GB |
| amdchess-v3.IQ4_NL.gguf | IQ4_NL | 0.18GB |
| amdchess-v3.Q4_K_S.gguf | Q4_K_S | 0.18GB |
| amdchess-v3.Q4_K.gguf | Q4_K | 0.19GB |
| amdchess-v3.Q4_K_M.gguf | Q4_K_M | 0.19GB |
| amdchess-v3.Q4_1.gguf | Q4_1 | 0.2GB |
| amdchess-v3.Q5_0.gguf | Q5_0 | 0.22GB |
| amdchess-v3.Q5_K_S.gguf | Q5_K_S | 0.22GB |
| amdchess-v3.Q5_K.gguf | Q5_K | 0.22GB |
| amdchess-v3.Q5_K_M.gguf | Q5_K_M | 0.22GB |
| amdchess-v3.Q5_1.gguf | Q5_1 | 0.23GB |
| amdchess-v3.Q6_K.gguf | Q6_K | 0.25GB |
| amdchess-v3.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-v3 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-v3
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: 1.3595
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 0.25
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.6481 | 0.0030 | 5 | 7.3246 |
| 7.1045 | 0.0059 | 10 | 6.8823 |
| 6.5856 | 0.0089 | 15 | 6.5701 |
| 6.1701 | 0.0118 | 20 | 6.0976 |
| 5.7428 | 0.0148 | 25 | 5.7033 |
| 5.6064 | 0.0177 | 30 | 5.3915 |
| 5.096 | 0.0207 | 35 | 4.9774 |
| 4.6607 | 0.0236 | 40 | 4.6606 |
| 4.4224 | 0.0266 | 45 | 4.3904 |
| 4.2617 | 0.0295 | 50 | 4.1209 |
| 4.0037 | 0.0325 | 55 | 3.9065 |
| 3.8326 | 0.0354 | 60 | 3.7226 |
| 3.5859 | 0.0384 | 65 | 3.5654 |
| 3.5209 | 0.0413 | 70 | 3.3901 |
| 3.2487 | 0.0443 | 75 | 3.2572 |
| 3.111 | 0.0472 | 80 | 3.0276 |
| 2.8844 | 0.0502 | 85 | 2.8643 |
| 2.7695 | 0.0531 | 90 | 2.7651 |
| 2.7369 | 0.0561 | 95 | 2.6283 |
| 2.4932 | 0.0590 | 100 | 2.5018 |
| 2.3424 | 0.0620 | 105 | 2.3886 |
| 2.3822 | 0.0649 | 110 | 2.3002 |
| 2.1709 | 0.0679 | 115 | 2.1980 |
| 2.0245 | 0.0708 | 120 | 2.1401 |
| 2.0681 | 0.0738 | 125 | 2.0873 |
| 2.0483 | 0.0767 | 130 | 2.0304 |
| 2.1128 | 0.0797 | 135 | 1.9849 |
| 1.9851 | 0.0826 | 140 | 1.9261 |
| 1.8878 | 0.0856 | 145 | 1.8993 |
| 1.9144 | 0.0885 | 150 | 1.8522 |
| 1.8315 | 0.0915 | 155 | 1.8441 |
| 1.8331 | 0.0945 | 160 | 1.8086 |
| 1.6939 | 0.0974 | 165 | 1.7622 |
| 1.7247 | 0.1004 | 170 | 1.7290 |
| 1.7578 | 0.1033 | 175 | 1.7001 |
| 1.7665 | 0.1063 | 180 | 1.6987 |
| 1.6891 | 0.1092 | 185 | 1.6677 |
| 1.5931 | 0.1122 | 190 | 1.6512 |
| 1.6587 | 0.1151 | 195 | 1.6247 |
| 1.6703 | 0.1181 | 200 | 1.6061 |
| 1.5718 | 0.1210 | 205 | 1.5952 |
| 1.6414 | 0.1240 | 210 | 1.5690 |
| 1.5659 | 0.1269 | 215 | 1.5563 |
| 1.7055 | 0.1299 | 220 | 1.5354 |
| 1.5557 | 0.1328 | 225 | 1.5216 |
| 1.526 | 0.1358 | 230 | 1.5040 |
| 1.5513 | 0.1387 | 235 | 1.4986 |
| 1.4993 | 0.1417 | 240 | 1.4960 |
| 1.5187 | 0.1446 | 245 | 1.4842 |
| 1.4945 | 0.1476 | 250 | 1.4721 |
| 1.4969 | 0.1505 | 255 | 1.4705 |
| 1.4805 | 0.1535 | 260 | 1.4485 |
| 1.3945 | 0.1564 | 265 | 1.4433 |
| 1.4712 | 0.1594 | 270 | 1.4359 |
| 1.4197 | 0.1623 | 275 | 1.4292 |
| 1.4211 | 0.1653 | 280 | 1.4243 |
| 1.2673 | 0.1682 | 285 | 1.4238 |
| 1.4609 | 0.1712 | 290 | 1.4490 |
| 1.4633 | 0.1741 | 295 | 1.4193 |
| 1.4171 | 0.1771 | 300 | 1.4049 |
| 1.4011 | 0.1800 | 305 | 1.4024 |
| 1.2451 | 0.1830 | 310 | 1.3998 |
| 1.5563 | 0.1860 | 315 | 1.3952 |
| 1.3135 | 0.1889 | 320 | 1.3910 |
| 1.4269 | 0.1919 | 325 | 1.3905 |
| 1.3852 | 0.1948 | 330 | 1.3868 |
| 1.4691 | 0.1978 | 335 | 1.3806 |
| 1.4233 | 0.2007 | 340 | 1.3768 |
| 1.3279 | 0.2037 | 345 | 1.3780 |
| 1.3566 | 0.2066 | 350 | 1.3721 |
| 1.4463 | 0.2096 | 355 | 1.3688 |
| 1.3598 | 0.2125 | 360 | 1.3696 |
| 1.4411 | 0.2155 | 365 | 1.3668 |
| 1.3842 | 0.2184 | 370 | 1.3663 |
| 1.2909 | 0.2214 | 375 | 1.3654 |
| 1.3835 | 0.2243 | 380 | 1.3647 |
| 1.4124 | 0.2273 | 385 | 1.3619 |
| 1.3389 | 0.2302 | 390 | 1.3625 |
| 1.4634 | 0.2332 | 395 | 1.3609 |
| 1.2831 | 0.2361 | 400 | 1.3602 |
| 1.2724 | 0.2391 | 405 | 1.3599 |
| 1.3864 | 0.2420 | 410 | 1.3596 |
| 1.3273 | 0.2450 | 415 | 1.3595 |
| 1.3081 | 0.2479 | 420 | 1.3595 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.20.1
- Created
- Mar 14, 2025
- Updated
- Mar 14, 2025