Upload folder using huggingface_hub

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- KoboldAI/LLaMA2-13B-Tiefighter
+- DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp
+base_model:
+- KoboldAI/LLaMA2-13B-Tiefighter
+- DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp
+---
+
+# D_AU-Tiefighter-Plus-Giraffe-13B-32k-slerp
+
+D_AU-Tiefighter-Plus-Giraffe-13B-32k-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [KoboldAI/LLaMA2-13B-Tiefighter](https://huggingface.co/KoboldAI/LLaMA2-13B-Tiefighter)
+* [DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp](https://huggingface.co/DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp)
+
+## 🧩 Configuration
+
+```yaml
+models:
+  - model: KoboldAI/LLaMA2-13B-Tiefighter
+    parameters:
+      weight: 0.8
+  - model: DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp
+    parameters:
+      weight: 0.2
+merge_method: linear
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "DavidAU/D_AU-Tiefighter-Plus-Giraffe-13B-32k-slerp"
+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"])
+```

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_length": 32768,
+  "max_position_embeddings": 32768,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "type": "linear"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+
+models:
+  - model: KoboldAI/LLaMA2-13B-Tiefighter
+    parameters:
+      weight: 0.8
+  - model: DavidAU/D_AU-Tiefighter-Giraffe-13B-32k-slerp
+    parameters:
+      weight: 0.2
+merge_method: linear
+dtype: bfloat16

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b76e65f1d67da03ab6b3e621d3ac0fd94b6d5de7c26ba10e54cee7f59b41d02
+size 1924190576

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efd11163625a600d96b217fcd2885a52a16a67708c471aed603b16ffce3aac27
+size 1903230048

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3900f8888ed946ffa6f0cfac40e7b1c760001c6878310334785870b95fd72ca7
+size 1903230048

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c451358bde9b6e70079332c8ba2757f48a06174c5863b0cfbdb937691105a458
+size 1903230048

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16fcfb40e5c065951d6d54bacdd9f278b02d2447f68c3ce98b0760dee4b9ef10
+size 1903230040

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3e67680cb8e829254b30f3c13480524b625b9f9c1ed7157d2cf88704cfff11b
+size 1903230048

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91ca43f8632d36fcacfa573e4a58a4dc33f7ca982e948b32ca2a6441d651b21e
+size 1903230048

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a620d7a492e41deba9e47b9cdbe1b863c45914cd0fe64cf7151cf87b918ad500
+size 1903230048

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca1b832e1e0c3f73f878e9fa0db38bb9005386338fd5b92079319305a39c24a8
+size 1903230040

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9311df1beaaa8c73db383afa29db883d838b3a20adab5ee08440f60e7530287
+size 1903230048

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4641902c141cd714d7feba27fa1e3fb46cec5dc67b59866e405236f41901a2cc
+size 1903230048

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:453b2094bfc793971afedc1ea0dac33feecd8875425abcaf39a135e0579ac49a
+size 1903230032

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c22deaa65f7af41ac04287745179a96559d62d83c55a7189491b589a481fe8c
+size 1903230016

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e0af4e710b6dafd6c0c1ffe4fc071adb6efb6ea3007383be6e304a171528359
+size 1268820000

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 26031728640}, "weight_map": {"lm_head.weight": "model-00001-of-00014.safetensors", "model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.norm.weight": "model-00014-of-00014.safetensors"}}

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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}