Hugging Face's logo

Thireus
/
WizardLM-70B-V1.0-HF-4.0bpw-h8-exl2

Text Generation
Transformers
llama
Model card Files Community
Thireus commited on
Commit
1cc989d
•
1 Parent(s): 1e12142

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -11
README.md CHANGED
@@ -16,17 +16,17 @@ quantized_by: Thireus
16
 
17
  ## Models available:
18
 
19
- | Link | BITS (-b) | HEAD BITS (-hb) | MEASU-REMENT LENGTH (-ml) | LENGTH (-l) | CAL DATASET (-c) | Size | V. | Max Context Length | Base Model | Layers | VRAM Min | VRAM Max | PPL**
20
- | ------ | --------- | --------------- | ------------------------ | ----------- | ---------------- | ---- | ------- | ------------------ | ---- | ---- |------------------ | ------------------ | ------------------ |
21
- | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 40GB | 44GB | 4.1640625 |
22
- | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 39GB | 44GB | 4.2421875 |
23
- | _soon_ | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | ..GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | ..GB | ..GB | |
24
- | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h8-exl2/) | 4.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 39GB | 44GB | 4.24609375 |
25
- | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.0625 |
26
- | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 48GB | 52GB | 4.09765625 |
27
- | _soon_ | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | ..GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | ..GB | ..GB | |
28
- | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h8-exl2/) | 5.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.09765625 |
29
- | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-6.0bpw-h6-exl2/) | 6.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 49GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/fae6fb296c6db4e3b1314c49c030541bed98acb9) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 56GB | 60GB | 4.0703125 |
30
 
31
  \* wikitext-2-raw-v1
32
 
 
16
 
17
  ## Models available:
18
 
19
+ | Link | BITS (-b) | HEAD BITS (-hb) | MEASU-REMENT LENGTH (-ml) | LENGTH (-l) | CAL DATASET (-c) | Size | V. | Max Context Length | Base Model | Layers | VRAM Min | VRAM Max | PPL** | Comments                                                                                                                         |
20
+ | ------ | --------- | --------------- | ------------------------ | ----------- | ---------------- | ---- | ------- | ------------------ | ---- | ---- |------------------ | ------------------ | ------------------ | ---------------------------------------------------------------------------------- |
21
+ | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 39GB | 44GB | 4.15234375 | Good results | | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 40GB | 44GB | 4.1640625 | Model suffers from poor prompt understanding and logic is affected |
22
+ | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-4.0bpw-h6-exl2/) | 4.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 33GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 39GB | 44GB | 4.2421875 | Model suffers from poor prompt understanding and logic is affected |
23
+ | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-4.0bpw-h8-exl2/) | 4.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 35GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 39GB | 44GB | 4.24609375 | Model suffers from poor prompt understanding and logic is affected |
24
+ | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-FP32-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/c0dd3412d59c0bc776264512bf76264e954c221d) | 4096 | [FP32](https://huggingface.co/WizardLM/WizardLM-70B-V1.0) | 80 | 47GB | 52GB | 4.06640625 | Best so far. Good results |
25
+ | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h8-exl2/) | 5.0 | 8 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/a4f2663e310919f007c593030d56ca110f99c261) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
26
+ | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 44GB | [0.0.1](https://github.com/turboderp/exllamav2/tree/aee7a281708d5faff2ad0ea4b3a3a4b754f458f3) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 48GB | 52GB | 4.0625 | Model suffers from poor prompt understanding and logic is affected |
27
+ | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16-5.0bpw-h6-exl2/) | 5.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 41GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/ec5164b8a8e282b91aedb2af94dfeb89887656b7) | 4096 | [BF16](https://huggingface.co/Thireus/WizardLM-70B-V1.0-BF16) | 80 | 47GB | 52GB | 4.09765625 | Model suffers from poor prompt understanding and logic is affected |
28
+ | [here](https://huggingface.co/Thireus/WizardLM-70B-V1.0-HF-6.0bpw-h6-exl2/) | 6.0 | 6 | 2048 | 2048 | [0000.parquet](https://huggingface.co/datasets/wikitext/tree/refs%2Fconvert%2Fparquet/wikitext-2-raw-v1/train)* | 49GB | [0.0.2](https://github.com/turboderp/exllamav2/tree/fae6fb296c6db4e3b1314c49c030541bed98acb9) | 4096 | [FP16](https://huggingface.co/simsim314/WizardLM-70B-V1.0-HF) | 80 | 56GB | 60GB | 4.0703125 | Model suffers from poor prompt understanding and logic is affected |
29
+
30
 
31
  \* wikitext-2-raw-v1
32