Upload folder using huggingface_hub

README.md

@@ -0,0 +1,43 @@
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- PygmalionAI/pygmalion-2-13b
+- elinas/chronos-13b-v2
+base_model:
+- PygmalionAI/pygmalion-2-13b
+- elinas/chronos-13b-v2
+---
+
+# LogicLumina-L3-13B
+
+LogicLumina-L3-13B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [PygmalionAI/pygmalion-2-13b](https://huggingface.co/PygmalionAI/pygmalion-2-13b)
+* [elinas/chronos-13b-v2](https://huggingface.co/elinas/chronos-13b-v2)
+
+## 🧩 Configuration
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Abdulhanan2006/LogicLumina-L3-13B"
+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 +1,29 @@
+{
+  "_name_or_path": "PygmalionAI/pygmalion-2-13b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "badwordsids": "[[29961], [14352], [24630], [29962], [11759], [15974], [5519], [25473], [18899], [25901], [7110], [9341], [13531], [518], [9310], [2636], [3366], [21069], [11970], [23098], [16733], [21298], [18173], [10846], [3816], [28513], [15625], [23192], [28166], [10062], [1385], [11724], [3108], [15555], [10834], [10370], [14330], [1822], [12436], [5262], [17094], [10725], [17077], [11424], [4197], [24406], [13359], [17531], [24566], [23076], [4514], [13192], [19942], [16261], [7072], [6024], [1402], [1839], [2033], [13970], [850], [5913], [28895], [5387], [8308], [24927], [5691], [12940], [19997], [18959], [11287], [16862], [4638], [22322], [29861], [21251], [14704], [17548], [12452], [17288], [23160], [24960], [8219], [18024], [5539], [7464], [27865], [29588], [20068], [19660], [27706], [22896], [24264], [12258], [2314], [4400], [5586], [12622], [6796], [7226], [21939], [18456], [14178], [21540], [21945], [14664], [16215], [10338], [17361], [7503], [13769], [26073], [9601], [26909], [7961], [8999], [20840], [16272], [21545], [3199], [10514], [5159], [22689], [6525], [20526], [27077], [18017]]",
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: PygmalionAI/pygmalion-2-13b
+        layer_range: [0, 40]
+      - model: elinas/chronos-13b-v2
+        layer_range: [0, 40]
+merge_method: slerp
+base_model: PygmalionAI/pygmalion-2-13b
+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-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6febc1a9366ea28fd09912bfaffb1d37d5ba9d4b979a84dd5da22360cd276c7b
+size 938486328

model-00002-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60e4198b2b4f5c225f46ed9b9c88e12cccd95fd896d5f95a028ae009b1605d7b
+size 985704256

model-00003-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ae9634edc0c5f35ddae770ed77ceb888fddca0bf5ac514adea3891ebb6562a
+size 917525776

model-00004-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e9062e8f651ee9d30c9232cb6929171151ff211690bd05098252ac4b5a041c0
+size 985704272

model-00005-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eeb5d3b5b2cc324061e56375c16121ee6b55bef74c8d03de621825372e301b5
+size 917525776

model-00006-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cf8674caa3069d45e8d5c4dd429c6ca036c47a46ca815c0fea6f2733662e0f8
+size 985704272

model-00007-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c91e9249e8d46b7737233b2c53133ec27e4c8996f883e54417ea9e003295688
+size 917525776

model-00008-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:041e8b201d6674c551ca054b250ae74ae00b824cbf33c74250eb5ed498209aa1
+size 985704272

model-00009-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f7cd648f011e4c04c21fa4b66d8aa74a8a993f4b0266621792c2d727f09f50
+size 917525776

model-00010-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68866da47b42a23c25b2f4924166336ef6ffa9f823cc5e9bfe648947cfa865d8
+size 985704264

model-00011-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:104870edcdce17d0aafabc4b18c0bcb1bb3e5823f8b16b9a2bedf91f1cb87a6b
+size 917525776

model-00012-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:428603036c8ad4ef32d9ba390b474f917c5b3411336fc2b4b1b4c1b9845c6d5d
+size 985704272

model-00013-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6136f58ca24c9a5e15826a910876c2173e4cbe3a2f39d2e462eeb50dbcee55f9
+size 917525776

model-00014-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13f74c721c449bf4e5e2437f14c3eefe9e77521c9ed93f277cfee1158ab47928
+size 985704272

model-00015-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af24b24a69c3d6bfe7299e537634ae99afd7c301d1b2dcb86fe80f1953852f48
+size 917525776

model-00016-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e60eb2695fde600aa4a0a078586cfd4336f23407a7bb4c52685476d4fb4aeda
+size 985704272

model-00017-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9b42122eefae1b031ed39f17023bc4dacba2ec7a890a8c39a4d68fde2ebd4b
+size 917525768

model-00018-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a29b21d8580e834ce9dc2f61cf0b85d30e342c4b277dc40675ba6419079697b1
+size 985704272

model-00019-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2366bba09dbfbe1e2e444e5b73be8f05aead2178f8f9280fad26e2e22761b0b3
+size 917525776

model-00020-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9e7998e353d8f7224f4e75a6234a223f7039a96133e96dce701ab75f35dc8f
+size 985704272

model-00021-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67da824b7d56aef3cdb81e229cf9d83effd01aff7de8af65e5f0d19f5eca958b
+size 917525776

model-00022-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19378113aaf296369e959bde234bfe50ed80990e0bbf68be39e829bd765ef185
+size 985704272

model-00023-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c365459e0f7f4dec389c97b4c0fbe789428eceee97c8afcac5bcee534f92bf05
+size 917525776

model-00024-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37d9541d7f47fba0361958d7b8fe17978b35fcf9574e25912cdba723b0920c68
+size 985704264

model-00025-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0c2d33748b97f677f61940814917e2a49431bd83cb520450096af0ec052d68c
+size 917525768

model-00026-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb37bbd9212eeb5fd92b4c3fcb36b07afaf6b6bb723d0100e6c278c7ef462da
+size 985704256

model-00027-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f5e12b533dfd44a83a5af025a57796e4d57bd6133c0d6d24547f5e1ab6f192
+size 917525768

model-00028-of-00028.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e502e273a18b3f0d8491c33b27922f0719943662c8fdf3dfd3fe3aeace01a159
+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 +1,30 @@
+{
+  "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
+  },
+  "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 +1,44 @@
+{
+  "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": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}