初始化项目，由ModelHub XC社区提供模型

Model: sethuiyer/Medichat-Llama3-8B
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,235 @@
+---
+base_model:
+- Undi95/Llama-3-Unholy-8B
+- Locutusque/llama-3-neural-chat-v1-8b
+- ruslanmv/Medical-Llama3-8B-16bit
+library_name: transformers
+tags:
+- mergekit
+- merge
+- medical
+license: other
+datasets:
+- mlabonne/orpo-dpo-mix-40k
+- Open-Orca/SlimOrca-Dedup
+- jondurbin/airoboros-3.2
+- microsoft/orca-math-word-problems-200k
+- m-a-p/Code-Feedback
+- MaziyarPanahi/WizardLM_evol_instruct_V2_196k
+- ruslanmv/ai-medical-chatbot
+model-index:
+- name: Medichat-Llama3-8B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 59.13
+      name: normalized accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 82.9
+      name: normalized accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 60.35
+      name: accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 49.65
+    source:
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 78.93
+      name: accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 60.35
+      name: accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Medichat-Llama3-8B
+      name: Open LLM Leaderboard
+language:
+- en
+---
+
+### Medichat-Llama3-8B
+
+Built upon the powerful LLaMa-3 architecture and fine-tuned on an extensive dataset of health information, this model leverages its vast medical knowledge to offer clear, comprehensive answers.
+
+This model is generally better for accurate and informative responses, particularly for users seeking in-depth medical advice.
+
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+models:
+  - model: Undi95/Llama-3-Unholy-8B
+    parameters:
+      weight: [0.25, 0.35, 0.45, 0.35, 0.25]
+      density: [0.1, 0.25, 0.5, 0.25, 0.1]
+  - model: Locutusque/llama-3-neural-chat-v1-8b
+  - model: ruslanmv/Medical-Llama3-8B-16bit
+    parameters:
+      weight: [0.55, 0.45, 0.35, 0.45, 0.55]
+      density: [0.1, 0.25, 0.5, 0.25, 0.1]
+merge_method: dare_ties
+base_model: Locutusque/llama-3-neural-chat-v1-8b
+parameters:
+  int8_mask: true
+dtype: bfloat16
+
+```
+
+# Comparision Against Dr.Samantha 7B
+
+| Subject                 | Medichat-Llama3-8B Accuracy (%) | Dr. Samantha Accuracy (%) |
+|-------------------------|---------------------------------|---------------------------|
+| Clinical Knowledge      | 71.70                           | 52.83                     |
+| Medical Genetics        | 78.00                           | 49.00                     |
+| Human Aging             | 70.40                           | 58.29                     |
+| Human Sexuality         | 73.28                           | 55.73                     |
+| College Medicine        | 62.43                           | 38.73                     |
+| Anatomy                 | 64.44                           | 41.48                     |
+| College Biology         | 72.22                           | 52.08                     |
+| High School Biology     | 77.10                           | 53.23                     |
+| Professional Medicine   | 63.97                           | 38.73                     |
+| Nutrition               | 73.86                           | 50.33                     |
+| Professional Psychology | 68.95                           | 46.57                     |
+| Virology                | 54.22                           | 41.57                     |
+| High School Psychology  | 83.67                           | 66.60                     |
+| **Average**             | **70.33**                       | **48.85**                 |
+
+
+The current model demonstrates a substantial improvement over the previous [Dr. Samantha](sethuiyer/Dr_Samantha-7b) model in terms of subject-specific knowledge and accuracy.
+
+### Usage:
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+class MedicalAssistant:
+    def __init__(self, model_name="sethuiyer/Medichat-Llama3-8B", device="cuda"):
+        self.device = device
+        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
+        self.model = AutoModelForCausalLM.from_pretrained(model_name).to(self.device)
+        self.sys_message = ''' 
+        You are an AI Medical Assistant trained on a vast dataset of health information. Please be thorough and
+        provide an informative answer. If you don't know the answer to a specific medical inquiry, advise seeking professional help.
+        '''
+
+    def format_prompt(self, question):
+        messages = [
+            {"role": "system", "content": self.sys_message},
+            {"role": "user", "content": question}
+        ]
+        prompt = self.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+        return prompt
+
+    def generate_response(self, question, max_new_tokens=512):
+        prompt = self.format_prompt(question)
+        inputs = self.tokenizer(prompt, return_tensors="pt").to(self.device)
+        with torch.no_grad():
+            outputs = self.model.generate(**inputs, max_new_tokens=max_new_tokens, use_cache=True)
+        answer = self.tokenizer.batch_decode(outputs, skip_special_tokens=True)[0].strip()
+        return answer
+
+if __name__ == "__main__":
+    assistant = MedicalAssistant()
+    question = '''
+    Symptoms:
+    Dizziness, headache, and nausea.
+
+    What is the differential diagnosis?
+    '''
+    response = assistant.generate_response(question)
+    print(response)
+
+```
+
+## Quants
+Thanks to [Quant Factory](https://huggingface.co/QuantFactory), the quantized version of this model is available at [QuantFactory/Medichat-Llama3-8B-GGUF](https://huggingface.co/QuantFactory/Medichat-Llama3-8B-GGUF),
+
+
+## Ollama
+This model is now also available on Ollama. You can use it by running the command ```ollama run monotykamary/medichat-llama3``` in your 
+terminal. If you have limited computing resources, check out this [video](https://www.youtube.com/watch?v=Qa1h7ygwQq8) to learn how to run it on 
+a Google Colab backend.

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Locutusque/llama-3-neural-chat-v1-8b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

mergekit_config.yml

@@ -0,0 +1,16 @@
+
+models:
+  - model: Undi95/Llama-3-Unholy-8B
+    parameters:
+      weight: [0.25, 0.35, 0.45, 0.35, 0.25]
+      density: [0.1, 0.25, 0.5, 0.25, 0.1]
+  - model: Locutusque/llama-3-neural-chat-v1-8b
+  - model: ruslanmv/Medical-Llama3-8B-16bit
+    parameters:
+      weight: [0.55, 0.45, 0.35, 0.45, 0.55]
+      density: [0.1, 0.25, 0.5, 0.25, 0.1]
+merge_method: dare_ties
+base_model: Locutusque/llama-3-neural-chat-v1-8b
+parameters:
+  int8_mask: true
+dtype: bfloat16

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eab9512c5226850c1905a70cb2b12492ee8d5d2348a99407e77a896bac176c55
+size 1973455376

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f95a818381175d9997fdc17d24c7073fa60de366b4e502e1bf086cf757bee4
+size 1895895336

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b2dd862fc36e8d7819d849fe83f99d4b43adcb4797babd58f7e9ef1f9e8aa7d
+size 1979798040

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:becba07adeaa93e687d248563b073a7a4e3c209c011005193fce80ce176ec3be
+size 1946227368

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:204eecb20cecec984f8296647ef448f292f791c0e6385936c1c0ea1658da4600
+size 1979798064

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efad6634ca90b7826d0cd9e5c29330346e095c5248e58e419f5efed711e11194
+size 1946227368

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323629c214632eb63f264bdb86ae3b400fb7b16e9ebcf989c0d64bbaca10bb29
+size 1979806352

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0dc970cb5402b513f8975ffda0df561f6eeefc672284e351068dbf5e824e96
+size 1308675136

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1772d401c0f7f378924cf5cdd60a73bbee0dbd2f463d52bb89509ddf00d5460
+size 1050673280

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}