初始化项目，由ModelHub XC社区提供模型

Model: DevQuasar/HermesNova-Llama-3.1-8B
Source: Original Platform

.gitattributes

@@ -0,0 +1,49 @@
+*.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
+*.model 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
+*.safetensors 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
+
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,121 @@
+---
+base_model:
+- NousResearch/Hermes-3-Llama-3.1-8B
+- arcee-ai/Llama-3.1-SuperNova-Lite
+library_name: transformers
+tags:
+- mergekit
+- merge
+license: llama3.1
+model-index:
+- name: HermesNova-Llama-3.1-8B
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      type: lm-evaluation-harness
+      name: bbh
+    metrics:
+    - name: acc_norm
+      type: acc_norm
+      value: 0.5418
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: lm-evaluation-harness
+      name: gpqa
+    metrics:
+    - name: acc_norm
+      type: acc_norm
+      value: 0.3365
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: lm-evaluation-harness
+      name: math
+    metrics:
+    - name: exact_match
+      type: exact_match
+      value: 0.1148
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: lm-evaluation-harness
+      name: mmlu
+    metrics:
+    - name: acc_norm
+      type: acc_norm
+      value: 0.3729
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: lm-evaluation-harness
+      name: musr
+    metrics:
+    - name: acc_norm
+      type: acc_norm
+      value: 0.4330
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      type: lm-evaluation-harness
+      name: hellaswag
+    metrics:
+    - name: acc
+      type: acc
+      value: 0.6306512646883091
+      verified: false
+    - name: acc_norm
+      type: acc_norm
+      value: 0.818263294164509
+      verified: false
+---
+[<img src="https://raw.githubusercontent.com/csabakecskemeti/devquasar/main/dq_logo_black-transparent.png" width="200"/>](https://devquasar.com)
+
+'Make knowledge free for everyone'
+
+<a href='https://ko-fi.com/L4L416YX7C' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi6.png?v=6' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>
+
+# HermesNova
+
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64e6d37e02dee9bcb9d9fa18/oxkvvhQOju_e5xl6REzNG.jpeg)
+
+The 2 most powerful LLama3.1 model Hermes-3-Llama-3.1-8B and Llama-3.1-SuperNova-Lite merged
+
+
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [NousResearch/Hermes-3-Llama-3.1-8B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B)
+* [arcee-ai/Llama-3.1-SuperNova-Lite](https://huggingface.co/arcee-ai/Llama-3.1-SuperNova-Lite)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: NousResearch/Hermes-3-Llama-3.1-8B
+    parameters:
+      weight: 1.0
+  - model: arcee-ai/Llama-3.1-SuperNova-Lite
+    parameters:
+      weight: 1.0
+merge_method: linear
+dtype: float16
+
+```

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128040,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

mergekit_config.yml

@@ -0,0 +1,9 @@
+models:
+  - model: NousResearch/Hermes-3-Llama-3.1-8B
+    parameters:
+      weight: 1.0
+  - model: arcee-ai/Llama-3.1-SuperNova-Lite
+    parameters:
+      weight: 1.0
+merge_method: linear
+dtype: float16

model-00001-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9271dcaa50c4f1d2fdee14d55e1ae7e788449d0ce47dbcb4e9267a67e636d01
+size 1050673280

model-00002-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b681cb5aaf74e5b02cfbbcd69ebb3c42f043d21a4f0a8a03f0b7e75fbd31936
+size 1050673288

model-00003-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:538d006c7a0b2bdaf7b6293b6c4bef93bfa3ab3629458338b9631d265bf46fe1
+size 989898984

model-00004-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66dd317e1be3467d7e9e425aae7744a3113e8ac43c27a570f2774ee7c9d3af0d
+size 989890712

model-00005-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbfd99b2829c0dd6dc00ffa6a08723191cd08876e4cb3e920c1747cce4703efd
+size 998287736

model-00006-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58215aaae3f37d47d6440d507b357d970026c88b251015955cb59b4ee0be4345
+size 947956192

model-00007-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65b0e1fbbecc14601bb4c7213774cb8cfa24a03924b3f1773538f85a2b414b23
+size 989890712

model-00008-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4fd8a045e6dd5f6071759b62591481d1afea96fc9097b54f5978a9c2ab85123
+size 989890696

model-00009-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edf3771a2266a855c87cbe66fab544223b54da442686f8d0df97bb0d166e40ac
+size 998287736

model-00010-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49efea8cac165b44d58b6ad043d8dcfb9a853fd39a1d971ccb861444cc59a8da
+size 947956192

model-00011-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af9fd847a6c1068057345127ddfd815d3b57339995dc21ddeec198018090a9e5
+size 989890712

model-00012-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea486d81c2ba7e2af489617d5a6807bb63f35752bc1ddfe15dee2eb50666da47
+size 989890712

model-00013-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab7b8a28f5015b8cbcb9f4e9e0e8bba0504c64e7ff77b3261a61906bbd7544d
+size 998287728

model-00014-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a7008b0b5023e3c1c96aae5a8100b057d9c9a28b5577965a103f895677c80d
+size 947956184

model-00015-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47874cfab84fcf552e52e7f3d6f3e0e17d0e93652a80a9eafefca2b4a057e86b
+size 989890688

model-00016-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff24c22995199a087ecf2de4dc28cfd2060738e5a963290a7675340f3bcfc06
+size 989890688

model-00017-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2723dfe02eb775b35943b374ef3423706bcba990b1de404e7a209281410221f2
+size 201343784

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:492ebf55999f2a71beed8104e12d808bfcba5a230b7e511f2c6ccbc616f9d76c
+size 9085140