Triangle104
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -25,6 +25,90 @@ tags:
|
|
25 |
This model was converted to GGUF format from [`prithivMLmods/Qwen-UMLS-7B-Instruct`](https://huggingface.co/prithivMLmods/Qwen-UMLS-7B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
26 |
Refer to the [original model card](https://huggingface.co/prithivMLmods/Qwen-UMLS-7B-Instruct) for more details on the model.
|
27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
## Use with llama.cpp
|
29 |
Install llama.cpp through brew (works on Mac and Linux)
|
30 |
|
|
|
25 |
This model was converted to GGUF format from [`prithivMLmods/Qwen-UMLS-7B-Instruct`](https://huggingface.co/prithivMLmods/Qwen-UMLS-7B-Instruct) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
|
26 |
Refer to the [original model card](https://huggingface.co/prithivMLmods/Qwen-UMLS-7B-Instruct) for more details on the model.
|
27 |
|
28 |
+
---
|
29 |
+
Model details:
|
30 |
+
-
|
31 |
+
The Qwen-UMLS-7B-Instruct model is a specialized, instruction-tuned language model designed for medical and healthcare-related tasks. It is fine-tuned on the Qwen2.5-7B-Instruct base model using the UMLS (Unified Medical Language System) dataset, making it an invaluable tool for medical professionals, researchers, and developers building healthcare applications.
|
32 |
+
|
33 |
+
Key Features:
|
34 |
+
|
35 |
+
Medical Expertise:
|
36 |
+
|
37 |
+
Trained on the UMLS dataset, ensuring deep domain knowledge in medical terminology, diagnostics, and treatment plans.
|
38 |
+
|
39 |
+
Instruction-Following:
|
40 |
+
|
41 |
+
Designed to handle complex queries with clarity and precision, suitable for diagnostic support, patient education, and research.
|
42 |
+
|
43 |
+
High-Parameter Model:
|
44 |
+
|
45 |
+
Leverages 7 billion parameters to deliver detailed, contextually accurate responses.
|
46 |
+
Training Details:
|
47 |
+
Base Model: Qwen2.5-7B-Instruct
|
48 |
+
Dataset: avaliev/UMLS
|
49 |
+
Comprehensive dataset of medical terminologies, relationships, and use cases with 99.1k samples.
|
50 |
+
|
51 |
+
Capabilities:
|
52 |
+
|
53 |
+
Clinical Text Analysis:
|
54 |
+
|
55 |
+
Interpret medical notes, prescriptions, and research articles.
|
56 |
+
|
57 |
+
Question-Answering:
|
58 |
+
|
59 |
+
Answer medical queries, provide explanations for symptoms, and suggest treatments based on user prompts.
|
60 |
+
|
61 |
+
Educational Support:
|
62 |
+
|
63 |
+
Assist in learning medical terminologies and understanding complex concepts.
|
64 |
+
|
65 |
+
Healthcare Applications:
|
66 |
+
|
67 |
+
Integrate into clinical decision-support systems or patient care applications.
|
68 |
+
|
69 |
+
Usage Instructions:
|
70 |
+
|
71 |
+
Setup: Download all files and ensure compatibility with the Hugging Face Transformers library.
|
72 |
+
|
73 |
+
Loading the Model:
|
74 |
+
|
75 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
76 |
+
|
77 |
+
model_name = "prithivMLmods/Qwen-UMLS-7B-Instruct"
|
78 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
79 |
+
model = AutoModelForCausalLM.from_pretrained(model_name)
|
80 |
+
|
81 |
+
Generate Medical Text:
|
82 |
+
|
83 |
+
input_text = "What are the symptoms and treatments for diabetes?"
|
84 |
+
inputs = tokenizer(input_text, return_tensors="pt")
|
85 |
+
outputs = model.generate(**inputs, max_length=200, temperature=0.7)
|
86 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
87 |
+
|
88 |
+
Customizing Outputs: Modify generation_config.json to optimize output style:
|
89 |
+
|
90 |
+
temperature for creativity vs. determinism.
|
91 |
+
max_length for concise or extended responses.
|
92 |
+
|
93 |
+
Applications:
|
94 |
+
|
95 |
+
Clinical Support:
|
96 |
+
|
97 |
+
Assist healthcare providers with quick, accurate information retrieval.
|
98 |
+
|
99 |
+
Patient Education:
|
100 |
+
|
101 |
+
Provide patients with understandable explanations of medical conditions.
|
102 |
+
|
103 |
+
Medical Research:
|
104 |
+
|
105 |
+
Summarize or analyze complex medical research papers.
|
106 |
+
|
107 |
+
AI-Driven Diagnostics:
|
108 |
+
|
109 |
+
Integrate with diagnostic systems for preliminary assessments.
|
110 |
+
|
111 |
+
---
|
112 |
## Use with llama.cpp
|
113 |
Install llama.cpp through brew (works on Mac and Linux)
|
114 |
|