Update model card: Add text-generation pipeline tag
#2
by
nielsr
HF Staff
- opened
README.md
CHANGED
|
@@ -1,16 +1,17 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
-
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
- ja
|
| 7 |
-
|
| 8 |
-
|
| 9 |
tags:
|
| 10 |
- pharmacy
|
| 11 |
- biology
|
| 12 |
- chemistry
|
| 13 |
- medical
|
|
|
|
| 14 |
---
|
| 15 |
|
| 16 |
# JPharmatron-7B
|
|
@@ -28,18 +29,18 @@ JPharmatron-7B is a 7B large language model designed for pharmaceutical applicat
|
|
| 28 |
|
| 29 |
The JPharmatron-7B is continually pre-trained using 8.8B tokens from Japanese and English datasets, based on Qwen2.5-7B. Compared to the JPharmatron-7B-base model, JPharmatron-7B has enhanced chat capabilities, obtained from Qwen2.5-7B-Instruct's chat vector.
|
| 30 |
|
| 31 |
-
-
|
| 32 |
-
-
|
| 33 |
-
-
|
| 34 |
-
-
|
| 35 |
-
-
|
| 36 |
|
| 37 |
### Model Sources [optional]
|
| 38 |
|
| 39 |
<!-- Provide the basic links for the model. -->
|
| 40 |
|
| 41 |
-
-
|
| 42 |
-
-
|
| 43 |
|
| 44 |
## Uses
|
| 45 |
|
|
@@ -95,4 +96,4 @@ See our preprint: [A Japanese Language Model and Three New Evaluation Benchmarks
|
|
| 95 |
|
| 96 |
## Model Card Authors [optional]
|
| 97 |
|
| 98 |
-
[@shinnosukeono](https://shinnosukeono.github.io/)
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model:
|
| 3 |
+
- EQUES/JPharmatron-7B-base
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
- ja
|
| 7 |
+
library_name: transformers
|
| 8 |
+
license: cc-by-sa-4.0
|
| 9 |
tags:
|
| 10 |
- pharmacy
|
| 11 |
- biology
|
| 12 |
- chemistry
|
| 13 |
- medical
|
| 14 |
+
pipeline_tag: text-generation
|
| 15 |
---
|
| 16 |
|
| 17 |
# JPharmatron-7B
|
|
|
|
| 29 |
|
| 30 |
The JPharmatron-7B is continually pre-trained using 8.8B tokens from Japanese and English datasets, based on Qwen2.5-7B. Compared to the JPharmatron-7B-base model, JPharmatron-7B has enhanced chat capabilities, obtained from Qwen2.5-7B-Instruct's chat vector.
|
| 31 |
|
| 32 |
+
- **Developed by:** EQUES Inc.
|
| 33 |
+
- **Funded by [optional]:** [GENIAC Project](https://www.meti.go.jp/policy/mono_info_service/geniac/index.html)
|
| 34 |
+
- **Model type:** Causal decoder-only
|
| 35 |
+
- **Language(s) (NLP):** Japanese, English
|
| 36 |
+
- **License:** CC-BY-SA-4.0
|
| 37 |
|
| 38 |
### Model Sources [optional]
|
| 39 |
|
| 40 |
<!-- Provide the basic links for the model. -->
|
| 41 |
|
| 42 |
+
- **Repository:** https://github.com/EQUES-Inc/pharma-LLM-eval
|
| 43 |
+
- **Paper [optional]:** [A Japanese Language Model and Three New Evaluation Benchmarks for Pharmaceutical NLP](https://arxiv.org/abs/2505.16661)
|
| 44 |
|
| 45 |
## Uses
|
| 46 |
|
|
|
|
| 96 |
|
| 97 |
## Model Card Authors [optional]
|
| 98 |
|
| 99 |
+
[@shinnosukeono](https://shinnosukeono.github.io/)
|