初始化项目，由ModelHub XC社区提供模型

Model: sethuiyer/OpenDolphinHermes_Llama2_7B Source: Original Platform
2026-06-15 07:05:17 +08:00
commit 7a55af502c
17 changed files with 93797 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 +1,229 @@
+---
+language:
+- en
+license: llama2
+library_name: transformers
+tags:
+- merge
+- mergekit
+- lazymergekit
+datasets:
+- teknium/openhermes
+- cognitivecomputations/dolphin
+base_model:
+- cognitivecomputations/dolphin-llama2-7b
+- Tensoic/Llama-2-openhermes
+pipeline_tag: text-generation
+model-index:
+- name: OpenDolphinHermes_Llama2_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: 55.03
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/OpenDolphinHermes_Llama2_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: 78.74
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/OpenDolphinHermes_Llama2_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: 52.25
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/OpenDolphinHermes_Llama2_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: 46.1
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/OpenDolphinHermes_Llama2_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: 73.16
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/OpenDolphinHermes_Llama2_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: 20.17
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=sethuiyer/OpenDolphinHermes_Llama2_7B
+      name: Open LLM Leaderboard
+---
+
+# OpenDolphinHermes_Llama2_7B
+
+
+<p align="center">
+  <img src="https://huggingface.co/sethuiyer/OpenDolphinHermes_Llama2_7B/resolve/main/dolphin_hermes.webp" height="256px" alt="SynthIQ">
+</p>
+
+mergekit SLERP of these two models
+* [cognitivecomputations/dolphin-llama2-7b](https://huggingface.co/cognitivecomputations/dolphin-llama2-7b)
+* [Tensoic/Llama-2-openhermes](https://huggingface.co/Tensoic/Llama-2-openhermes)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: cognitivecomputations/dolphin-llama2-7b
+        layer_range: [0, 32]
+      - model: Tensoic/Llama-2-openhermes
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: Tensoic/Llama-2-openhermes
+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
+```
+
+# Prompt Template (ChatML)
+```text
+<|im_start|>system
+You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.
+Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content.
+Please ensure that your responses are socially unbiased and positive in nature.
+
+If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct.
+If you don't know the answer to a question, please don't share false information.
+<|im_end|>
+<|im_start|>user
+{ .Prompt}
+<|im_end|>
+<|im_start|>assistant
+```
+
+# OpenLLM Leaderboard
+
+| T | Model                                      | Average | ARC  | HellaSwag | MMLU  | TruthfulQA | Winogrande | GSM8K |
+|---|--------------------------------------------|---------|------|-----------|-------|------------|------------|-------|
+| 0 | meta-llama/llama-2-13b-hf        | 55.69   | 59.39 | 82.13     | 55.77 | 37.38      | 76.64      | 22.82 |
+| 1 | sethuiyer/OpenDolphinHermes_Llama2_7B      | 54.24   | 55.03| 78.74     | 52.25 | 46.1       | 73.16      | 20.17 |
+| 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  |
+
+## Why?
+
+I wanted a LLaMa2-7B model which is as good as base LLaMa2-13B model.
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "sethuiyer/OpenDolphinHermes_Llama2_7B"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+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"])
+```
+
+Output:
+```text
+A large language model is a type of artificial intelligence system that has been trained on a massive amount of data, often millions or even billions of words, to learn the patterns and relationships between words and phrases.
+These models can then be used to generate new text, understand and translate languages, and perform various natural language processing tasks.
+They have become increasingly popular in recent years due to advances in machine learning technology and their ability to achieve high levels of accuracy and performance on natural language processing tasks.
+Examples of large language models include GPT-2, BERT, and T5.
+```
+## Thanks
+Thanks to Google Colab for the compute.
+# [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__OpenDolphinHermes_Llama2_7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |54.24|
+|AI2 Reasoning Challenge (25-Shot)|55.03|
+|HellaSwag (10-Shot)              |78.74|
+|MMLU (5-Shot)                    |52.25|
+|TruthfulQA (0-shot)              |46.10|
+|Winogrande (5-shot)              |73.16|
+|GSM8k (5-shot)                   |20.17|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "Tensoic/Llama-2-openhermes",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}
--- a/dolphin_hermes.webp
+++ b/dolphin_hermes.webp
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: cognitivecomputations/dolphin-llama2-7b
+        layer_range: [0, 32]
+      - model: Tensoic/Llama-2-openhermes
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: Tensoic/Llama-2-openhermes
+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
--- a/model-00001-of-00007.safetensors
+++ b/model-00001-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d7a337902882fe8bbbb99887dd4bea3cbcc272888e8c21d1a301a9ca3940336
+size 1933652888
--- a/model-00002-of-00007.safetensors
+++ b/model-00002-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:872d7cfca09c98920e0488078145ad323847d9cc2d9da27628579a2f7261b893
+size 1933661192
--- a/model-00003-of-00007.safetensors
+++ b/model-00003-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b6bd3afeaed202d5e8fe4ca046fe3c41f70277759c9efe58df230b4eb4372c9
+size 1933661176
--- a/model-00004-of-00007.safetensors
+++ b/model-00004-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c07e8cc672de9cbb1e88d1cca6a54ad784001a282a6149142c112ab8dfe1d8fd
+size 1990275936
--- a/model-00005-of-00007.safetensors
+++ b/model-00005-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0ed06ac8bbfcf679c5974a23cc07040e29d3d800ea4ac459aa9340448b0446c
+size 1923175144
--- a/model-00006-of-00007.safetensors
+++ b/model-00006-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1974e89153f4785fa1dd07fcf5fd29ad379b45aeb9738e3718a0dba063e081f4
+size 1963003976
--- a/model-00007-of-00007.safetensors
+++ b/model-00007-of-00007.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88f02c4da6533cf0b8e1b39ef03476f258737149ae90335868d05f6617813e52
+size 1799434672
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_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
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer.model
+++ b/tokenizer.model
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "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": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}