Upload folder using huggingface_hub

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- lmsys/vicuna-13b-v1.5
+- OpenAssistant/llama2-13b-orca-8k-3319
+base_model:
+- lmsys/vicuna-13b-v1.5
+- OpenAssistant/llama2-13b-orca-8k-3319
+---
+
+# vicuna-orac
+
+vicuna-orac is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [lmsys/vicuna-13b-v1.5](https://huggingface.co/lmsys/vicuna-13b-v1.5)
+* [OpenAssistant/llama2-13b-orca-8k-3319](https://huggingface.co/OpenAssistant/llama2-13b-orca-8k-3319)
+
+## 🧩 Configuration
+
+```yaml
+models:
+  - model: lmsys/vicuna-13b-v1.5
+    parameters:
+      weight: 0.5
+  - model: OpenAssistant/llama2-13b-orca-8k-3319
+    parameters:
+      weight: 0.5
+merge_method: linear
+dtype: bfloat16
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Cartinoe5930/vicuna-orac"
+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 +1,8 @@
+{
+  "<pad>": 32000,
+  "<|assistant|>": 32001,
+  "<|prefix_begin|>": 32004,
+  "<|prefix_end|>": 32002,
+  "<|prompter|>": 32005,
+  "<|system|>": 32003
+}

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "OpenAssistant/llama2-13b-orca-8k-3319",
+  "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": 8192,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "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": 2.0,
+    "type": "linear"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.1",
+  "use_cache": true,
+  "vocab_size": 32016
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+
+models:
+  - model: lmsys/vicuna-13b-v1.5
+    parameters:
+      weight: 0.5
+  - model: OpenAssistant/llama2-13b-orca-8k-3319
+    parameters:
+      weight: 0.5
+merge_method: linear
+dtype: bfloat16

model-00001-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed43984cbb4e33724d87cef9dde299f5329821c72a1ebd3df055e7859d94e855
+size 938486328

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c02e045dcf7df4317e79e008f9d752c625978eb7eb6376f201919dd93b3a220
+size 985704256

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed754486a5ab7852dcfca773d71d5409d31cf2fc28ee1b69c6202316ef5baa15
+size 917525776

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d68a1688a4ca0a3184d93ff3f80e28c7f1816584539f6141fd753934a1ab911
+size 985704272

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ee38af3e608217e920aed47be300a9526c7df3798a6426567ce4bba0fc09936
+size 917525776

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc38ac265aff41f3fb4b6d368195b8873bcf4e06ad0c7c0fd5b3d54a85658e56
+size 985704272

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d293eb9fe2b4b309e53f3662d6840cd89204e9ede986e52a06a4734a98af1076
+size 917525776

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cda4cf2c6fccb4229b995fd488a6c667dafe90a6eb1da666a8c663cd12b1fc0
+size 985704272

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7985e486a36c296c6a8cd7b5d8cc159added07e51d41d094bea7c71831e9b2d9
+size 917525776

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9321e5d9b567620607bb7c2d31cc1b7215c26ac9c40ffe7f6576862b75e763
+size 985704264

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7832cf8c3fa13bdfa495f49154446eb9acb8759ae3633fdb232e316a4db186db
+size 917525776

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8454aea183774b09a71a85288f6282bfa20d8983e08143bcafac151b82e7893a
+size 985704272

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6370d7a58598a769dd522c9e3c6561e04bbf0996aeafd92daf3c74db8c806fc6
+size 917525776

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f766eea00d6bfd874ee821c6bc37b8d38b5b6da4a80abf0ccd87cbadffce57b
+size 985704272

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d112080529655bb824873fff563feb5b9b352633708b07b944e94207ce81e8ca
+size 917525776

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d583fd48b193e9249ced603c6a74c12ed1f28ebc08b20927aceb0f7f9f14070
+size 985704272

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19b3794436ad73e2bebf287cd6e99c92c1f0e7d14f60a01620eb4a9ebef40760
+size 917525768

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809d3f4783333ad6c085b269353d9d30c89356f2d2f66a041f63308d2e0d32ec
+size 985704272

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e344bec9efeaa9b0701d498d89bbebe471196df4786ffff1f8800baa17b74e9f
+size 917525776

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be0b28b7cd15c73b656a470cbd3fa6a2b1ca4374bfb55c95675844408e84956c
+size 985704272

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c54a3aa5ff83ddc463ed319372f4e39b82ea5e219089253659984f8d92d90295
+size 917525776

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ebbff4591e59d1f501e5d24ec38ec23f37f12f7033ef8954138a8a9c1024d2d
+size 985704272

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:885317d031c88403dc4f9b968705bf623e99f14a0632107823a40037a761b9cf
+size 917525776

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0b417a7a888ef239a7662bb3244194814184cca7bec8664122675bc2b1fe6e6
+size 985704264

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f89022b6503f312876b5be3c9fcb7837eb1b58ff60f79bb1925827ec57833d96
+size 917525768

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2eaf32b9cb77663103125207bb06d9a2ef8dbfa83b6356e9612a62ff2af7086
+size 985704256

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0267bb0a701705d8f05ecfa5ae0843cdd24f971b25ca50d34015cf79cfdb5098
+size 917525768

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3790abc4b528c8cb1f550312103e767e617812c0a5a6078bd41d1a370208a69
+size 351294256

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-00028.safetensors", "model.embed_tokens.weight": "model-00001-of-00028.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00028.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00028.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00028.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00028.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00028.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00028.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00028.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00028.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00028.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00028.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00028.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00028.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00028.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00028.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00028.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00028.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00028.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00028.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00028.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00028.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00028.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00028.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00028.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00028.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00028.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00028.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00028.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00028.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00028.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00028.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00028.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00028.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00028.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00028.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00009-of-00028.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00009-of-00028.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00010-of-00028.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00028.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.input_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00028.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00028.safetensors", "model.layers.21.input_layernorm.weight": "model-00010-of-00028.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00028.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00028.safetensors", "model.layers.22.input_layernorm.weight": "model-00011-of-00028.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00011-of-00028.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00028.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00012-of-00028.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00028.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00028.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.input_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00028.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00028.safetensors", "model.layers.24.input_layernorm.weight": "model-00012-of-00028.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00028.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00028.safetensors", "model.layers.25.input_layernorm.weight": "model-00013-of-00028.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00013-of-00028.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00028.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00014-of-00028.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00028.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00028.safetensors", "model.layers.27.input_layernorm.weight": "model-00014-of-00028.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00015-of-00028.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00015-of-00028.safetensors", "model.layers.28.input_layernorm.weight": "model-00015-of-00028.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00015-of-00028.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00028.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00016-of-00028.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00016-of-00028.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00016-of-00028.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.input_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00016-of-00028.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00028.safetensors", "model.layers.3.input_layernorm.weight": "model-00016-of-00028.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00017-of-00028.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00017-of-00028.safetensors", "model.layers.30.input_layernorm.weight": "model-00017-of-00028.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00017-of-00028.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00017-of-00028.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00018-of-00028.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00028.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.input_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00028.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00018-of-00028.safetensors", "model.layers.32.input_layernorm.weight": "model-00018-of-00028.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00019-of-00028.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00019-of-00028.safetensors", "model.layers.33.input_layernorm.weight": "model-00019-of-00028.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00019-of-00028.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00019-of-00028.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00020-of-00028.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00020-of-00028.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00020-of-00028.safetensors", "model.layers.35.input_layernorm.weight": "model-00020-of-00028.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00021-of-00028.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00021-of-00028.safetensors", "model.layers.36.input_layernorm.weight": "model-00021-of-00028.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00021-of-00028.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00021-of-00028.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00022-of-00028.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00022-of-00028.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00022-of-00028.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00022-of-00028.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.input_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00022-of-00028.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00022-of-00028.safetensors", "model.layers.38.input_layernorm.weight": "model-00022-of-00028.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00023-of-00028.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00023-of-00028.safetensors", "model.layers.39.input_layernorm.weight": "model-00023-of-00028.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00023-of-00028.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00023-of-00028.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00024-of-00028.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.input_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00024-of-00028.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00024-of-00028.safetensors", "model.layers.5.input_layernorm.weight": "model-00024-of-00028.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00025-of-00028.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.input_layernorm.weight": "model-00025-of-00028.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00025-of-00028.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00026-of-00028.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00026-of-00028.safetensors", "model.layers.8.input_layernorm.weight": "model-00026-of-00028.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00027-of-00028.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00027-of-00028.safetensors", "model.layers.9.input_layernorm.weight": "model-00027-of-00028.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00027-of-00028.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00027-of-00028.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00028-of-00028.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00028-of-00028.safetensors", "model.norm.weight": "model-00028-of-00028.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,44 @@
+{
+  "additional_special_tokens": [
+    "<|assistant|>",
+    "<|prefix_end|>",
+    "<|system|>",
+    "<|prefix_begin|>",
+    "<|prompter|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<s>",
+    "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 +1,96 @@
+{
+  "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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|prefix_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|prefix_begin|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|prompter|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|assistant|>",
+    "<|prefix_end|>",
+    "<|system|>",
+    "<|prefix_begin|>",
+    "<|prompter|>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sep_token": "<s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}