初始化项目，由ModelHub XC社区提供模型

Model: louisbrulenaudet/Pearl-7B-0210-ties Source: Original Platform
2026-05-07 06:37:41 +08:00
commit eeb8f0ff2f
18 changed files with 366 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,58 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+ 
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+model-00008-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00006-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00007-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.model filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,160 @@
+---
+tags:
+- merge
+- mergekit
+- louisbrulenaudet/Pearl-7B-slerp
+- WizardLM/WizardMath-7B-V1.1
+- cognitivecomputations/WestLake-7B-v2-laser
+- CultriX/NeuralTrix-7B-dpo
+- chemistry
+- biology
+- math
+base_model:
+- louisbrulenaudet/Pearl-7B-slerp
+- WizardLM/WizardMath-7B-V1.1
+- cognitivecomputations/WestLake-7B-v2-laser
+- CultriX/NeuralTrix-7B-dpo
+license: apache-2.0
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+model-index:
+- name: Pearl-7B-0210-ties
+  results:
+  - task:
+      type: text-generation
+    metrics:
+    - name: Average
+      type: Average
+      value: 74.66
+    - name: ARC
+      type: ARC
+      value: 71.08
+    - name: GSM8K
+      type: GSM8K
+      value: 69.98
+    - name: Winogrande
+      type: Winogrande
+      value: 83.98
+    - name: TruthfulQA
+      type: TruthfulQA
+      value: 70.47
+    - name: HellaSwag
+      type: HellaSwag
+      value: 88.63
+    source:
+      name: Open LLM Leaderboard
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
+---
+<center><img src='https://i.imgur.com/0xFTuAX.png' width='450px'></center>
+
+# Pearl-7B-0210-ties, an xtraordinary 7B model
+
+**03-22-2024 - To date, louisbrulenaudet/Pearl-34B-ties is the "Best 🤝 base merges and moerges model of around 30B" on the Open LLM Leaderboard.**
+
+Pearl-7B-0210-ties is a merge of the following models:
+* [louisbrulenaudet/Pearl-7B-slerp](https://huggingface.co/louisbrulenaudet/Pearl-7B-slerp)
+* [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)
+* [cognitivecomputations/WestLake-7B-v2-laser](https://huggingface.co/cognitivecomputations/WestLake-7B-v2-laser)
+* [CultriX/NeuralTrix-7B-dpo](https://huggingface.co/CultriX/NeuralTrix-7B-dpo)
+
+Evaluation
+
+The evaluation was performed using the HuggingFace Open LLM Leaderboard.
+
+| Model                                            | Average | ARC   | HellaSwag | MMLU  | TruthfulQA | Winogrande | GSM8K | #Params (B) |
+|--------------------------------------------------|---------|-------|-----------|-------|------------|------------|-------|--------------|
+| louisbrulenaudet/Pearl-34B-ties                 | 75.48   | 70.99 | 84.83     | 76.63 | 70.32      | 82.64      | 67.48 | 34.39        |
+| louisbrulenaudet/Pearl-7B-0211-ties            | 75.11   | 71.42 | 88.86     | 63.91 | 71.46      | 84.37      | 70.66 | 7.24         |
+| NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO    | 73.35   | 71.08 | 87.29     | 72.17 | 54.83      | 83.11      | 71.65 | 46.7         |
+| argilla/notus-8x7b-experiment                  | 73.18   | 70.99 | 87.73     | 71.33 | 65.79      | 81.61      | 61.64 | 46.7         |
+| louisbrulenaudet/Pearl-7B-slerp                | 72.75   | 68.00 | 87.16     | 64.04 | 62.35      | 81.29      | 73.62 | 7.24         |
+| mistralai/Mixtral-8x7B-Instruct-v0.1           | 72.7    | 70.14 | 87.55     | 71.4  | 64.98      | 81.06      | 61.11 | 46.7         |
+| microsoft/Orca-2-13b                            | 61.98   | 60.92 | 79.85     | 60.3  | 56.42      | 76.56      | 37.83 | 13           |
+| microsoft/phi-2                                 | 61.33   | 61.09 | 75.11     | 58.11 | 44.47      | 74.35      | 54.81 | 2.78         |
+
+### Ties merging
+
+TIES-Merging is a method designed to facilitate the efficient merging of multiple task-specific models into a consolidated multitask model. It addresses two primary challenges encountered in the process of model merging with a focus on maintaining objectivity.
+
+One key challenge tackled by TIES-Merging involves addressing redundancy in model parameters. This is achieved by identifying and eliminating redundant parameters within task-specific models, emphasizing the changes made during fine-tuning and selectively retaining the top-k% most significant changes while discarding the rest.
+
+Another challenge pertains to conflicts arising from disagreements between parameter signs across different models. TIES-Merging resolves these conflicts by creating a unified sign vector representing the most dominant direction of change across all models.
+
+The TIES-Merging process consists of three steps:
+
+- Trim: Reduces redundancy in task-specific models by retaining a fraction of the most significant parameters (density parameter) and resetting the remaining parameters to zero.
+- Elect Sign: Resolves sign conflicts across different models by creating a unified sign vector based on the most dominant direction (positive or negative) in terms of cumulative magnitude.
+- Disjoint Merge: Averages parameter values aligned with the unified sign vector, excluding zero values.
+
+## Configuration
+
+```yaml
+models:
+  - model: OpenPipe/mistral-ft-optimized-1227
+  - model: louisbrulenaudet/Pearl-7B-slerp
+    parameters:
+      density: 0.5
+      weight: 0.4
+  - model: WizardLM/WizardMath-7B-V1.1
+    parameters:
+      density: 0.5
+      weight: 0.2
+  - model: cognitivecomputations/WestLake-7B-v2-laser
+    parameters:
+      density: 0.5
+      weight: 0.2
+  - model: CultriX/NeuralTrix-7B-dpo
+    parameters:
+     density: 0.5
+     weight: 0.2
+merge_method: ties
+base_model: OpenPipe/mistral-ft-optimized-1227
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: float16
+```
+
+## Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "louisbrulenaudet/Pearl-7B-0210-ties"
+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"])
+```
+
+## Citing & Authors
+
+If you use this code in your research, please use the following BibTeX entry.
+
+```BibTeX
+@misc{louisbrulenaudet2023,
+  author =       {Louis Brulé Naudet},
+  title =        {Pearl-7B-0210-ties, an xtraordinary 7B model},
+  year =         {2023}
+  howpublished = {\url{https://huggingface.co/louisbrulenaudet/Pearl-7B-0210-ties}},
+}
+```
+
+## Feedback
+
+If you have any feedback, please reach out at [louisbrulenaudet@icloud.com](mailto:louisbrulenaudet@icloud.com).
--- a/config.json
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "OpenPipe/mistral-ft-optimized-1227",
+  "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": "float16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,25 @@
+
+models:
+  - model: OpenPipe/mistral-ft-optimized-1227
+  - model: louisbrulenaudet/Pearl-7B-slerp
+    parameters:
+      density: 0.5
+      weight: 0.4
+  - model: WizardLM/WizardMath-7B-V1.1
+    parameters:
+      density: 0.5
+      weight: 0.2
+  - model: cognitivecomputations/WestLake-7B-v2-laser
+    parameters:
+      density: 0.5
+      weight: 0.2
+  - model: CultriX/NeuralTrix-7B-dpo
+    parameters:
+     density: 0.5
+     weight: 0.2
+merge_method: ties
+base_model: OpenPipe/mistral-ft-optimized-1227
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: float16
--- a/model-00001-of-00008.safetensors
+++ b/model-00001-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4902ba1db8ddd8fa355a67a3bfecd933f592a5b2bb78c44f513b3a1954fbc7ed
+size 1912681544
--- a/model-00002-of-00008.safetensors
+++ b/model-00002-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dac4193befb04049225d4b332f2feb71f9a859ce6a6812336fcb5f6004cc5a2f
+size 1979781416
--- a/model-00003-of-00008.safetensors
+++ b/model-00003-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f74dda44067a9b02c3ea4cb654474abca571780043a9dc9e0ea3ceec825d8d0
+size 1946243928
--- a/model-00004-of-00008.safetensors
+++ b/model-00004-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96e492364d72d14eb337985a8393bb29123b78b4bacf7a9daebc604806908953
+size 1979781384
--- a/model-00005-of-00008.safetensors
+++ b/model-00005-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbe6e369c9982f7396b545d38f3c74ca11576ab939a8c00f108131c7d0833d6c
+size 1862349040
--- a/model-00006-of-00008.safetensors
+++ b/model-00006-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233e95c0036ce1070955ab29c5e555102eef8c599f23c99d23f358e0028d5c83
+size 1916866472
--- a/model-00007-of-00008.safetensors
+++ b/model-00007-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f889bcf4291a0e6217fc58dfd18c9765ab5372985509cc4d0dab63ccd7edd21
+size 1979781416
--- a/model-00008-of-00008.safetensors
+++ b/model-00008-of-00008.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce2850ecc432ac9c39a2b674dfcf9ac877df031216c22775f06c287f9154469
+size 906012456
--- 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": 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
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer.model
+++ b/tokenizer.model
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,42 @@
+{
+  "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>",
+  "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
+}
				`@@ -0,0 +1 @@`
				`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`