Add model card metadata
Browse files
README.md
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
license: other
|
| 4 |
+
base_model: aaditya/Llama3-OpenBioLLM-8B
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
+
library_name: llama.cpp
|
| 7 |
+
language:
|
| 8 |
+
- en
|
| 9 |
+
tags:
|
| 10 |
+
- gguf
|
| 11 |
+
- quantized
|
| 12 |
+
- ollama
|
| 13 |
+
- bioinformatics
|
| 14 |
+
quantized_by: richardyoung
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
# OpenBioLLM (Llama3-8B) GGUF
|
| 18 |
+
|
| 19 |
+
Quantized build of the OpenBioLLM Llama3-8B model for biomedical question answering, packaged for Ollama / llama.cpp runtimes. This release contains the Modelfile exported from the Ollama registry plus the matching GGUF binary.
|
| 20 |
+
|
| 21 |
+
- Base model: [`aaditya/Llama3-OpenBioLLM-8B`](https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B)
|
| 22 |
+
- Domain: Biomedical / life-sciences QA and reasoning
|
| 23 |
+
|
| 24 |
+
## Variant
|
| 25 |
+
|
| 26 |
+
| Variant | Size | Blob |
|
| 27 |
+
| --- | --- | --- |
|
| 28 |
+
| `latest` | 7.95 GB | `sha256-1cdfa5be309b5c9206925746aa8fa60601b3a04bc130d85f3257b65121408178` |
|
| 29 |
+
|
| 30 |
+
## Usage with Ollama
|
| 31 |
+
|
| 32 |
+
```bash
|
| 33 |
+
ollama create openbiollm -f modelfiles/openbiollm--latest.Modelfile
|
| 34 |
+
ollama run openbiollm
|
| 35 |
+
```
|
| 36 |
+
|
| 37 |
+
## Source
|
| 38 |
+
|
| 39 |
+
Originally published on my Ollama profile: https://ollama.com/richardyoung/openbiollm
|