Downloads · 30 days
66
4% of all-time downloads
RichardErkhov/lighteternal_-_Llama3-merge-biomed-8b-gguf
lighteternal_-_Llama3-merge-biomed-8b-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
66
4% of all-time downloads
All-time downloads
1.6K
Public
Repo size
92.9 GB
Likes
0
Public
Click a slice to open those files.
.gguf108 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
Llama3-merge-biomed-8b - GGUF
| Name | Quant method | Size |
|---|---|---|
| Llama3-merge-biomed-8b.Q2_K.gguf | Q2_K | 2.96GB |
| Llama3-merge-biomed-8b.IQ3_XS.gguf | IQ3_XS | 3.28GB |
| Llama3-merge-biomed-8b.IQ3_S.gguf | IQ3_S | 3.43GB |
| Llama3-merge-biomed-8b.Q3_K_S.gguf | Q3_K_S | 3.41GB |
| Llama3-merge-biomed-8b.IQ3_M.gguf | IQ3_M | 3.52GB |
| Llama3-merge-biomed-8b.Q3_K.gguf | Q3_K | 3.74GB |
| Llama3-merge-biomed-8b.Q3_K_M.gguf | Q3_K_M | 3.74GB |
| Llama3-merge-biomed-8b.Q3_K_L.gguf | Q3_K_L | 4.03GB |
| Llama3-merge-biomed-8b.IQ4_XS.gguf | IQ4_XS | 4.18GB |
| Llama3-merge-biomed-8b.Q4_0.gguf | Q4_0 | 4.34GB |
| Llama3-merge-biomed-8b.IQ4_NL.gguf | IQ4_NL | 4.38GB |
| Llama3-merge-biomed-8b.Q4_K_S.gguf | Q4_K_S | 4.37GB |
| Llama3-merge-biomed-8b.Q4_K.gguf | Q4_K | 4.58GB |
| Llama3-merge-biomed-8b.Q4_K_M.gguf | Q4_K_M | 4.58GB |
| Llama3-merge-biomed-8b.Q4_1.gguf | Q4_1 | 4.78GB |
| Llama3-merge-biomed-8b.Q5_0.gguf | Q5_0 | 5.21GB |
| Llama3-merge-biomed-8b.Q5_K_S.gguf | Q5_K_S | 5.21GB |
| Llama3-merge-biomed-8b.Q5_K.gguf | Q5_K | 5.34GB |
| Llama3-merge-biomed-8b.Q5_K_M.gguf | Q5_K_M | 5.34GB |
| Llama3-merge-biomed-8b.Q5_1.gguf | Q5_1 | 5.65GB |
| Llama3-merge-biomed-8b.Q6_K.gguf | Q6_K | 6.14GB |
| Llama3-merge-biomed-8b.Q8_0.gguf | Q8_0 | 7.95GB |
base_model:
This is a DARE-TIES Merge of Llama3-8b-Instruct + NousResearch/Hermes-2-Pro-Llama-3-8B + aaditya/Llama3-OpenBioLLM-8B. It is a simple experiment to assess whether combining models with strengths in general language understanding and biomedical knowledge can enhance performance on specialized tasks without compromising general applicability. The results indicate promising outcomes in areas like HendrycksTest tasks related to Biology and Medicine, as well as improvements in complex reasoning as seen in the ARC Challenge and Winogrande benchmarks.
I recommend using the prompt template of Llama3: https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3/
| Task | Metric | Ours (%) | Llama38BInstr. (%) | OpenBioLLM8B (%) |
|---|---|---|---|---|
| ARC Challenge | Accuracy | 59.39 | 57.17 | 55.38 |
| Normalized Accuracy | 63.65 | 60.75 | 58.62 | |
| Hellaswag | Accuracy | 62.59 | 59.04 | 61.83 |
| Normalized Accuracy | 81.53 | 78.55 | 80.76 | |
| Winogrande | Accuracy | 75.93 | 74.51 | 70.88 |
| GSM8K | Accuracy | 59.36 | 68.69 | 10.15 |
| HendrycksTest-Anatomy | Accuracy | 72.59 | 65.19 | 69.62 |
| HendrycksTest-Clinical Knowledge | Accuracy | 77.83 | 74.72 | 60.38 |
| HendrycksTest-College Biology | Accuracy | 81.94 | 79.86 | 79.86 |
| HendrycksTest-College Medicine | Accuracy | 69.36 | 63.58 | 70.52 |
| HendrycksTest-Medical Genetics | Accuracy | 86.00 | 80.00 | 80.00 |
| HendrycksTest-Professional Medicine | Accuracy | 77.94 | 71.69 | 77.94 |
This is a merge of pre-trained language models created using mergekit.
This model was merged using the DARE TIES merge method using meta-llama/Meta-Llama-3-8B-Instruct as a base.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: meta-llama/Meta-Llama-3-8B-Instruct
# Base model providing a general foundation without specific parameters
- model: meta-llama/Meta-Llama-3-8B-Instruct
parameters:
density: 0.60
weight: 0.5
- model: NousResearch/Hermes-2-Pro-Llama-3-8B
parameters:
density: 0.55
weight: 0.1
- model: aaditya/Llama3-OpenBioLLM-8B
parameters:
density: 0.55
weight: 0.4
merge_method: dare_ties
base_model: meta-llama/Meta-Llama-3-8B-Instruct
parameters:
int8_mask: true
dtype: bfloat16