Upload folder using huggingface_hub

README.md

@@ -0,0 +1,72 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- OmnicromsBrain/StoryFusion-7B
+- jdqwoi/TooManyMixRolePlay-7B
+base_model:
+- OmnicromsBrain/StoryFusion-7B
+- jdqwoi/TooManyMixRolePlay-7B
+---
+
+
+# EXL2 quants of [jdqwoi/TooManyMixRolePlay-7B-Story](https://huggingface.co/jdqwoi/TooManyMixRolePlay-7B-Story)
+
+[4.00 bits per weight](https://huggingface.co/kim512/TooManyMixRolePlay-7B-Story-4.0bpw-exl2)  
+[5.00 bits per weight](https://huggingface.co/kim512/TooManyMixRolePlay-7B-Story-5.0bpw-exl2)  
+[6.00 bits per weight](https://huggingface.co/kim512/TooManyMixRolePlay-7B-Story-6.0bpw-exl2)  
+[7.00 bits per weight](https://huggingface.co/kim512/TooManyMixRolePlay-7B-Story-7.0bpw-exl2)  
+[8.00 bits per weight](https://huggingface.co/kim512/TooManyMixRolePlay-7B-Story-8.0bpw-exl2)  
+
+# TooManyMixRolePlay-7B-Story
+
+TooManyMixRolePlay-7B-Story is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [OmnicromsBrain/StoryFusion-7B](https://huggingface.co/OmnicromsBrain/StoryFusion-7B)
+* [jdqwoi/TooManyMixRolePlay-7B](https://huggingface.co/jdqwoi/TooManyMixRolePlay-7B)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: OmnicromsBrain/StoryFusion-7B
+        layer_range: [0, 32]
+      - model: jdqwoi/TooManyMixRolePlay-7B
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: OmnicromsBrain/StoryFusion-7B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.5
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "jdqwoi/TooManyMixRolePlay-7B-Story"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

cal_data.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08be1103ff8fcef33b570f3c0f5ae4cc7f9dc5c3f264105baa55fc9b132ed1be
+size 1638488

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "OmnicromsBrain/StoryFusion-7B",
+  "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,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "unsloth_version": "2024.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

hidden_states.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ace25d870c54b616a70dbb2b67d963166b3f470401d21b0217c9e76e643746c
+size 1677730376

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51cc2baf44a4d589666ff1b8de5846c055eb1fd8b7cc422425f788be1afc48d2
+size 6977937724

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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": "<unk>",
+    "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 +1,47 @@
+{
+  "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": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 255,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}