Upload folder using huggingface_hub

README.md

@@ -0,0 +1,51 @@
+---
+base_model:
+- alpindale/Mistral-7B-v0.2-hf
+- mistralai/Mistral-7B-Instruct-v0.2
+- KoboldAI/Mistral-7B-Erebus-v3
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# Mistral-7B-Erebus-v3-Instruct-32k
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+Merge script copied from this [ichigoberry/pandafish-2-7b-32k](https://huggingface.co/ichigoberry/pandafish-2-7b-32k).
+
+## 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 [alpindale/Mistral-7B-v0.2-hf](https://huggingface.co/alpindale/Mistral-7B-v0.2-hf) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
+* [KoboldAI/Mistral-7B-Erebus-v3](https://huggingface.co/KoboldAI/Mistral-7B-Erebus-v3)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+ - model: alpindale/Mistral-7B-v0.2-hf
+ # No parameters necessary for base model
+ - model: mistralai/Mistral-7B-Instruct-v0.2
+ parameters:
+ density: 0.53
+ weight: 0.4
+ - model: KoboldAI/Mistral-7B-Erebus-v3
+ parameters:
+ density: 0.53
+ weight: 0.4
+merge_method: dare_ties
+base_model: alpindale/Mistral-7B-v0.2-hf
+parameters:
+ int8_mask: true
+dtype: bfloat16
+
+```

config.json

@@ -0,0 +1,26 @@
+{
+ "_name_or_path": "alpindale/Mistral-7B-v0.2-hf",
+ "architectures": [
+ "MistralForCausalLM"
+ ],
+ "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": "mistral",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 32,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.38.2",
+ "use_cache": true,
+ "vocab_size": 32000
+}

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:213f4002710728ab5a114feee4f24f41a4f75c562bbd2e6b8ad5ddcd81a702f3
+size 3854891640

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,
+ "add_prefix_space": true,
+ "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
+ }
+ },
+ "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
+}