nitsuai aashish1904 commited on
Commit
56d64f2
·
verified ·
0 Parent(s):

Duplicate from QuantFactory/Bio-Medical-Llama-3-8B-GGUF

Browse files

Co-authored-by: Aashish Kumar <aashish1904@users.noreply.huggingface.co>

.gitattributes ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Bio-Medical-Llama-3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Bio-Medical-Llama-3-8B.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Bio-Medical-Llama-3-8B.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Bio-Medical-Llama-3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Bio-Medical-Llama-3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Bio-Medical-Llama-3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Bio-Medical-Llama-3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Bio-Medical-Llama-3-8B.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Bio-Medical-Llama-3-8B.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Bio-Medical-Llama-3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Bio-Medical-Llama-3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Bio-Medical-Llama-3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
48
+ Bio-Medical-Llama-3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
49
+ Bio-Medical-Llama-3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
50
+ Bio-Medical-Llama-3-8B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
51
+ Bio-Medical-Llama-3-8B.Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
52
+ Bio-Medical-Llama-3-8B.Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
Bio-Medical-Llama-3-8B.Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c784e1927d58f57de95893bf1b194279d3673754accfb70070e7a9f378cd1447
3
+ size 3179132128
Bio-Medical-Llama-3-8B.Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:945bdec10b4fbbef17299affcec7a2b4f93c0f3e5747342a4c1db9559a86e4da
3
+ size 4321957088
Bio-Medical-Llama-3-8B.Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7454f306a9ee7a122683dc0d04a953781a4a436f5586198c6516119610220275
3
+ size 4018918624
Bio-Medical-Llama-3-8B.Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeaa27c5152e2777874a9326c8baf3045323096698f7bd988c8ea22c6791a0f4
3
+ size 3664499936
Bio-Medical-Llama-3-8B.Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc9d7b077c2905b3eda1469437a61f4de46d1e30e2e065b4208f7d4fa7485189
3
+ size 4661212384
Bio-Medical-Llama-3-8B.Q4_0_4_4.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32f48cd7b3f1ce44d0e5d00e12630b7da9e646614772f3f001e420d654478e8d
3
+ size 4661212384
Bio-Medical-Llama-3-8B.Q4_0_4_8.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b17e3188dad499a43bbe9f50bb9ff0a57d982cd772d1656e002b0346d3f40ae0
3
+ size 4661212384
Bio-Medical-Llama-3-8B.Q4_0_8_8.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1c52d2e77b7586a74f15a2a067f7e7c12b0217b4013f4312f6a33b5c646ce14
3
+ size 4661212384
Bio-Medical-Llama-3-8B.Q4_1.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df82ad925107eed054d2718745d208f61b35d1fb15bbfbf0ec063e1fe89b5411
3
+ size 5130253536
Bio-Medical-Llama-3-8B.Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:672939e0487d02c55734132c25a59f26e4deaac7cd49445a7028f2291139edcc
3
+ size 4920734944
Bio-Medical-Llama-3-8B.Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00daa04169ecaf6a74b12dcfb390ad9ba9dfc0fbe992ea1b6a17c1f49c9a81a3
3
+ size 4692669664
Bio-Medical-Llama-3-8B.Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27347d5fd7259f9bf14db9232166132c8d12f0755cb4299f8d8e92b30dd3db2c
3
+ size 5599294688
Bio-Medical-Llama-3-8B.Q5_1.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1311a94aadea3dbbd427931a149179fbf6484426e740cee2f84f1d75303255aa
3
+ size 6068335840
Bio-Medical-Llama-3-8B.Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26c365ad78be010656669eda582db3cb00ec34d846843afec7cfca596366ab13
3
+ size 5732988128
Bio-Medical-Llama-3-8B.Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc4033667b9c1a46e360c6e264eebda516bfdadb360f2b184622b1ad01150d19
3
+ size 5599294688
Bio-Medical-Llama-3-8B.Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6345e90f034437ee2037c99b081cf497de52028b9a9f1415c47ab525f219b16f
3
+ size 6596007136
Bio-Medical-Llama-3-8B.Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b9f59906832d010b21cac8d41a1a01eae819c585380ad628375f813af8dee50
3
+ size 8540771552
README.md ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+
4
+ license: other
5
+ library_name: transformers
6
+ tags:
7
+ - generated_from_trainer
8
+ - medical
9
+ - Healthcare & Lifesciences
10
+ - BioMed
11
+ base_model: meta-llama/Meta-Llama-3-8B-Instruct
12
+ thumbnail: https://collaiborate.com/logo/logo-blue-bg-1.png
13
+ model-index:
14
+ - name: Bio-Medical-Llama-3-8B
15
+ results: []
16
+ datasets:
17
+ - collaiborateorg/BioMedData
18
+
19
+ ---
20
+
21
+ [![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)
22
+
23
+
24
+ # QuantFactory/Bio-Medical-Llama-3-8B-GGUF
25
+ This is quantized version of [ContactDoctor/Bio-Medical-Llama-3-8B](https://huggingface.co/ContactDoctor/Bio-Medical-Llama-3-8B) created using llama.cpp
26
+
27
+ # Original Model Card
28
+
29
+
30
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
+ should probably proofread and complete it, then remove this comment. -->
32
+
33
+ # Bio-Medical
34
+
35
+
36
+ ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/653f5b93cd52f288490edc83/zPMUugzfOiwTiRw88jm7T.jpeg)
37
+
38
+ This model is a fine-tuned version of https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct on our custom "BioMedData" dataset.
39
+
40
+ ## Model details
41
+
42
+ Model Name: Bio-Medical-Llama-3-8B
43
+
44
+ Base Model: Llama-3-8B-Instruct
45
+
46
+ Parameter Count: 8 billion
47
+
48
+ Training Data: Custom high-quality biomedical dataset
49
+
50
+ Number of Entries in Dataset: 500,000+
51
+
52
+ Dataset Composition: The dataset comprises both synthetic and manually curated samples, ensuring a diverse and comprehensive coverage of biomedical knowledge.
53
+
54
+
55
+ ## Model description
56
+
57
+ Bio-Medical-Llama-3-8B model is a specialized large language model designed for biomedical applications. It is finetuned from the meta-llama/Meta-Llama-3-8B-Instruct model using a custom dataset containing over 500,000 diverse entries. These entries include a mix of synthetic and manually curated data, ensuring high quality and broad coverage of biomedical topics.
58
+
59
+ The model is trained to understand and generate text related to various biomedical fields, making it a valuable tool for researchers, clinicians, and other professionals in the biomedical domain.
60
+
61
+ ## Evaluation Metrics
62
+
63
+ Bio-Medical-Llama-3-8B model outperforms many of the leading LLMs and find below its metrics evaluated using the Eleuther AI Language Model Evaluation Harness framework against the tasks medmcqa, medqa_4options, mmlu_anatomy, mmlu_clinical_knowledge, mmlu_college_biology, mmlu_college_medicine, mmlu_medical_genetics, mmlu_professional_medicine and pubmedqa.
64
+
65
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/653f5b93cd52f288490edc83/kAzLH_rIk9QKujsuD2ErO.png)
66
+
67
+ ## Intended uses & limitations
68
+
69
+ Bio-Medical-Llama-3-8B model is intended for a wide range of applications within the biomedical field, including:
70
+
71
+ 1. Research Support: Assisting researchers in literature review and data extraction from biomedical texts.
72
+ 2. Clinical Decision Support: Providing information to support clinical decision-making processes.
73
+ 3. Educational Tool: Serving as a resource for medical students and professionals seeking to expand their knowledge base.
74
+
75
+ ## Limitations and Ethical Considerations
76
+
77
+ While Bio-Medical-Llama-3-8B model performs well in various biomedical NLP tasks, users should be aware of the following limitations:
78
+
79
+ > Biases: The model may inherit biases present in the training data. Efforts have been made to curate a balanced dataset, but some biases may persist.
80
+
81
+ > Accuracy: The model's responses are based on patterns in the data it has seen and may not always be accurate or up-to-date. Users should verify critical information from reliable sources.
82
+
83
+ > Ethical Use: The model should be used responsibly, particularly in clinical settings where the stakes are high. It should complement, not replace, professional judgment and expertise.
84
+
85
+
86
+ ## How to use
87
+
88
+ import transformers
89
+ import torch
90
+
91
+ model_id = "ContactDoctor/Bio-Medical-Llama-3-8B"
92
+
93
+ pipeline = transformers.pipeline(
94
+ "text-generation",
95
+ model=model_id,
96
+ model_kwargs={"torch_dtype": torch.bfloat16},
97
+ device_map="auto",
98
+ )
99
+
100
+ messages = [
101
+ {"role": "system", "content": "You are an expert trained on healthcare and biomedical domain!"},
102
+ {"role": "user", "content": "I'm a 35-year-old male and for the past few months, I've been experiencing fatigue, increased sensitivity to cold, and dry, itchy skin. What is the diagnosis here?"},
103
+ ]
104
+
105
+ prompt = pipeline.tokenizer.apply_chat_template(
106
+ messages,
107
+ tokenize=False,
108
+ add_generation_prompt=True
109
+ )
110
+
111
+ terminators = [
112
+ pipeline.tokenizer.eos_token_id,
113
+ pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
114
+ ]
115
+
116
+ outputs = pipeline(
117
+ prompt,
118
+ max_new_tokens=256,
119
+ eos_token_id=terminators,
120
+ do_sample=True,
121
+ temperature=0.6,
122
+ top_p=0.9,
123
+ )
124
+ print(outputs[0]["generated_text"][len(prompt):])
125
+
126
+ ## License
127
+
128
+ This model is licensed under the [Bio-Medical-Llama-3-8B (Non-Commercial Use Only)](./LICENSE). Please review the terms and conditions before using the model.
129
+
130
+
131
+ ### Contact Information
132
+
133
+ For further information, inquiries, or issues related to Biomed-LLM, please contact:
134
+
135
+ Email: info@contactdoctor.in
136
+
137
+ Website: https://www.contactdoctor.in
138
+
139
+ ### Training hyperparameters
140
+
141
+ The following hyperparameters were used during training:
142
+ - learning_rate: 0.0002
143
+ - train_batch_size: 12
144
+ - eval_batch_size: 8
145
+ - seed: 42
146
+ - gradient_accumulation_steps: 4
147
+ - total_train_batch_size: 32
148
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
149
+ - lr_scheduler_type: cosine
150
+ - lr_scheduler_warmup_ratio: 0.03
151
+ - training_steps: 2000
152
+ - mixed_precision_training: Native AMP
153
+
154
+ ### Framework versions
155
+
156
+ - PEFT 0.11.0
157
+ - Transformers 4.40.2
158
+ - Pytorch 2.1.2
159
+ - Datasets 2.19.1
160
+ - Tokenizers 0.19.1
161
+
162
+ ### Citation
163
+
164
+ If you use Bio-Medical LLM in your research or applications, please cite it as follows:
165
+
166
+ @misc{ContactDoctor_Bio-Medical-Llama-3-8B,
167
+ author = ContactDoctor,
168
+ title = {Bio-Medical: A High-Performance Biomedical Language Model},
169
+ year = {2024},
170
+ howpublished = {https://huggingface.co/ContactDoctor/Bio-Medical-Llama-3-8B},
171
+ }