初始化项目，由ModelHub XC社区提供模型

Model: martyn/mixtral-megamerge-dare-8x7b-v2 Source: Original Platform
2026-04-12 13:33:08 +08:00
commit 5f6208feed
29 changed files with 92385 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 +1,39 @@
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
+inference: false
+tags:
+- dare
+- super mario merge
+- pytorch
+- mixtral
+- merge
+---
+
+# mixtral megamerge 8x7b v2
+
+The following models were merged with DARE using [https://github.com/martyn/safetensors-merge-supermario](https://github.com/martyn/safetensors-merge-supermario)
+
+## Mergelist
+
+```
+mistralai/Mixtral-8x7B-v0.1
+mistralai/Mixtral-8x7B-Instruct-v0.1
+cognitivecomputations/dolphin-2.6-mixtral-8x7b
+Brillibitg/Instruct_Mixtral-8x7B-v0.1_Dolly15K
+orangetin/OpenHermes-Mixtral-8x7B
+NeverSleep/Noromaid-v0.1-mixtral-8x7b-v3
+```
+
+## Merge command
+
+```
+python3 hf_merge.py to_merge_mixtral2.txt mixtral-2 -p 0.15 -lambda 1.95
+```
+
+### Notes
+
+* MoE gates were filtered for compatibility then averaged with `(tensor1 + tensor2)/2`
+* seems to generalize prompting formats and sampling settings
--- a/config.json
+++ b/config.json
@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/workspace/models/Mixtral-8x7B-v0.1",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": true,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32002
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.36.0.dev0"
+}
--- a/mergelist.txt
+++ b/mergelist.txt
@@ -0,0 +1,6 @@
+mistralai/Mixtral-8x7B-v0.1
+mistralai/Mixtral-8x7B-Instruct-v0.1
+cognitivecomputations/dolphin-2.6-mixtral-8x7b
+Brillibits/Instruct_Mixtral-8x7B-v0.1_Dolly15K
+orangetin/OpenHermes-Mixtral-8x7B
+NeverSleep/Noromaid-v0.1-mixtral-8x7b-v3
--- a/model-00001-of-00019.safetensors
+++ b/model-00001-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0dfbf311572b30b01615a07cbf39ec8774dc2f16010c348f809978ad66f4be8
+size 4892825968
--- a/model-00002-of-00019.safetensors
+++ b/model-00002-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdbad6e66d2738e4ae609ce55ca29d13507dfd680d2fbe43bd52a4ea8cfb6ff9
+size 4983004016
--- a/model-00003-of-00019.safetensors
+++ b/model-00003-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:977003508efb2a265d942882e37137d9e9fbd68b08f8d6b138f6a4afa70c99ec
+size 4983004016
--- a/model-00004-of-00019.safetensors
+++ b/model-00004-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49ad786d36ebeb9acbfc626946fb162163ef2eaacbd350c7c87b972fe05f23ca
+size 4899035200
--- a/model-00005-of-00019.safetensors
+++ b/model-00005-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b97d8ac6f3206afaa693ca9d4b7cb8042d14b4a1221cac2664f4fb69f86e25d6
+size 4983004016
--- a/model-00006-of-00019.safetensors
+++ b/model-00006-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bbc60737c1f16739d81a02b48cad29f346a13a31fa6999e9993071f56befd1f
+size 4983004016
--- a/model-00007-of-00019.safetensors
+++ b/model-00007-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8597ff157700bb16cd0cabaee0190cb99504e8aa5c798f8652b5bd3cf061768a
+size 4899035248
--- a/model-00008-of-00019.safetensors
+++ b/model-00008-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e215e26eb54fbc0a219779675453e7e5fbdeb437fc32602b3ac48ead5a374228
+size 4983004072
--- a/model-00009-of-00019.safetensors
+++ b/model-00009-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e310742fa0b75372575c90d5d5069da316e39816a96ec58fc07cf42a3be2d4f8
+size 4983004072
--- a/model-00010-of-00019.safetensors
+++ b/model-00010-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9daf46fb3d72b6a7f87ad3ef7897fd3b925271bc3319545e8ade20c391dc38
+size 4899035248
--- a/model-00011-of-00019.safetensors
+++ b/model-00011-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:711193b1fcb0d337a310a07fe2a6df2ea724cad75195866cee4c5f266890be28
+size 4983004072
--- a/model-00012-of-00019.safetensors
+++ b/model-00012-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24c168f48c07853526f6dd8af0ab51d2b13cce5e402d821682caaeca5ccaf274
+size 4983004072
--- a/model-00013-of-00019.safetensors
+++ b/model-00013-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f44556473cd376827bffa529de0bc787368b0498a7e2ff59350145285a96a87
+size 4983004072
--- a/model-00014-of-00019.safetensors
+++ b/model-00014-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:490957d2945399f43ed92ea791301a38d15240fcace6c4659d743802559363e4
+size 4899035248
--- a/model-00015-of-00019.safetensors
+++ b/model-00015-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9180ab0dd77add0d8ccdc1e92b9b719c1907056708f0ecc642134f317fec4f1
+size 4983004072
--- a/model-00016-of-00019.safetensors
+++ b/model-00016-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7a30ea0e19ac5f9e36b4f410446910e7cb49c063f82f9cb198420a7559e31d4
+size 4983004072
--- a/model-00017-of-00019.safetensors
+++ b/model-00017-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:821bbe6c0e5b73291ee864f311d09dd22a48cf3ad0d0f53e2d02d58388f15887
+size 4899035248
--- a/model-00018-of-00019.safetensors
+++ b/model-00018-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40edce4bd5a5e6c80f2499fc8f22fe2035c452b6a0c0d188bf0d665dfaf35e07
+size 4983004072
--- a/model-00019-of-00019.safetensors
+++ b/model-00019-of-00019.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a3c297a086cbb73e094bf3fb13ec4079d25ce8ac99e1c3166634bccb76c1d7d
+size 4221695472
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "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": "</s>",
+  "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 +1,61 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": true,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}