Upload folder using huggingface_hub

README.md

@@ -0,0 +1,248 @@
+---
+base_model:
+- DewEfresh/neo_7b
+tags:
+- merge
+- mergekit
+- lazymergekit
+- DewEfresh/neo_7b
+---
+
+# Neo_7b-merge6
+
+Neo_7b-merge6 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [DewEfresh/neo_7b](https://huggingface.co/DewEfresh/neo_7b)
+
+## 🧩 Configuration
+
+```yaml
+models:
+  - model: m-a-p/neo_7b
+  - model: DewEfresh/neo_7b
+    parameters:
+      weight: 0.5
+merge_method: slerp
+base_model: m-a-p/neo_7b
+parameters:
+  t: 0.5
+dtype: bfloat16
+
+custom_layers:
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [0, 3]
+      - model: DewEfresh/neo_7b
+        layers: [0, 3]
+    method: weighted_average
+    target_layers: [0]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [1, 3]
+      - model: DewEfresh/neo_7b
+        layers: [1, 3]
+    method: weighted_average
+    target_layers: [1]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [2, 3]
+      - model: DewEfresh/neo_7b
+        layers: [2, 3]
+    method: weighted_average
+    target_layers: [2]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [4, 7]
+      - model: DewEfresh/neo_7b
+        layers: [4, 7]
+    method: weighted_average
+    target_layers: [3]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [5, 7]
+      - model: DewEfresh/neo_7b
+        layers: [5, 7]
+    method: weighted_average
+    target_layers: [4]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [6, 7]
+      - model: DewEfresh/neo_7b
+        layers: [6, 7]
+    method: weighted_average
+    target_layers: [5]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [8, 11]
+      - model: DewEfresh/neo_7b
+        layers: [8, 11]
+    method: weighted_average
+    target_layers: [6]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [9, 11]
+      - model: DewEfresh/neo_7b
+        layers: [9, 11]
+    method: weighted_average
+    target_layers: [7]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [10, 11]
+      - model: DewEfresh/neo_7b
+        layers: [10, 11]
+    method: weighted_average
+    target_layers: [8]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [12, 15]
+      - model: DewEfresh/neo_7b
+        layers: [12, 15]
+    method: weighted_average
+    target_layers: [9]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [13, 15]
+      - model: DewEfresh/neo_7b
+        layers: [13, 15]
+    method: weighted_average
+    target_layers: [10]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [14, 15]
+      - model: DewEfresh/neo_7b
+        layers: [14, 15]
+    method: weighted_average
+    target_layers: [11]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [16, 19]
+      - model: DewEfresh/neo_7b
+        layers: [16, 19]
+    method: weighted_average
+    target_layers: [12]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [17, 19]
+      - model: DewEfresh/neo_7b
+        layers: [17, 19]
+    method: weighted_average
+    target_layers: [13]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [18, 19]
+      - model: DewEfresh/neo_7b
+        layers: [18, 19]
+    method: weighted_average
+    target_layers: [14]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [20, 23]
+      - model: DewEfresh/neo_7b
+        layers: [20, 23]
+    method: weighted_average
+    target_layers: [15]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [21, 23]
+      - model: DewEfresh/neo_7b
+        layers: [21, 23]
+    method: weighted_average
+    target_layers: [16]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [22, 23]
+      - model: DewEfresh/neo_7b
+        layers: [22, 23]
+    method: weighted_average
+    target_layers: [17]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [24, 27]
+      - model: DewEfresh/neo_7b
+        layers: [24, 27]
+    method: weighted_average
+    target_layers: [18]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [25, 27]
+      - model: DewEfresh/neo_7b
+        layers: [25, 27]
+    method: weighted_average
+    target_layers: [19]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [26, 27]
+      - model: DewEfresh/neo_7b
+        layers: [26, 27]
+    method: weighted_average
+    target_layers: [20]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [28, 31]
+      - model: DewEfresh/neo_7b
+        layers: [28, 31]
+    method: weighted_average
+    target_layers: [21]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [29, 31]
+      - model: DewEfresh/neo_7b
+        layers: [29, 31]
+    method: weighted_average
+    target_layers: [22]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [30, 31]
+      - model: DewEfresh/neo_7b
+        layers: [30, 31]
+    method: weighted_average
+    target_layers: [23]
+    layer_weights: [0.75, 0.25]
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "DewEfresh/Neo_7b-merge6"
+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": 28,
+  "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 +1,205 @@
+
+models:
+  - model: m-a-p/neo_7b
+  - model: DewEfresh/neo_7b
+    parameters:
+      weight: 0.5
+merge_method: slerp
+base_model: m-a-p/neo_7b
+parameters:
+  t: 0.5
+dtype: bfloat16
+
+custom_layers:
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [0, 3]
+      - model: DewEfresh/neo_7b
+        layers: [0, 3]
+    method: weighted_average
+    target_layers: [0]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [1, 3]
+      - model: DewEfresh/neo_7b
+        layers: [1, 3]
+    method: weighted_average
+    target_layers: [1]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [2, 3]
+      - model: DewEfresh/neo_7b
+        layers: [2, 3]
+    method: weighted_average
+    target_layers: [2]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [4, 7]
+      - model: DewEfresh/neo_7b
+        layers: [4, 7]
+    method: weighted_average
+    target_layers: [3]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [5, 7]
+      - model: DewEfresh/neo_7b
+        layers: [5, 7]
+    method: weighted_average
+    target_layers: [4]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [6, 7]
+      - model: DewEfresh/neo_7b
+        layers: [6, 7]
+    method: weighted_average
+    target_layers: [5]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [8, 11]
+      - model: DewEfresh/neo_7b
+        layers: [8, 11]
+    method: weighted_average
+    target_layers: [6]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [9, 11]
+      - model: DewEfresh/neo_7b
+        layers: [9, 11]
+    method: weighted_average
+    target_layers: [7]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [10, 11]
+      - model: DewEfresh/neo_7b
+        layers: [10, 11]
+    method: weighted_average
+    target_layers: [8]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [12, 15]
+      - model: DewEfresh/neo_7b
+        layers: [12, 15]
+    method: weighted_average
+    target_layers: [9]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [13, 15]
+      - model: DewEfresh/neo_7b
+        layers: [13, 15]
+    method: weighted_average
+    target_layers: [10]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [14, 15]
+      - model: DewEfresh/neo_7b
+        layers: [14, 15]
+    method: weighted_average
+    target_layers: [11]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [16, 19]
+      - model: DewEfresh/neo_7b
+        layers: [16, 19]
+    method: weighted_average
+    target_layers: [12]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [17, 19]
+      - model: DewEfresh/neo_7b
+        layers: [17, 19]
+    method: weighted_average
+    target_layers: [13]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [18, 19]
+      - model: DewEfresh/neo_7b
+        layers: [18, 19]
+    method: weighted_average
+    target_layers: [14]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [20, 23]
+      - model: DewEfresh/neo_7b
+        layers: [20, 23]
+    method: weighted_average
+    target_layers: [15]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [21, 23]
+      - model: DewEfresh/neo_7b
+        layers: [21, 23]
+    method: weighted_average
+    target_layers: [16]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [22, 23]
+      - model: DewEfresh/neo_7b
+        layers: [22, 23]
+    method: weighted_average
+    target_layers: [17]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [24, 27]
+      - model: DewEfresh/neo_7b
+        layers: [24, 27]
+    method: weighted_average
+    target_layers: [18]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [25, 27]
+      - model: DewEfresh/neo_7b
+        layers: [25, 27]
+    method: weighted_average
+    target_layers: [19]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [26, 27]
+      - model: DewEfresh/neo_7b
+        layers: [26, 27]
+    method: weighted_average
+    target_layers: [20]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [28, 31]
+      - model: DewEfresh/neo_7b
+        layers: [28, 31]
+    method: weighted_average
+    target_layers: [21]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [29, 31]
+      - model: DewEfresh/neo_7b
+        layers: [29, 31]
+    method: weighted_average
+    target_layers: [22]
+    layer_weights: [0.75, 0.25]
+  - sources:
+      - model: m-a-p/neo_7b
+        layers: [30, 31]
+      - model: DewEfresh/neo_7b
+        layers: [30, 31]
+    method: weighted_average
+    target_layers: [23]
+    layer_weights: [0.75, 0.25]

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 sha256:842f7380860bf7fcbc76d2380d90cadd65d691872aea7b707c770947a2456da6
+size 4907455800

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c646eb68fbc0f40d473ef6eb80dd23fcb436002f2f32848ec9e4c3e46ad8e216
+size 755001136

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 15587432448}, "weight_map": {"lm_head.weight": "model-00001-of-00004.safetensors", "model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.norm.weight": "model-00004-of-00004.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
+}