Downloads · 30 days
1.5K
3% of all-time downloads
Lewdiculous/L3-8B-Stheno-v3.3-32K-GGUF-IQ-Imatrix
L3-8B-Stheno-v3.3-32K-GGUF-IQ-Imatrix is a machine learning model from Lewdiculous. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
My GGUF-IQ-Imatrix quants for Sao10K/L3-8B-Stheno-v3.3-32K.
Downloads · 30 days
1.5K
3% of all-time downloads
All-time downloads
56.5K
Public
Repo size
83.4 GB
Likes
44
Public
Click a slice to open those files.
.gguf83.4 GB · 100%
From the Hugging Face model README
My GGUF-IQ-Imatrix quants for Sao10K/L3-8B-Stheno-v3.3-32K.
Sao10K with Stheno yet again, now bigger and better than ever! <br> I recommend checking his page for feedback and support.
[!IMPORTANT] Quantization process: <br> Imatrix data was generated from the FP16-GGUF and conversions directly from the BF16-GGUF. <br> This is a bit more disk and compute intensive but hopefully avoids any losses during conversion. <br> To run this model, please use the latest version of KoboldCpp. <br> If you noticed any issues let me know in the discussions.
<details> <summary>⇲ Click here to expand/hide information – General chart with relative quant parformances.</summary>[!NOTE] General usage: <br> For 8GB VRAM GPUs, I recommend the Q4_K_M-imat (4.89 BPW) quant for up to 12288 context sizes. <br>
Presets: <br> Some compatible SillyTavern presets can be found here (Virt's Roleplay Presets). <br> Check discussions such as this one for other recommendations and samplers.
</details>[!NOTE] Recommended read: <br>
"Which GGUF is right for me? (Opinionated)" by Artefact2
Click the image to view full size.
[!TIP] Personal-support: <br> I apologize for disrupting your experience. <br> Eventually I may be able to use a dedicated server for this, but for now hopefully these quants are helpful. <br> If you want and you are able to... <br> You can spare some change over here (Ko-fi). <br>
Author-support: <br> You can support the author at their own page.

Trained with compute from Backyard.ai | Thanks to them and @dynafire for helping me out.
Training Details: <br>Trained at 8K Context -> Expanded to 32K Context with PoSE training.
Dataset Modifications: <br>- Further Cleaned up Roleplaying Samples -> Quality Check <br>- Removed Low Quality Samples from Manual Check -> Increased Baseline Quality Floor <br>- More Creative Writing Samples -> 2x Samples <br>- Remade and Refined Detailed Instruct Data
Notes: <br>- Training run is much less aggressive than previous Stheno versions. <br>- This model works when tested in bf16 with the same configs as within the file. <br>- I do not know the effects quantisation has on it. <br>- Roleplays pretty well. Feels nice in my opinion. <br>- It has some issues on long context understanding and reasoning. Much better vs rope scaling normally though, so that is a plus. <br>- Reminder, this isn't a native 32K model. It has it's issues, but it's coherent and working well.
Sanity Check // Needle in a Haystack Results:
<br>- This is not as complex as RULER or NIAN, but it's a basic evaluator. Some improper train examples had Haystack scores ranging from Red to Orange for most of the extended contexts.

Wandb Run:

Relevant Axolotl Configurations: <br>-> Taken from winglian/Llama-3-8b-64k-PoSE <br>- I tried to find my own configs, hours of tinkering but the one he used worked best, so I stuck to it. <br>- 2M Rope Theta had the best loss results during training compared to other values. <br>- Leaving it at 500K rope wasn't that much worse, but 4M and 8M Theta made the grad_norm values worsen even if loss drops fast. <br>- Mixing in Pretraining Data was a PITA. Made it a lot worse with formatting. <br>- Pretraining / Noise made it worse at Haystack too? It wasn't all Green, Mainly Oranges. <br>- Improper / Bad Rope Theta shows in Grad_Norm exploding to thousands. It'll drop to low values alright, but it's a scary fast drop even with gradient clipping.
sequence_len: 8192
use_pose: true
pose_max_context_len: 32768
overrides_of_model_config:
rope_theta: 2000000.0
max_position_embeddings: 32768
# peft_use_dora: true
adapter: lora
peft_use_rslora: true
lora_model_dir:
lora_r: 256
lora_alpha: 256
lora_dropout: 0.1
lora_target_linear: true
lora_target_modules:
- gate_proj
- down_proj
- up_proj
- q_proj
- v_proj
- k_proj
- o_proj
warmup_steps: 80
gradient_accumulation_steps: 6
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine_with_min_lr
learning_rate: 0.00004
lr_scheduler_kwargs:
min_lr: 0.000004
</details>