Update README.md

README.md

@@ -1,49 +1,69 @@
 ---
-base_model:
-- johnsnowlabs/JSL-MedMNX-7B
-- dmis-lab/meerkat-7b-v1.0
+license: cc-by-nc-nd-4.0
+language:
+- en
 library_name: transformers
 tags:
-- mergekit
-- merge
-
+- reward model
+- RLHF
+- medical
 ---
-# merge
 
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+# JSL-MedMNX-7B-v2.0
+
 
-## Merge Details
-### Merge Method
+[<img src="https://repository-images.githubusercontent.com/104670986/2e728700-ace4-11ea-9cfc-f3e060b25ddf">](http://www.johnsnowlabs.com)
 
-This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [johnsnowlabs/JSL-MedMNX-7B](https://huggingface.co/johnsnowlabs/JSL-MedMNX-7B) as a base.
 
-### Models Merged
+This model is developed by [John Snow Labs](https://www.johnsnowlabs.com/).
+Performance on biomedical benchmarks: [Open Medical LLM Leaderboard](https://huggingface.co/spaces/openlifescienceai/open_medical_llm_leaderboard).
 
-The following models were included in the merge:
-* [dmis-lab/meerkat-7b-v1.0](https://huggingface.co/dmis-lab/meerkat-7b-v1.0)
+This model is available under a [CC-BY-NC-ND](https://creativecommons.org/licenses/by-nc-nd/4.0/deed.en) license and must also conform to this [Acceptable Use Policy](https://huggingface.co/johnsnowlabs). If you need to license  this model for commercial use, please contact us at info@johnsnowlabs.com.
 
-### Configuration
+## 💻 Usage
 
-The following YAML configuration was used to produce this model:
+```python
+!pip install -qU transformers accelerate
 
-```yaml
+from transformers import AutoTokenizer
+import transformers
+import torch
 
-models:
-  - model: johnsnowlabs/JSL-MedMNX-7B
-    parameters:
-      density: 0.53
-      weight: 0.4
-  - model: dmis-lab/meerkat-7b-v1.0
-    parameters:
-      density: 0.53
-      weight: 0.3
- 
-merge_method: dare_ties
-tokenizer_source: union
-base_model: johnsnowlabs/JSL-MedMNX-7B
-parameters:
-  int8_mask: true
-dtype: bfloat16
+model = "johnsnowlabs/JSL-MedMNX-7B"
+messages = [{"role": "user", "content": "What is a large language model?"}]
 
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
 
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
 ```
+
+## 🏆 Evaluation
+
+|             Tasks             |Version|Filter|n-shot| Metric |Value |   |Stderr|
+|-------------------------------|-------|------|-----:|--------|-----:|---|-----:|
+|stem                           |N/A    |none  |     0|acc     |0.6085|±  |0.0057|
+|                               |       |none  |     0|acc_norm|0.5700|±  |0.0067|
+| - medmcqa                     |Yaml   |none  |     0|acc     |0.5625|±  |0.0077|
+|                               |       |none  |     0|acc_norm|0.5625|±  |0.0077|
+| - medqa_4options              |Yaml   |none  |     0|acc     |0.5947|±  |0.0138|
+|                               |       |none  |     0|acc_norm|0.5947|±  |0.0138|
+| - anatomy (mmlu)              |      0|none  |     0|acc     |0.6444|±  |0.0414|
+| - clinical_knowledge (mmlu)   |      0|none  |     0|acc     |0.7509|±  |0.0266|
+| - college_biology (mmlu)      |      0|none  |     0|acc     |0.7639|±  |0.0355|
+| - college_medicine (mmlu)     |      0|none  |     0|acc     |0.6532|±  |0.0363|
+| - medical_genetics (mmlu)     |      0|none  |     0|acc     |0.7500|±  |0.0435|
+| - professional_medicine (mmlu)|      0|none  |     0|acc     |0.7537|±  |0.0262|
+| - pubmedqa                    |      1|none  |     0|acc     |0.7760|±  |0.0187|
+
+|Groups|Version|Filter|n-shot| Metric |Value |   |Stderr|
+|------|-------|------|-----:|--------|-----:|---|-----:|
+|stem  |N/A    |none  |     0|acc     |0.6085|±  |0.0057|
+|      |       |none  |     0|acc_norm|0.5700|±  |0.0067|