Compare commits

...

10 Commits

9 changed files with 32 additions and 4 deletions

3
.gitattributes vendored
View File

@@ -49,3 +49,6 @@ openhermes-2.5-strix-philosophy-mistral-7b.Q4_K_S.gguf filter=lfs diff=lfs merge
openhermes-2.5-strix-philosophy-mistral-7b.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text openhermes-2.5-strix-philosophy-mistral-7b.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
openhermes-2.5-strix-philosophy-mistral-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text openhermes-2.5-strix-philosophy-mistral-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
openhermes-2.5-strix-philosophy-mistral-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text openhermes-2.5-strix-philosophy-mistral-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
openhermes-2.5-strix-philosophy-mistral-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
openhermes-2.5-strix-philosophy-mistral-7b[[:space:]]Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
openhermes-2.5-strix-philosophy-mistral-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text

View File

@@ -3,7 +3,7 @@ language:
- en - en
license: apache-2.0 license: apache-2.0
tags: tags:
- transformers - trl
- text-generation-inference - text-generation-inference
- unsloth - unsloth
- mistral - mistral
@@ -11,11 +11,33 @@ tags:
base_model: teknium/OpenHermes-2.5-Mistral-7B base_model: teknium/OpenHermes-2.5-Mistral-7B
datasets: datasets:
- sayhan/strix-philosophy-qa - sayhan/strix-philosophy-qa
library_name: trl library_name: transformers
--- ---
![image/png](https://cdn-uploads.huggingface.co/production/uploads/65aa2d4b356bf23b4a4da247/nN4JZlIMeF-K2sFYfhLLT.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65aa2d4b356bf23b4a4da247/nN4JZlIMeF-K2sFYfhLLT.png)
# OpenHermes 2.5 Stix Philosophy Mistral 7B # OpenHermes 2.5 Stix Philosophy Mistral 7B
- **Finetuned by:** [sayhan](https://huggingface.co/sayhan) - **Finetuned by:** [sayhan](https://huggingface.co/sayhan)
- **License:** apache-2.0 - **License:** [apache-2.0](https://choosealicense.com/licenses/apache-2.0/)
- **Finetuned from model :** [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) - **Finetuned from model :** [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
- **Dataset:** [sayhan/strix-philosophy-qa](https://huggingface.co/datasets/sayhan/strix-philosophy-qa) - **Dataset:** [sayhan/strix-philosophy-qa](https://huggingface.co/datasets/sayhan/strix-philosophy-qa)
---
**LoRA rank:** 8
**LoRA alpha:** 16
**LoRA dropout:** 0
**Rank-stabilized LoRA:** Yes
**Number of epochs:** 3
**Learning rate:** 1e-5
**Batch size:** 2
**Gradient accumulation steps:** 4
**Weight decay:** 0.01
**Target modules:**
```
- Query projection (`q_proj`)
- Key projection (`k_proj`)
- Value projection (`v_proj`)
- Output projection (`o_proj`)
- Gate projection (`gate_proj`)
- Up projection (`up_proj`)
- Down projection (`down_proj`)
```

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e9128f0e34d5668450c3a29a0885685aba5bf0d22ff4e876d4e39861b314b380
size 14484764640