Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- KoboldAI/LLaMA2-13B-Tiefighter
+- ddh0/OrcaMaid-v3-13b-32k
+base_model:
+- KoboldAI/LLaMA2-13B-Tiefighter
+- ddh0/OrcaMaid-v3-13b-32k
+---
+
+# D_AU-Tiefighter-OrcaMaid-V3-13B-32k-slerp
+
+D_AU-Tiefighter-OrcaMaid-V3-13B-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)
+* [ddh0/OrcaMaid-v3-13b-32k](https://huggingface.co/ddh0/OrcaMaid-v3-13b-32k)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: KoboldAI/LLaMA2-13B-Tiefighter
+        layer_range: [0, 40]
+      - model: ddh0/OrcaMaid-v3-13b-32k
+        layer_range: [0, 40]
+merge_method: slerp
+base_model: ddh0/OrcaMaid-v3-13b-32k
+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 = "DavidAU/D_AU-Tiefighter-OrcaMaid-V3-13B-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"])
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "ddh0/OrcaMaid-v3-13b-32k",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "ddh0/OrcaMaid-v3-13b-32k--configuration_llama.LlamaConfig",
+    "AutoModelForCausalLM": "ddh0/OrcaMaid-v3-13b-32k--modeling_llama_yarn.LlamaForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "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,
+    "finetuned": false,
+    "original_max_position_embeddings": 4096,
+    "type": "yarn"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: KoboldAI/LLaMA2-13B-Tiefighter
+        layer_range: [0, 40]
+      - model: ddh0/OrcaMaid-v3-13b-32k
+        layer_range: [0, 40]
+merge_method: slerp
+base_model: ddh0/OrcaMaid-v3-13b-32k
+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

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:702ec63635ad3fb161916bf0213e54e43d94a076930d275a40038dc6abcadeef
+size 1924190576

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:379cb5272bd8dee67744f77f521b9fd23396cb5225ecc060121902818f1c714a
+size 1903230048

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:340b8b5a02f4652a663ff8d5925f5bde5693c09b0dbaf7c73db5dc99351650de
+size 1903230048

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d542fcb07f129f8714d2cf84b9592a88f0eba4c5a86757930f094bc3b2f784c0
+size 1903230048

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7040cde272c17df4e76a024cf424523f106f4ecf36095a8d45eab3903e9e15f
+size 1903230040

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb96d398897b0a924a50817905f91cce0bf088aa95a5f7a0d8854c1e0cac5301
+size 1903230048

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e4c87652d50c151fb68379a773af84d550265e144cdcfe02d4aec5808a27e8
+size 1903230048

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abc45357b1487e24c4ecccd8fdb0a1342bdd7aefd002629a824b869694e681dd
+size 1903230048

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e31381c940de6bb549e56db84c5a7cf07146585d1a9d208bedc3905b1427bed5
+size 1903230040

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78baa7524617fd6ddc3e9d0894b1dacd251c34f242eb9458d947c60b69eaf9b4
+size 1903230048

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d6bc8328c2e896cdc75e670a053ae211fcb4e3b21fa941951bd6f17e9db746
+size 1903230048

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f094cc8e861c8e5fb3a3bf2d67b80e82d1a37c0f051372e00c0f03066642ba7
+size 1903230032

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ba7a8186d001f4101e60bd3ee7cb253e4aef04c23895ac76b596c92c994819
+size 1903230016

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:618ee9ce896b4c6272f76593b1bc0aadfb783596cb6152c451cc61adab99746e
+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 +1,30 @@
+{
+  "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": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "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 +1,51 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "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": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}