Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,7 @@ tags: []
|
|
| 6 |
# Model Card for Model ID
|
| 7 |
|
| 8 |
<!-- Provide a quick summary of what the model is/does. -->
|
|
|
|
| 9 |
This model aims to optimize QA & summerization tasks for the capstone project "Edge LLM - Reducing LLM Memory Footprint to < 2GB" in UW, sponsered by Amazon.
|
| 10 |
|
| 11 |
|
|
@@ -14,6 +15,7 @@ This model aims to optimize QA & summerization tasks for the capstone project "E
|
|
| 14 |
### Model Description
|
| 15 |
|
| 16 |
<!-- Provide a longer summary of what this model is. -->
|
|
|
|
| 17 |
Base model is Yao1627/Llama-2-7b-chat-hf-shortgpt-25-percent-lora, which has been pruned with shortgpt by 25%(8) layers according to block inference, fine-tuned by lora with timdettmers/openassistant-guanaco data.
|
| 18 |
|
| 19 |
This model is further fine-tuned by randomly-selected 10k sample of sharegpt dataset. Link is as followed: <https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/blob/main/ShareGPT_V3_unfiltered_cleaned_split_no_imsorry.json>
|
|
|
|
| 6 |
# Model Card for Model ID
|
| 7 |
|
| 8 |
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
This model aims to optimize QA & summerization tasks for the capstone project "Edge LLM - Reducing LLM Memory Footprint to < 2GB" in UW, sponsered by Amazon.
|
| 11 |
|
| 12 |
|
|
|
|
| 15 |
### Model Description
|
| 16 |
|
| 17 |
<!-- Provide a longer summary of what this model is. -->
|
| 18 |
+
|
| 19 |
Base model is Yao1627/Llama-2-7b-chat-hf-shortgpt-25-percent-lora, which has been pruned with shortgpt by 25%(8) layers according to block inference, fine-tuned by lora with timdettmers/openassistant-guanaco data.
|
| 20 |
|
| 21 |
This model is further fine-tuned by randomly-selected 10k sample of sharegpt dataset. Link is as followed: <https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/blob/main/ShareGPT_V3_unfiltered_cleaned_split_no_imsorry.json>
|