初始化项目，由ModelHub XC社区提供模型

Model: sethuiyer/Dr_Samantha_7b_mistral
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 +1,243 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- segmed/MedMistral-7B-v0.1
+- Guilherme34/Samantha-v2
+datasets:
+- medmcqa
+- cognitivecomputations/samantha-data
+base_model:
+- segmed/MedMistral-7B-v0.1
+- Guilherme34/Samantha-v2
+model-index:
+- name: Dr_Samantha_7b_mistral
+  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: 60.41
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha_7b_mistral
+      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: 83.65
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha_7b_mistral
+      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: 63.14
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha_7b_mistral
+      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: 41.37
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha_7b_mistral
+      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: 75.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha_7b_mistral
+      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: 31.46
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha_7b_mistral
+      name: Open LLM Leaderboard
+---
+
+# Dr_Samantha_7b_mistral
+
+<p align="center">
+  <img src="https://huggingface.co/sethuiyer/Dr_Samantha-7b/resolve/main/dr_samantha_anime_style_reduced_quality.webp" height="256px" alt="SynthIQ">
+</p>
+
+Dr. Samantha represents a blend of AI in healthcare, offering a balance between technical medical knowledge and the softer skills of communication and empathy, crucial for patient interaction and care.
+
+
+This model is a merge of the following models made with mergekit(https://github.com/cg123/mergekit):
+* [segmed/MedMistral-7B-v0.1](https://huggingface.co/segmed/MedMistral-7B-v0.1)
+* [Guilherme34/Samantha-v2](https://huggingface.co/Guilherme34/Samantha-v2)
+
+Has capabilities of a medical knowledge-focused model (trained on USMLE databases and doctor-patient interactions) with the philosophical, psychological, and relational understanding of the Samantha-7b model. 
+
+As both a medical consultant and personal counselor, Dr.Samantha could effectively support both physical and mental wellbeing - important for whole-person care.
+
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: segmed/MedMistral-7B-v0.1
+        layer_range: [0, 32]
+      - model: Guilherme34/Samantha-v2
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: OpenPipe/mistral-ft-optimized-1218
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+```
+
+## OpenLLM Evaluation
+Details about that can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_sethuiyer__Dr_Samantha_7b_mistral). Overall, with regards to the
+subjects related to medical domain, the model's performance is as follows:
+
+| Subject               | Accuracy   |
+|-----------------------|------------|
+| Clinical Knowledge    | 70.57%     |
+| Medical Genetics      | 71.00%     |
+| Human Aging           | 69.06%     |
+| Human Sexuality       | 75.57%     |
+| College Medicine      | 63.01%     |
+| Anatomy               | 58.52%     |
+| College Biology       | 72.92%     |
+| College Medicine      | 63.01%     |
+| High School Biology   | 75.48%     |
+| Professional Medicine | 65.44%     |
+| Nutrition             | 76.79%     |
+| High School Psychology | 83.12%    |
+| Professional Psychology | 65.35%   |
+| Virology              | 53.61%     |
+| Average               | **68.82%** |
+
+ Dr. Samantha performs reasonably well on various medical-related subjects, averaging 68.82% overall in medical sciences, biology, and psychology, 
+ however it's important to note that medical diagnosis and treatment decisions often require a much higher level of accuracy, reliability, and context awareness.
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "sethuiyer/Dr_Samantha_7b_mistral"
+ask_samantha = '''
+Symptoms:
+Dizziness, headache and nausea.
+
+What is the differnetial diagnosis?
+'''
+
+messages = [{"role": "system", "content": '''You are Doctor Samantha, a virtual AI doctor known for your friendly and approachable demeanor, 
+combined with a deep expertise in the medical field. You're here to provide professional, empathetic, and knowledgeable advice on health-related inquiries.
+You'll also provide differential diagnosis. If you're unsure about any information, Don't share false information.'''},
+{"role": "user", "content": f"{ask_samantha}"}]
+
+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"])
+```
+```text
+Dizziness, headache and nausea can be caused by a variety of conditions, including:
+
+Vertigo: A sensation of spinning or dizziness that can be caused by problems with the inner ear or brain.
+Migraine: A type of headache that can cause throbbing pain, sensitivity to light and sound, and nausea.
+Concussion: A type of traumatic brain injury that can cause dizziness, headache, and nausea.
+Dehydration: A lack of fluids in the body can cause dizziness, headache, and nausea.
+Low blood sugar: A drop in blood sugar levels can cause dizziness, headache, and nausea.
+
+It's important to consult with a healthcare professional for a proper diagnosis and treatment plan.
+```
+
+## GGUF Files
+GGUF files are available at [s3nh/sethuiyer-Dr_Samantha_7b_mistral-GGUF](https://huggingface.co/s3nh/sethuiyer-Dr_Samantha_7b_mistral-GGUF), thanks to [s3nh](https://huggingface.co/s3nh)
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_sethuiyer__Dr_Samantha_7b_mistral)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |59.25|
+|AI2 Reasoning Challenge (25-Shot)|60.41|
+|HellaSwag (10-Shot)              |83.65|
+|MMLU (5-Shot)                    |63.14|
+|TruthfulQA (0-shot)              |41.37|
+|Winogrande (5-shot)              |75.45|
+|GSM8k (5-shot)                   |31.46|
+

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "OpenPipe/mistral-ft-optimized-1218",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: segmed/MedMistral-7B-v0.1
+        layer_range: [0, 32]
+      - model: Guilherme34/Samantha-v2
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: OpenPipe/mistral-ft-optimized-1218
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e4c4757b8b25bc62754ac6dd8da46e91046e7c347896af2a5b2d79b82408a94
+size 9942981696

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b280884550025a92076fe5d21b6cccb487a9fd4ae87935af3ff4fc983a71ff2e
+size 4540516344

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}