You can deploy this model and start earning money today!

RichardErkhov/
johnsnowlabs_-_JSL-MedPhi2-2.7B-gguf

Name: johnsnowlabs_-_JSL-MedPhi2-2.7B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

JSL-MedPhi2-2.7B - GGUF

Model creator: https://huggingface.co/johnsnowlabs/
Original model: https://huggingface.co/johnsnowlabs/JSL-MedPhi2-2.7B/

Name	Quant method	Size
JSL-MedPhi2-2.7B.Q2_K.gguf	Q2_K	1.03GB
JSL-MedPhi2-2.7B.IQ3_XS.gguf	IQ3_XS	1.12GB
JSL-MedPhi2-2.7B.IQ3_S.gguf	IQ3_S	1.16GB
JSL-MedPhi2-2.7B.Q3_K_S.gguf	Q3_K_S	1.16GB
JSL-MedPhi2-2.7B.IQ3_M.gguf	IQ3_M	1.23GB
JSL-MedPhi2-2.7B.Q3_K.gguf	Q3_K	1.33GB
JSL-MedPhi2-2.7B.Q3_K_M.gguf	Q3_K_M	1.33GB
JSL-MedPhi2-2.7B.Q3_K_L.gguf	Q3_K_L	1.47GB
JSL-MedPhi2-2.7B.IQ4_XS.gguf	IQ4_XS	1.43GB
JSL-MedPhi2-2.7B.Q4_0.gguf	Q4_0	1.49GB
JSL-MedPhi2-2.7B.IQ4_NL.gguf	IQ4_NL	1.5GB
JSL-MedPhi2-2.7B.Q4_K_S.gguf	Q4_K_S	1.51GB
JSL-MedPhi2-2.7B.Q4_K.gguf	Q4_K	1.62GB
JSL-MedPhi2-2.7B.Q4_K_M.gguf	Q4_K_M	1.62GB
JSL-MedPhi2-2.7B.Q4_1.gguf	Q4_1	1.65GB
JSL-MedPhi2-2.7B.Q5_0.gguf	Q5_0	1.8GB
JSL-MedPhi2-2.7B.Q5_K_S.gguf	Q5_K_S	1.8GB
JSL-MedPhi2-2.7B.Q5_K.gguf	Q5_K	1.87GB
JSL-MedPhi2-2.7B.Q5_K_M.gguf	Q5_K_M	1.87GB
JSL-MedPhi2-2.7B.Q5_1.gguf	Q5_1	1.95GB
JSL-MedPhi2-2.7B.Q6_K.gguf	Q6_K	2.13GB
JSL-MedPhi2-2.7B.Q8_0.gguf	Q8_0	2.75GB

Original model description:

tags:

phi-2
sft
medical base_model:
microsoft/phi2 license: cc-by-nc-nd-4.0

JSL-MedPhi2-2.7B

This model is developed by John Snow Labs.

This model is available under a CC-BY-NC-ND license and must also conform to this Acceptable Use Policy. If you need to license this model for commercial use, please contact us at info@johnsnowlabs.com.

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "johnsnowlabs/JSL-MedPhi2-2.7B"
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	Metric	Value		Stderr
stem	N/A	none	acc_norm	0.3904	±	0.0066
		none	acc	0.4402	±	0.0058
- medmcqa	Yaml	none	acc	0.3899	±	0.0075
		none	acc_norm	0.3899	±	0.0075
- medqa_4options	Yaml	none	acc	0.3920	±	0.0137
		none	acc_norm	0.3920	±	0.0137
- anatomy (mmlu)	0	none	acc	0.4815	±	0.0432
- clinical_knowledge (mmlu)	0	none	acc	0.6340	±	0.0296
- college_biology (mmlu)	0	none	acc	0.6181	±	0.0406
- college_medicine (mmlu)	0	none	acc	0.5665	±	0.0378
- medical_genetics (mmlu)	0	none	acc	0.6300	±	0.0485
- professional_medicine (mmlu)	0	none	acc	0.4522	±	0.0302
- pubmedqa	1	none	acc	0.7300	±	0.0199

Groups	Version	Filter	n-shot	Metric	Value		Stderr
stem	N/A	none	0	acc_norm	0.3904	±	0.0066
		none	0	acc	0.4402	±	0.0058

RichardErkhov/johnsnowlabs_-_JSL-MedPhi2-2.7B-gguf

Original model description:

JSL-MedPhi2-2.7B

💻 Usage

🏆 Evaluation

RichardErkhov/
johnsnowlabs_-_JSL-MedPhi2-2.7B-gguf