初始化项目，由ModelHub XC社区提供模型

Model: sethuiyer/Dr_Samantha-7b Source: Original Platform
2026-04-11 12:51:58 +08:00
commit 73e4cf8b88
12 changed files with 93803 additions and 0 deletions
--- a/.gitattributes
+++ b/.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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,256 @@
+---
+language:
+- en
+- zh
+license: llama2
+library_name: transformers
+tags:
+- llama
+- merge
+- medical
+datasets:
+- GBaker/MedQA-USMLE-4-options
+- cognitivecomputations/samantha-data
+- shibing624/medical
+base_model:
+- Severus27/BeingWell_llama2_7b
+- ParthasarathyShanmugam/llama-2-7b-samantha
+pipeline_tag: text-generation
+model-index:
+- name: Dr_Samantha-7b
+  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: 53.84
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha-7b
+      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: 77.95
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha-7b
+      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: 47.94
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha-7b
+      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: 45.58
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha-7b
+      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: 73.56
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha-7b
+      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: 18.8
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/Dr_Samantha-7b
+      name: Open LLM Leaderboard
+---
+
+# Dr. Samantha
+
+<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>
+
+## Overview
+
+Dr. Samantha is a language model made by merging `Severus27/BeingWell_llama2_7b` and `ParthasarathyShanmugam/llama-2-7b-samantha` using [mergekit](https://github.com/cg123/mergekit).
+
+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.
+
+
+# Yaml Config
+
+```yaml
+
+slices:
+  - sources:
+      - model: Severus27/BeingWell_llama2_7b
+        layer_range: [0, 32]
+      - model: ParthasarathyShanmugam/llama-2-7b-samantha
+        layer_range: [0, 32]
+
+merge_method: slerp
+base_model: TinyPixel/Llama-2-7B-bf16-sharded
+
+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 # fallback for rest of tensors
+tokenizer_source: union
+
+dtype: bfloat16
+
+```
+
+## Prompt Template
+
+```text
+Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+### Instruction:
+What is your name?
+
+### Response:
+My name is Samantha.
+```
+
+## ⚡ Quantized models
+
+* **GGUF**:https://huggingface.co/TheBloke/Dr_Samantha-7B-GGUF
+* **GPTQ**: https://huggingface.co/TheBloke/Dr_Samantha-7B-GPTQ
+* **AWQ**: https://huggingface.co/TheBloke/Dr_Samantha-7B-AWQ
+
+Thanks to [TheBloke](https://huggingface.co/TheBloke) for making this available! 
+
+Dr.Samantha is now available on Ollama. You can use it by running the command ```ollama run stuehieyr/dr_samantha``` 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.
+
+## OpenLLM Leaderboard Performance
+| T | Model                            | Average | ARC   | Hellaswag | MMLU  | TruthfulQA | Winogrande | GSM8K |
+|---|----------------------------------|---------|-------|-----------|-------|------------|------------|-------|
+| 1 | sethuiyer/Dr_Samantha-7b         | 52.95   | 53.84 | 77.95     | 47.94 | 45.58      | 73.56      | 18.8  |
+| 2 | togethercomputer/LLaMA-2-7B-32K-Instruct | 50.02   | 51.11 | 78.51     | 46.11 | 44.86      | 73.88      | 5.69  |
+| 3 | togethercomputer/LLaMA-2-7B-32K  | 47.07   | 47.53 | 76.14     | 43.33 | 39.23      | 71.9       | 4.32  |
+
+
+## Subject-wise Accuracy
+
+| Subject               | Accuracy (%) |
+|-----------------------|--------------|
+| Clinical Knowledge    | 52.83        |
+| Medical Genetics      | 49.00        |
+| Human Aging           | 58.29        |
+| Human Sexuality       | 55.73        |
+| College Medicine      | 38.73        |
+| Anatomy               | 41.48        |
+| College Biology       | 52.08        |
+| College Medicine      | 38.73        |
+| High School Biology   | 53.23        |
+| Professional Medicine | 38.73        |
+| Nutrition             | 50.33        |
+| Professional Psychology | 46.57      |
+| Virology              | 41.57        |
+| High School Psychology | 66.60       |
+| Average                | 48.85%      |
+
+
+## Evaluation by GPT-4 across 25 random prompts from ChatDoctor-200k Dataset
+
+### Overall Rating: 83.5/100
+
+#### Pros:
+
+- Demonstrates extensive medical knowledge through accurate identification of potential causes for various symptoms.
+- Responses consistently emphasize the importance of seeking professional diagnoses and treatments.
+- Advice to consult specialists for certain concerns is well-reasoned.
+- Practical interim measures provided for symptom management in several cases.
+- Consistent display of empathy, support, and reassurance for patients' well-being.
+- Clear and understandable explanations of conditions and treatment options.
+- Prompt responses addressing all aspects of medical inquiries.
+
+#### Cons:
+
+- Could occasionally place stronger emphasis on urgency when symptoms indicate potential emergencies.
+- Discussion of differential diagnoses could explore a broader range of less common causes.
+- Details around less common symptoms and their implications need more depth at times.
+- Opportunities exist to gather clarifying details on symptom histories through follow-up questions.
+- Consider exploring full medical histories to improve diagnostic context where relevant.
+- Caution levels and risk factors associated with certain conditions could be underscored more.
+
+
+
+# [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)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |52.95|
+|AI2 Reasoning Challenge (25-Shot)|53.84|
+|HellaSwag (10-Shot)              |77.95|
+|MMLU (5-Shot)                    |47.94|
+|TruthfulQA (0-shot)              |45.58|
+|Winogrande (5-shot)              |73.56|
+|GSM8k (5-shot)                   |18.80|
+
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32001
+}
--- a/dr_samantha_anime_style_reduced_quality.webp
+++ b/dr_samantha_anime_style_reduced_quality.webp
--- a/model-00001-of-00002.safetensors
+++ b/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3210215203d97ef23b2b143d0ad3c892793c98b2eddc4cdc58390cce6ccebd37
+size 9976578712
--- a/model-00002-of-00002.safetensors
+++ b/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9d4e32e306da1d593754da227055e06913e5734fb9e67a34d855aaf248a628d
+size 3500302736
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer.model
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,47 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}