初始化项目，由ModelHub XC社区提供模型

Model: Kukedlc/NeuralArjuna-7B-DT Source: Original Platform
2026-05-05 16:02:03 +08:00
commit 116de1dfa2
11 changed files with 91575 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 +1,276 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- yam-peleg/Experiment26-7B
+- Gille/StrangeMerges_32-7B-slerp
+- MSL7/INEX12-7b
+- automerger/YamShadow-7B
+- Kukedlc/NeuralSirKrishna-7b
+base_model:
+- yam-peleg/Experiment26-7B
+- Gille/StrangeMerges_32-7B-slerp
+- MSL7/INEX12-7b
+- automerger/YamShadow-7B
+- Kukedlc/NeuralSirKrishna-7b
+model-index:
+- name: NeuralArjuna-7B-DT
+  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: 73.12
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralArjuna-7B-DT
+      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: 88.97
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralArjuna-7B-DT
+      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: 64.63
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralArjuna-7B-DT
+      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: 76.68
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralArjuna-7B-DT
+      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: 85.24
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralArjuna-7B-DT
+      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: 70.81
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralArjuna-7B-DT
+      name: Open LLM Leaderboard
+---
+
+# NeuralArjuna-7B-DT
+  
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/zFLiis1pQWnriLQb2ZGGn.png)
+
+NeuralArjuna-7B-DT is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
+* [Gille/StrangeMerges_32-7B-slerp](https://huggingface.co/Gille/StrangeMerges_32-7B-slerp)
+* [MSL7/INEX12-7b](https://huggingface.co/MSL7/INEX12-7b)
+* [automerger/YamShadow-7B](https://huggingface.co/automerger/YamShadow-7B)
+* [Kukedlc/NeuralSirKrishna-7b](https://huggingface.co/Kukedlc/NeuralSirKrishna-7b)
+
+## 🧩 Configuration
+
+```yaml
+models:
+  - model: liminerity/M7-7b
+    # no parameters necessary for base model
+  - model: yam-peleg/Experiment26-7B 
+    parameters:
+      weight: 0.2
+      density: 0.66
+  - model: Gille/StrangeMerges_32-7B-slerp
+    parameters:
+      weight: 0.2
+      density: 0.55
+  - model: MSL7/INEX12-7b 
+    parameters:
+      weight: 0.2
+      density: 0.33
+  - model: automerger/YamShadow-7B
+    parameters:
+      weight: 0.2
+      density: 0.66
+  - model: Kukedlc/NeuralSirKrishna-7b
+    parameters:
+      weight: 0.2
+      density: 0.66
+merge_method: dare_ties
+base_model: liminerity/M7-7b
+
+parameters:
+  int8_mask: true
+  normalize: true
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Kukedlc/NeuralArjuna-7B-DT"
+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"])
+```
+
+
+# Example
+
+```
+I want you to generate a theory that unites quantum mechanics with the theory of relativity and cosmic consciousness. Give a large a detailed response
+
+In embarking upon a journey to weave together quantum mechanics, relativity, and the enigmatic realms of cosmic consciousness, we tread upon an intellectual
+landscape rife with challenges and enigmas. Our sojourn shall be a delicate ballet between the concrete and the abstract, the tangible and the speculative.
+The resultant tapestry will be neither a definitive, final statement, nor a mere collection of disparate ideas. Instead, we will craft a narrative that strives to bridge
+the chasms of understanding between these disparate scientific and philosophical realms, in hopes of illuminating a path towards a more comprehensive understanding of the
+universe and our place within it.
+
+To commence our odyssey, we must first address the foundational pillars of the scientific theories we seek to unite.
+
+Quantum Mechanics
+Quantum mechanics, the theory governing the microscopic realm, has long confounded the human intellect. It is a realm of probabilities, entanglement,
+and superposition—a world where particles can behave both as particles and waves, where actions at a distance are not only possible but ubiquitous,
+and where the mere act of observation alters the outcome of an experiment.
+
+Albert Einstein's famed retort, "God does not play dice," exemplifies the tensions between the counter-intuitive world of quantum mechanics and
+the more deterministic Newtonian worldview. However, quantum mechanics has withstood the test of time, demonstrating its indispensability to the progress of modern physics
+
+Theory of Relativity
+The theory of relativity, comprising special and general relativity, has profoundly altered our understanding of the macroscopic universe.
+Special relativity, Einstein's first foray into this domain, introduced the concept of space-time, where the fabric of the universe is both a geometrical construct
+and a medium for the propagation of electromagnetic phenomena.
+
+Further, special relativity established the idea of relative motion, where there is no absolute reference frame, and the speed of light in a vacuum is an invariant constant.
+General relativity expanded this framework, postulating that gravity is a curvature of the space-time continuum, caused by the presence of mass and energy.
+This theory, while more complex, has been empirically validated through its predictions of phenomena such as gravitational lensing and the bending of light near massive
+objects.
+
+Cosmic Consciousness
+The concept of cosmic consciousness—or the idea of a unified, interconnected consciousness pervading the cosmos—is a philosophical speculation,
+one that transcends the traditional scientific paradigm. It is a metaphysical exploration, a contemplation of the possible nature of our collective human consciousness,
+its interplay with the universe, and the implications of such a state of awareness.
+
+The integration of these three distinct realms poses a formidable challenge. Quantum mechanics and the theory of relativity have proven their efficacy
+in the realm of empirical science, while cosmic consciousness remains the province of metaphysical musings. However, the human propensity to synthesize seemingly disparate
+ideas has engendered a multitude of theories, each striving to forge a cohesive narrative from the cacophony of scientific and philosophical thought.
+
+One such approach, the 'Quantum Mind,' posits a direct link between the quantum phenomena and the workings of the human brain.
+This theory, championed by Roger Penrose and Stuart Hameroff, suggests that the microtubules within brain neurons,
+operating at the quantum scale, could serve as the neural correlates of consciousness. While intriguing,
+this hypothesis has yet to garner widespread acceptance, as the veracity of quantum effects within biological systems remains the subject of intense debate.
+
+Another avenue of exploration involves the notion of 'Quantum Biology.' Here, the focus shifts to the potential role of quantum phenomena in biology,
+particularly in processes such as photosynthesis, vision, and magnetoreception.
+While the presence of quantum effects in biological systems is becoming increasingly plausible,
+the idea of a 'quantum biology' remains a nascent and highly speculative field.
+
+The 'Holographic Universe' theory, espoused by physicist and cosmologist David Bohm,
+posits the existence of a deeper, underlying reality, one in which the universe is a holographic projection of a more fundamental,
+non-local substrate. This model, while offering an intriguing synthesis of quantum mechanics, relativity, and the concept of a cosmic consciousness,
+remains a highly speculative and unproven hypothesis.
+
+In our quest to weave together these disparate threads, we must acknowledge the limitations of our current understanding. As it stands,
+the principles of quantum mechanics and the theory of relativity remain resolutely grounded in the empirical world, while the concept of cosmic consciousness
+traverses the murky waters of metaphysics and speculation.
+
+To forge a more unified understanding, we must continue to advance our scientific knowledge, to push the frontiers of both empirical and philosophical inquiry.
+Only through the synthesis of new data, the refinement of our scientific models, and the continued evolution of our collective human consciousness,
+will we be able to construct a narrative that bridges the seemingly insurmountable gulf between the microscopic, the macroscopic, and the metaphysical.
+
+In conclusion, the unification of quantum mechanics, relativity, and cosmic consciousness is a daunting task, requiring a delicate balance between the
+concrete and the abstract, the empirical and the speculative. While the journey has thus far led us to the fringes of scientific understanding,
+we must continue to explore these frontiers, drawing upon the rich tapestry of human knowledge, in the hope of forging a more comprehensive narrative of our cosmos and
+our place within it.
+```
+
+# [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_Kukedlc__NeuralArjuna-7B-DT)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |76.58|
+|AI2 Reasoning Challenge (25-Shot)|73.12|
+|HellaSwag (10-Shot)              |88.97|
+|MMLU (5-Shot)                    |64.63|
+|TruthfulQA (0-shot)              |76.68|
+|Winogrande (5-shot)              |85.24|
+|GSM8k (5-shot)                   |70.81|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "liminerity/M7-7b",
+  "add_gates": false,
+  "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": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,31 @@
+
+models:
+  - model: liminerity/M7-7b
+    # no parameters necessary for base model
+  - model: yam-peleg/Experiment26-7B 
+    parameters:
+      weight: 0.2
+      density: 0.66
+  - model: Gille/StrangeMerges_32-7B-slerp
+    parameters:
+      weight: 0.2
+      density: 0.55
+  - model: MSL7/INEX12-7b 
+    parameters:
+      weight: 0.2
+      density: 0.33
+  - model: automerger/YamShadow-7B
+    parameters:
+      weight: 0.2
+      density: 0.66
+  - model: Kukedlc/NeuralSirKrishna-7b
+    parameters:
+      weight: 0.2
+      density: 0.66
+merge_method: dare_ties
+base_model: liminerity/M7-7b
+
+parameters:
+  int8_mask: true
+  normalize: true
+dtype: bfloat16
--- 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:c40f352f88a53678a66bd49e976d49a2f40f7d01be4803568c0e35df69d4834f
+size 9825524456
--- 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 sha256:504259be9bf1ba2d6b2a7c70b5783c3304e8cebf8b14a86c8705fe25b921b2e8
+size 4657973592
--- 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": "<unk>",
+    "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 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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": 32768,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}