Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ 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
+remix.webp filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,7 +1,10 @@
 ---
 base_model:
-- Moraliane/NekoMix-12B
-library_name: exllamav2
+- IlyaGusev/saiga_nemo_12b
+- Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24
+- TheDrummer/Rocinante-12B-v1.1
+- MarinaraSpaghetti/NemoMix-Unleashed-12B
+library_name: transformers
 tags:
 - mergekit
 - merge
@@ -12,29 +15,6 @@ language:
 - ru
 - en
 ---
-# NekoMix-12B-exl2
-Original model: [NekoMix-12B](https://huggingface.co/Moraliane/NekoMix-12B) by [Moraliane](https://huggingface.co/Moraliane)  
-
-## Quants
-[4bpw h6 (main)](https://huggingface.co/cgus/NekoMix-12B-exl2/tree/main)  
-[4.5bpw h6](https://huggingface.co/cgus/NekoMix-12B-exl2/tree/4.5bpw-h6)  
-[5bpw h6](https://huggingface.co/cgus/NekoMix-12B-exl2/tree/5bpw-h6)  
-[6bpw h6](https://huggingface.co/cgus/NekoMix-12B-exl2/tree/6bpw-h6)  
-[8bpw h8](https://huggingface.co/cgus/NekoMix-12B-exl2/tree/8bpw-h8)  
-
-## Quantization notes
-Made with Exllamav2 0.2.8 with default dataset.  
-It seems to be primarily a Russian RP model. No clue how it performs at all.  
-It can be used with TabbyAPI or Text-Generation-WebUI with RTX GPU on Windows or RTX/ROCm on Linux.  
-Exllamav2 doesn't support offloading to RAM, so make sure it fits your GPU. Otherwise use GGUF quants instead.  
-For example, with 12GB VRAM it can be used at 6bpw/Q6 cache at 16k context.  
-
-Эта модель может использоваться с TabbyAPI или Text-Generation-WebUI.  
-Для работы с ней требуется Nvidia RTX (Windows) или RTX/ROCm (Linux).  
-Exl2 формат требует, чтобы модель полностью помещалась в видеопамяти.  
-Например, с 12ГБ видеопамяти можно использовать 6bpw версию с Q6 кэшем с 16k контекстом.
-
-# Original model card
 # NekoMix-12B
 
 ![NekoMix-12B](./remix.webp)

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)"
+        }
+    }
+}

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa1b072d84efc707bc94166e143cf7586086fc99844f32b8c8bd9608ee6a82a
+size 7326722564

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