初始化项目，由ModelHub XC社区提供模型

Model: jaspionjader/Kosmos-EVAA-Franken-Immersive-v40-8B
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+base_model:
+- jaspionjader/Kosmos-EVAA-Franken-Immersive-v39-8B
+- jaspionjader/knf-1-8b
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# 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 SLERP merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [jaspionjader/Kosmos-EVAA-Franken-Immersive-v39-8B](https://huggingface.co/jaspionjader/Kosmos-EVAA-Franken-Immersive-v39-8B)
+* [jaspionjader/knf-1-8b](https://huggingface.co/jaspionjader/knf-1-8b)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+- sources:
+  - model: jaspionjader/Kosmos-EVAA-Franken-Immersive-v39-8B
+    layer_range:
+    - 0
+    - 32
+  - model: jaspionjader/knf-1-8b
+    layer_range:
+    - 0
+    - 32
+merge_method: slerp
+base_model: jaspionjader/Kosmos-EVAA-Franken-Immersive-v39-8B
+parameters:
+  t:
+  - filter: self_attn
+    value:
+    - 0.35
+    - 0.25
+    - 0.27
+    - 0.33
+    - 0.3
+  - filter: mlp
+    value:
+    - 0.25
+    - 0.35
+    - 0.33
+    - 0.27
+    - 0.7
+  - value: 0.41
+dtype: bfloat16
+```

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "jaspionjader/Kosmos-EVAA-Franken-Immersive-v39-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "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": "bfloat16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

mergekit_config.yml

@@ -0,0 +1,30 @@
+slices:
+- sources:
+  - model: jaspionjader/Kosmos-EVAA-Franken-Immersive-v39-8B
+    layer_range:
+    - 0
+    - 32
+  - model: jaspionjader/knf-1-8b
+    layer_range:
+    - 0
+    - 32
+merge_method: slerp
+base_model: jaspionjader/Kosmos-EVAA-Franken-Immersive-v39-8B
+parameters:
+  t:
+  - filter: self_attn
+    value:
+    - 0.35
+    - 0.25
+    - 0.27
+    - 0.33
+    - 0.3
+  - filter: mlp
+    value:
+    - 0.25
+    - 0.35
+    - 0.33
+    - 0.27
+    - 0.7
+  - value: 0.41
+dtype: bfloat16

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b756d4a23109a9844ddf832989f087137f50c277f3754fc8804632843e70acca
+size 4953586384

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0d2edc2806be7642561a099b5eeaf6af1fd03d2db584f456a0cb972bd0d9697
+size 4999819336

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38ce600cd3a283e5e2771a8e31e20d5b7158ab2f22b793d071c29bc020ebfc8e
+size 4915916144

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bac0f0fd507e9c749d7fa46213a6f9c92c1ec299746dbe02aff6cc4a6e04eaa
+size 1191234472

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": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920