Commits · 93799c9df9e0c51cbc653da310668fbf2cd7a293 · OpenDAS / AutoAWQ

25 Aug, 2023 4 commits
- Remove tinychat · 93799c9d
  Casper authored Aug 25, 2023
  
  93799c9d
- Remove examples · 6924d106
  Casper authored Aug 25, 2023
  
  6924d106
- Move kernels to base directory · b85ee5c1
  Casper authored Aug 25, 2023
  
  b85ee5c1
- Merge remote-tracking branch 'origin/refactor-models' · 1e82667b
  Casper authored Aug 25, 2023
  
  1e82667b
24 Aug, 2023 3 commits
- Add speed benchmark · 46750ff9
  Casper Hansen authored Aug 24, 2023
  
  46750ff9
- Integrate fused modules into AWQ model loading · 63346c34
  Casper Hansen authored Aug 24, 2023
  
  63346c34
- Refactor into one setup.py · 870a9dc9
  Casper Hansen authored Aug 24, 2023
  
  870a9dc9
22 Aug, 2023 6 commits
- Implement loading correct sequence length based on config + custom max_new_tokens · d9bab50c
  Casper Hansen authored Aug 22, 2023
  
  d9bab50c
- Implemented fp16 and fp32 sanitization. · b53a9be2
  Casper Hansen authored Aug 22, 2023
  
  b53a9be2
- Fix #69 - sanitize NaN and infs. · 6708bbcb
  Casper Hansen authored Aug 22, 2023
  
  6708bbcb
- Set full quant as default. Always load unquantized with AutoModel instead of accelerate. · 321d74ff
  Casper Hansen authored Aug 22, 2023
  
  321d74ff
- Change entry_type to 'eval' for running tasks. Add better support for tasks... · bd899094
  Casper authored Aug 22, 2023
```
Change entry_type to 'eval' for running tasks. Add better support for tasks (use quant+unquant, multiple tasks, n_shot, batch_size.
```
  bd899094
- Merge remote-tracking branch 'upstream/main' into refactor-models · a1aa84cc
  Casper authored Aug 22, 2023
  
  a1aa84cc
21 Aug, 2023 2 commits
- Merge pull request #77 from Sakits/main · f3a90b77
  Jiaming Tang authored Aug 21, 2023
  
  f3a90b77
- [Minor] Temporarily change calibration dataset URL · 9c1ab9ba
  Jiaming Tang authored Aug 21, 2023
  
  9c1ab9ba
19 Aug, 2023 15 commits
- Modify README and examples · 2a243105
  Casper Hansen authored Aug 19, 2023
  
  2a243105
- FP16 weights example works · fd5b8c88
  Casper Hansen authored Aug 19, 2023
  
  fd5b8c88
- Revert · 0834fb46
  Casper Hansen authored Aug 19, 2023
  
  0834fb46
- Initial commit · d13bd43e
  Casper Hansen authored Aug 19, 2023
  
  d13bd43e
- TinyChat working with new framework · 8c8498e8
  Casper Hansen authored Aug 19, 2023
  
  8c8498e8
- Support Bloom models · 5c2c85fe
  Casper Hansen authored Aug 19, 2023
  
  5c2c85fe
- Fix logic for saving model · dd3010fb
  Casper Hansen authored Aug 19, 2023
  
  dd3010fb
- Support safetensors · 04e177ad
  Casper Hansen authored Aug 19, 2023
  
  04e177ad
- Support Falcon 7B+40B · d73d13b2
  Casper Hansen authored Aug 19, 2023
  
  d73d13b2
- Fix dict access · 06073073
  Casper Hansen authored Aug 19, 2023
  
  06073073
- Save model file with filename from quant_config · dcd58818
  Casper Hansen authored Aug 19, 2023
  
  dcd58818
- Create generate method · cc779bed
  Casper Hansen authored Aug 19, 2023
  
  cc779bed
- Load quantized model with saved quant_config · d68441d0
  Casper Hansen authored Aug 19, 2023
  
  d68441d0
- Make BaseAWQForCausalLM a torch.nn.Module · 84d23089
  Casper Hansen authored Aug 19, 2023
  
  84d23089
- Rename q_config -> quant_config. Include w_bit in quant_config. Save quant_config.json. · d35ade75
  Casper Hansen authored Aug 19, 2023
  
  d35ade75
18 Aug, 2023 7 commits
- Add OPT support · 6f30f051
  Casper Hansen authored Aug 18, 2023
  
  6f30f051
- Increase robustness of model loading · 471f811b
  Casper Hansen authored Aug 18, 2023
  
  471f811b
- Fix comment · 916fdf97
  Casper Hansen authored Aug 18, 2023
  
  916fdf97
- Refactor model class. Add LLaMa support (LLaMa-2, Vicuna, etc). · e2858cef
  Casper Hansen authored Aug 18, 2023
  
  e2858cef
- save_quantized working in all cases, from_quantized adapted. · d430694b
  Casper Hansen authored Aug 18, 2023
  
  d430694b
- Implement fallback calibration dataset (wikitext). · af4e0622
  Casper Hansen authored Aug 18, 2023
  
  af4e0622
- Implemented save_quantized. Generalize from_quantized.Add comments. · ed347704
  Casper Hansen authored Aug 18, 2023
  
  ed347704
17 Aug, 2023 3 commits
- Implement from_pretrained. Fix static methods and classmethods · 14d198c6
  Casper Hansen authored Aug 17, 2023
  
  14d198c6
- Cleanup code · 35ac58c7
  Casper Hansen authored Aug 17, 2023
  
  35ac58c7
- Create AutoAWQForCausalLM and load quantized models with from_quantized · e09dc751
  Casper Hansen authored Aug 17, 2023
  
  e09dc751