Upload 7 files

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* 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
+learderboard.png filter=lfs diff=lfs merge=lfs -text
+remixwife.webp filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,96 @@
+---
+base_model:
+- IlyaGusev/saiga_nemo_12b
+- elinas/Chronos-Gold-12B-1.0
+- Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24
+- MarinaraSpaghetti/NemoMix-Unleashed-12B
+library_name: transformers
+tags:
+- mergekit
+- merge
+- rp
+- role-play
+- mistral
+language:
+- ru
+- en
+---
+# SAINEMO-reMIX
+![SAINEMO-reMIX](./remixwife.webp)
+
+# GGUF: thx team mradermacher
+https://huggingface.co/mradermacher/SAINEMO-reMIX-GGUF
+
+# GGUF imatrix
+https://huggingface.co/mradermacher/SAINEMO-reMIX-i1-GGUF
+# learderboard
+![SAINEMO-reMIX](./learderboard.png)
+
+# Presets
+The given presets are quite suitable for this model. https://huggingface.co/MarinaraSpaghetti/SillyTavern-Settings/tree/main/Customized/Mistral%20Improved
+# Sampler
+
+
+```
+Temp - 0,7 - 1,2 ~
+TopA - 0,1
+DRY - 0,8 1,75 2 0
+I recommend trying the stock presets from SillyTavern, such as simple-1.
+```
+
+
+
+
+
+
+
+
+
+
+
+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 della_linear merge method using E:\Programs\TextGen\text-generation-webui\models\IlyaGusev_saiga_nemo_12b as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* E:\Programs\TextGen\text-generation-webui\models\elinas_Chronos-Gold-12B-1.0
+* E:\Programs\TextGen\text-generation-webui\models\Vikhrmodels_Vikhr-Nemo-12B-Instruct-R-21-09-24
+* E:\Programs\TextGen\text-generation-webui\models\MarinaraSpaghetti_NemoMix-Unleashed-12B
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: E:\Programs\TextGen\text-generation-webui\models\IlyaGusev_saiga_nemo_12b
+    parameters:
+      weight: 0.55  # Основной акцент на русском языке
+      density: 0.4
+  - model: E:\Programs\TextGen\text-generation-webui\models\MarinaraSpaghetti_NemoMix-Unleashed-12B
+    parameters:
+      weight: 0.2  # РП модель, чуть меньший вес из-за ориентации на английский
+      density: 0.4
+  - model: E:\Programs\TextGen\text-generation-webui\models\elinas_Chronos-Gold-12B-1.0
+    parameters:
+      weight: 0.15  # Вторая РП модель
+      density: 0.4
+  - model: E:\Programs\TextGen\text-generation-webui\models\Vikhrmodels_Vikhr-Nemo-12B-Instruct-R-21-09-24
+    parameters:
+      weight: 0.25  # Русскоязычная поддержка и баланс
+      density: 0.4
+
+merge_method: della_linear
+base_model: E:\Programs\TextGen\text-generation-webui\models\IlyaGusev_saiga_nemo_12b
+parameters:
+  epsilon: 0.05
+  lambda: 1
+dtype: float16
+tokenizer_source: base
+
+```

config.json

@@ -0,0 +1,40 @@
+{
+    "_name_or_path": "E:\\Programs\\TextGen\\text-generation-webui\\models\\IlyaGusev_saiga_nemo_12b",
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 1024000,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "pad_token_id": 10,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.46.3",
+    "unsloth_version": "2024.8",
+    "use_cache": true,
+    "vocab_size": 131072,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.2.8",
+        "bits": 4.0,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

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": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "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:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292