初始化项目，由ModelHub XC社区提供模型

Model: davzoku/frankencria-llama2-12.5b-v1.3-m.2 Source: Original Platform
2026-05-06 07:59:45 +08:00
commit 74d62227c5
23 changed files with 93702 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 +1,86 @@
+---
+inference: false
+language: en
+license: llama2
+model_type: llama
+datasets:
+  - mlabonne/CodeLlama-2-20k
+pipeline_tag: text-generation
+base_model:
+- davzoku/cria-llama2-7b-v1.3
+library_name: transformers
+tags:
+- mergekit
+- merge
+- llama-2
+
+---
+# FrankenCRIA v1.3-m.2
+
+## What is FrankenCRIA?
+
+<p align="center">
+  <img src="https://github.com/davzoku/cria/blob/main/assets/frankencria-icon-512x512.png?raw=true" width="300" height="300" alt="FrankenCRIA Logo"> <br>
+  <i>This is a frankenmerge of <a href="https://huggingface.co/davzoku/cria-llama2-7b-v1.3">davzoku/cria-llama2-7b-v1.3</a>.</i>
+</p>
+
+The configuration is the same as [vilm/vinallama-12.5b-chat-DUS](https://huggingface.co/vilm/vinallama-12.5b-chat-DUS).
+
+
+Please be aware that this model is highly experimental, and no further training has been conducted following the merge. 
+Therefore, the model performance may not meet expectations, as described in the [SOLAR paper](https://arxiv.org/abs/2312.15166)
+
+
+## 📦 FrankenCRIA Model Release
+
+FrankenCRIA v1.3 comes with several variants.
+
+- [davzoku/frankencria-llama2-11b-v1.3-m.1](https://huggingface.co/davzoku/frankencria-llama2-11b-v1.3-m.1): 11B FrankenMerge inspired by [Undi95/Mistral-11B-v0.1](https://huggingface.co/Undi95/Mistral-11B-v0.1)
+- [davzoku/frankencria-llama2-12.5b-v1.3-m.2](https://huggingface.co/davzoku/frankencria-llama2-12.5b-v1.3-m.2): 12.5B interleaving FrankenMerge inspired by [vilm/vinallama-12.5b-chat-DUS](https://huggingface.co/vilm/vinallama-12.5b-chat-DUS)
+
+
+## 🧩 Merge Details 
+### Merge Method
+
+This model was merged using the passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [davzoku/cria-llama2-7b-v1.3](https://huggingface.co/davzoku/cria-llama2-7b-v1.3)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+# https://huggingface.co/vilm/vinallama-12.5b-chat-DUS
+slices:
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [0, 16]
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [8, 16]
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [8, 16]
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [16, 24]
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [16, 24]
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [24, 28]
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [24, 28]
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [28, 32]
+merge_method: passthrough
+dtype: bfloat16
+
+```
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,3 @@
+{
+  "<pad>": 32000
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "davzoku/cria-llama2-7b-v1.3",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "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": 60,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/mergekit_config.yml
+++ b/mergekit_config.yml
@@ -0,0 +1,28 @@
+# https://huggingface.co/vilm/vinallama-12.5b-chat-DUS
+slices:
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [0, 16]
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [8, 16]
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [8, 16]
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [16, 24]
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [16, 24]
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [24, 28]
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [24, 28]
+  - sources:
+      - model: davzoku/cria-llama2-7b-v1.3
+        layer_range: [28, 32]
+merge_method: passthrough
+dtype: bfloat16
--- a/model-00001-of-00013.safetensors
+++ b/model-00001-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca50ee464f25993d854dabec72ae82d858210cffe320021b6c88faa8047ed79
+size 1979781688
--- a/model-00002-of-00013.safetensors
+++ b/model-00002-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38f886bca8993f0a51f9e9bf2aec4b0b13cb11cd94bacac1c45d2a8aff1c8342
+size 1967215752
--- a/model-00003-of-00013.safetensors
+++ b/model-00003-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c735f1679e4ef078fafc38608ae47f465e0c1456e6610fc8f1fe822874df83e5
+size 1990284288
--- a/model-00004-of-00013.safetensors
+++ b/model-00004-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d65e02bb4c93f3b3ce934022c818aba54a5b878ee2fc3362b93f44bcf4d873b
+size 1933661184
--- a/model-00005-of-00013.safetensors
+++ b/model-00005-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f9af6c8b6adf6e9e24e3398426f50a95f8bcf35ecd9636a1c16e5c3e67b7491
+size 1979790008
--- a/model-00006-of-00013.safetensors
+++ b/model-00006-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b740dcefb296e5f4db654a12ad9ab48afbc8bd88023a41ecc8fc061642c83b33
+size 1933652880
--- a/model-00007-of-00013.safetensors
+++ b/model-00007-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1043ad3301fed76d0d717e7541e63527a7d05bb7bbaa88d58c68aed6310ecfd
+size 1977718344
--- a/model-00008-of-00013.safetensors
+++ b/model-00008-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02b9e84e7566dbe8a93a6a103783511784630ab8dd7e1d023c5134e3d967bc62
+size 1935724512
--- a/model-00009-of-00013.safetensors
+++ b/model-00009-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d50f8378a9b534408eb4b434a36b613c84685b94c64e21f326d0fd54006efe9
+size 1977726600
--- a/model-00010-of-00013.safetensors
+++ b/model-00010-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06df8f427a9c11645664e2aa5fe13438b46e4c3e06f97b23cb327cfcb8a1bf71
+size 1753297528
--- a/model-00011-of-00013.safetensors
+++ b/model-00011-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84efd33a923751217b8b135ee07b4530fc239c49ec5564694098e8475c02fbbd
+size 1918955112
--- a/model-00012-of-00013.safetensors
+++ b/model-00012-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bad44acf169e755d69e7abdfca1ab39c8f431f28c04eadba7d9f691420d2713
+size 1933661184
--- a/model-00013-of-00013.safetensors
+++ b/model-00013-of-00013.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:265138a9c0e6d77f81e8f233e4678d67b15e81b97d6dee5daa495f47cd48a80f
+size 1528893416
--- 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": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "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
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,48 @@
+{
+  "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": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}