Upload folder using huggingface_hub

README.md

@@ -0,0 +1,59 @@
+---
+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. For purposes other than RP, use quantizations done on a more general dataset.
+
+Requires ExllamaV2 version 0.0.11 and up.
+
+Original model link: [notstoic/Nous-Hermes-2-Mixtruct-v0.1-8x7B-DPO-DARE_TIES](https://huggingface.co/notstoic/Nous-Hermes-2-Mixtruct-v0.1-8x7B-DPO-DARE_TIES)
+
+Original model README below.
+
+***
+
+# Nous-Hermes-2-Mixtruct-v0.1-8x7B-DPO-DARE_TIES
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+
+An experimental merge.
+
+Prompt format: ChatML or Mixtral-8x7B-Instruct-v0.1
+
+### 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 ./models/Mixtral-8x7B-v0.1 as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
+* [Nous-Hermes-2-Mixtral-8x7B-DPO](https://huggingface.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: ./models/Mixtral-8x7B-Instruct-v0.1
+    parameters:
+      density: 0.5
+      weight: 1.0
+  - model: ./models/Nous-Hermes-2-Mixtral-8x7B-DPO
+    parameters:
+      density: 0.5
+      weight: 0.5
+merge_method: dare_ties
+base_model: ./models/Mixtral-8x7B-v0.1
+parameters:
+  #normalize: false
+  #int8_mask: true
+dtype: bfloat16
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "./models/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: ./models/Mixtral-8x7B-Instruct-v0.1
+    parameters:
+      density: 0.5
+      weight: 1.0
+  - model: ./models/Nous-Hermes-2-Mixtral-8x7B-DPO
+    parameters:
+      density: 0.5
+      weight: 0.5
+merge_method: dare_ties
+base_model: ./models/Mixtral-8x7B-v0.1
+parameters:
+  #normalize: false
+  #int8_mask: true
+dtype: bfloat16

output-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b8542f1a4c5a51cd9a4fc47460ad4fa422464b7b8ed632359f1b7ccf1c97ff9
+size 8569572792

output-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5c23414151cd3f0ed2f64c8c43049ba063422575dce69be32e8c06ed68d767c
+size 8590094464

output-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9aa57ae48d52f9dbe1a654e94ba46fc0a814013a1a7f20af6f1ceea9ca967b3
+size 8580775624

output-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c31beb2c633632e6951d557637ee468e5be1de8a8b06c53135d26e11da10f0
+size 3674523552

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
+}