Upload folder using huggingface_hub

README.md

@@ -0,0 +1,177 @@
+---
+base_model:
+- m-a-p/neo_7b
+- m-a-p/neo_7b
+tags:
+- merge
+- mergekit
+- lazymergekit
+- m-a-p/neo_7b
+---
+
+# Neo_7b-merge4
+
+Neo_7b-merge4 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [m-a-p/neo_7b](https://huggingface.co/m-a-p/neo_7b)
+* [m-a-p/neo_7b](https://huggingface.co/m-a-p/neo_7b)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  # Group 1
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [0, 0]
+      - model: m-a-p/neo_7b
+        layer_range: [3, 3]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [1, 1]
+      - model: m-a-p/neo_7b
+        layer_range: [3, 3]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [2, 2]
+      - model: m-a-p/neo_7b
+        layer_range: [3, 3]
+  # Group 2
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [4, 4]
+      - model: m-a-p/neo_7b
+        layer_range: [7, 7]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [5, 5]
+      - model: m-a-p/neo_7b
+        layer_range: [7, 7]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [6, 6]
+      - model: m-a-p/neo_7b
+        layer_range: [7, 7]
+  # Group 3
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [8, 8]
+      - model: m-a-p/neo_7b
+        layer_range: [11, 11]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [9, 9]
+      - model: m-a-p/neo_7b
+        layer_range: [11, 11]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [10, 10]
+      - model: m-a-p/neo_7b
+        layer_range: [11, 11]
+  # Group 4
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [12, 12]
+      - model: m-a-p/neo_7b
+        layer_range: [15, 15]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [13, 13]
+      - model: m-a-p/neo_7b
+        layer_range: [15, 15]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [14, 14]
+      - model: m-a-p/neo_7b
+        layer_range: [15, 15]
+  # Group 5
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [16, 16]
+      - model: m-a-p/neo_7b
+        layer_range: [19, 19]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [17, 17]
+      - model: m-a-p/neo_7b
+        layer_range: [19, 19]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [18, 18]
+      - model: m-a-p/neo_7b
+        layer_range: [19, 19]
+  # Group 6
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [20, 20]
+      - model: m-a-p/neo_7b
+        layer_range: [23, 23]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [21, 21]
+      - model: m-a-p/neo_7b
+        layer_range: [23, 23]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [22, 22]
+      - model: m-a-p/neo_7b
+        layer_range: [23, 23]
+  # Group 7 (last group)
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [24, 24]
+      - model: m-a-p/neo_7b
+        layer_range: [27, 27]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [25, 25]
+      - model: m-a-p/neo_7b
+        layer_range: [27, 27]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [26, 26]
+      - model: m-a-p/neo_7b
+        layer_range: [27, 27]
+merge_method: slerp
+base_model: m-a-p/neo_7b
+parameters:
+  t: 0.3333  # Apply 1/3 of the 4th layer to each of the previous 3 layers
+dtype: bfloat16
+output_path: ./merged_redistributed_neo_7b
+model_config:
+  num_hidden_layers: 21
+  attention_bias: false
+  attention_dropout: 0.0
+  hidden_act: "silu"
+  hidden_size: 3072
+  intermediate_size: 24576
+  num_attention_heads: 16
+  num_key_value_heads: 16
+  rms_norm_eps: 1e-05
+  rope_theta: 10000.0
+  use_cache: true
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "DewEfresh/Neo_7b-merge4"
+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"])
+```

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<|CLS|>": 64000,
+  "<|EOD|>": 64002,
+  "<|MASK|>": 64003,
+  "<|PAD|>": 64004,
+  "<|SEP|>": 64001
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "m-a-p/neo_7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 0,
+  "num_key_value_heads": 16,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.3",
+  "use_cache": true,
+  "vocab_size": 64256
+}

mergekit_config.yml

@@ -0,0 +1,132 @@
+
+slices:
+  # Group 1
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [0, 0]
+      - model: m-a-p/neo_7b
+        layer_range: [3, 3]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [1, 1]
+      - model: m-a-p/neo_7b
+        layer_range: [3, 3]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [2, 2]
+      - model: m-a-p/neo_7b
+        layer_range: [3, 3]
+  # Group 2
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [4, 4]
+      - model: m-a-p/neo_7b
+        layer_range: [7, 7]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [5, 5]
+      - model: m-a-p/neo_7b
+        layer_range: [7, 7]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [6, 6]
+      - model: m-a-p/neo_7b
+        layer_range: [7, 7]
+  # Group 3
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [8, 8]
+      - model: m-a-p/neo_7b
+        layer_range: [11, 11]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [9, 9]
+      - model: m-a-p/neo_7b
+        layer_range: [11, 11]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [10, 10]
+      - model: m-a-p/neo_7b
+        layer_range: [11, 11]
+  # Group 4
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [12, 12]
+      - model: m-a-p/neo_7b
+        layer_range: [15, 15]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [13, 13]
+      - model: m-a-p/neo_7b
+        layer_range: [15, 15]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [14, 14]
+      - model: m-a-p/neo_7b
+        layer_range: [15, 15]
+  # Group 5
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [16, 16]
+      - model: m-a-p/neo_7b
+        layer_range: [19, 19]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [17, 17]
+      - model: m-a-p/neo_7b
+        layer_range: [19, 19]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [18, 18]
+      - model: m-a-p/neo_7b
+        layer_range: [19, 19]
+  # Group 6
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [20, 20]
+      - model: m-a-p/neo_7b
+        layer_range: [23, 23]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [21, 21]
+      - model: m-a-p/neo_7b
+        layer_range: [23, 23]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [22, 22]
+      - model: m-a-p/neo_7b
+        layer_range: [23, 23]
+  # Group 7 (last group)
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [24, 24]
+      - model: m-a-p/neo_7b
+        layer_range: [27, 27]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [25, 25]
+      - model: m-a-p/neo_7b
+        layer_range: [27, 27]
+  - sources:
+      - model: m-a-p/neo_7b
+        layer_range: [26, 26]
+      - model: m-a-p/neo_7b
+        layer_range: [27, 27]
+merge_method: slerp
+base_model: m-a-p/neo_7b
+parameters:
+  t: 0.3333  # Apply 1/3 of the 4th layer to each of the previous 3 layers
+dtype: bfloat16
+output_path: ./merged_redistributed_neo_7b
+model_config:
+  num_hidden_layers: 21
+  attention_bias: false
+  attention_dropout: 0.0
+  hidden_act: "silu"
+  hidden_size: 3072
+  intermediate_size: 24576
+  num_attention_heads: 16
+  num_key_value_heads: 16
+  rms_norm_eps: 1e-05
+  rope_theta: 10000.0
+  use_cache: true

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41209159383a6438fa1e73146df470aae582c40bf510ec2495a3f8780477ce87
+size 789584192

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93f2a7f3db85521671732789bb8fd1bb3ae3a7e0d33170ea530f53a25346fcdd
+size 4998668592

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1227a57ac0fc74f5a2c223e5e41dd53ba09f50acbf6d63e5f166a8e1fc740c5e
+size 4926336584

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5abc28b3d1b89d4077e831f565ea2b0794a20ade31c750e450a00c7ebc9327ea
+size 4907455792

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:028abab236ed774f37153fc8d7c0dc2f87b34b3dc964d20ffab314a43f3d6706
+size 226505520

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 789583872}, "weight_map": {"lm_head.weight": "model-00001-of-00001.safetensors", "model.embed_tokens.weight": "model-00001-of-00001.safetensors", "model.norm.weight": "model-00001-of-00001.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "additional_special_tokens": [
+    "<|CLS|>",
+    "<|SEP|>",
+    "<|EOD|>",
+    "<|MASK|>",
+    "<|PAD|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a2447b0e5664cabb2481587597102d82f42f0ccb7ef22e1c2d95494a8b03c5
+size 1002561

tokenizer_config.json

@@ -0,0 +1,95 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "64000": {
+      "content": "<|CLS|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64001": {
+      "content": "<|SEP|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64002": {
+      "content": "<|EOD|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64003": {
+      "content": "<|MASK|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64004": {
+      "content": "<|PAD|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|CLS|>",
+    "<|SEP|>",
+    "<|EOD|>",
+    "<|MASK|>",
+    "<|PAD|>"
+  ],
+  "auto_map": {
+    "AutoTokenizer": [
+      "m-a-p/neo_7b--tokenization_neo.NEOTokenizer",
+      null
+    ]
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% set system_message = 'You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.\\n\\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don\\'t know the answer to a question, please don\\'t share false information.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if loop.index0 == 0 and system_message is defined %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '<s>' + '[INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "NEOTokenizer",
+  "unk_token": "<unk>",
+  "use_fast": false
+}