Upload folder using huggingface_hub

README.md

@@ -0,0 +1,55 @@
+---
+base_model: []
+tags:
+- mergekit
+- merge
+
+---
+
+Quantized using 200 samples of 8192 tokens from an RP-oriented [PIPPA](https://huggingface.co/datasets/royallab/PIPPA-cleaned) dataset.
+
+Requires ExllamaV2 version 0.0.11 and up.
+
+Original model link: [Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss-DARE-TIES](https://huggingface.co/Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss-DARE-TIES)
+
+Original model README below.
+
+***
+
+# Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss-DARE-TIES
+
+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 [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using ./extra_hdd/Mixtral-8x7B-v0.1 as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* ./extra_hdd2/Mixtral-8x7B-Instruct-v0.1
+* ./extra_hdd/Mixtral-8x7B-v0.1-LimaRP-ZLoss
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: ./extra_hdd2/Mixtral-8x7B-Instruct-v0.1
+    parameters:
+      density: 0.5
+      weight: 1.0
+  - model: ./extra_hdd/Mixtral-8x7B-v0.1-LimaRP-ZLoss
+    parameters:
+      density: 0.5
+      weight: 0.5
+merge_method: dare_ties
+base_model: ./extra_hdd/Mixtral-8x7B-v0.1
+parameters:
+  #normalize: false
+  #int8_mask: true
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "./extra_hdd/Mixtral-8x7B-v0.1",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "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": false,
+  "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": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,15 @@
+models:
+  - model: ./extra_hdd2/Mixtral-8x7B-Instruct-v0.1
+    parameters:
+      density: 0.5
+      weight: 1.0
+  - model: ./extra_hdd/Mixtral-8x7B-v0.1-LimaRP-ZLoss
+    parameters:
+      density: 0.5
+      weight: 0.5
+merge_method: dare_ties
+base_model: ./extra_hdd/Mixtral-8x7B-v0.1
+parameters:
+  #normalize: false
+  #int8_mask: true
+dtype: bfloat16

output-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b96ddfd82f65a74fea2b46450b15d3762f7fe2778b41016bb81fedc11e290b07
+size 8587044912

output-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05c5caa1dc4cd31ae19b6468b0ee19b261a59e58641c8ed554fd39499de54585
+size 8590141584

output-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb47923e8f88ecb43a8b43ab653884c3020c4486921c6c266a0fa3d9d2f3df0
+size 4693482920

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}