Upload folder using huggingface_hub

README.md

@@ -0,0 +1,63 @@
+---
+base_model:
+- Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO
+- cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated
+tags:
+- merge
+- mergekit
+- lazymergekit
+- Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO
+- cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated
+---
+
+# MistralPhi3-14B-slerp
+
+MistralPhi3-14B-slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO](https://huggingface.co/Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO)
+* [cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated](https://huggingface.co/cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO
+        layer_range: [0, 32]
+      - model: cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO
+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 = "allknowingroger/MistralPhi3-14B-slerp"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 4096,
+  "model_type": "mistral",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 10,
+  "pad_token_id": 32009,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 2048,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 32064
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO
+        layer_range: [0, 32]
+      - model: cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: Danielbrdz/Barcenas-14b-Phi-3-medium-ORPO
+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-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:954ffa015458943c465487dfda2f1c3d8606a011fdae87d7259d1165fbfb78a4
+size 840182216

model-00002-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa1cdfd6b0d457cd9d1631041c5ab35e1e82926eb9d0ece8be350d28cfe35b2
+size 865096856

model-00003-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a5e8ac9b71e617877970e36996c3e9d86321fc686130bc751e5ab8b33bd43b6
+size 996190024

model-00004-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e62dee6e8b707f123c087ad3495c32eec4e71e6c75adc8bbc148bdef82d018d
+size 865096864

model-00005-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b46e391a091b32312bfc976a296614d5b15c807ba5fc7fff16ac29780a1536a
+size 865096864

model-00006-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:619a409f7c32faa9875fbb27dc77685005c8d84ca1573aa35bfbd9e5ef449702
+size 996190032

model-00007-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9aef937c2de636c40a84a2bf0d67e27fef9bcd77105822453bc3dad817c7ea4
+size 865096864

model-00008-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e6826d07fffdf8fcb487a85e868bfc6371b314946308b422e6bf7d2c7646ed
+size 865096864

model-00009-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1638584c4cff4e7747c072ac7d04d35e365637fe31569010299ac7b6a33f0045
+size 996190032

model-00010-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c472c710c2f915cdd2477e37c9d0c724df981308b29e58f811162501c12f42b3
+size 865096864

model-00011-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a305b6dbf49822c25524a0e5c8846a3cf91f132247ab2e37f5358c6f89f14d19
+size 865096856

model-00012-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b386db3402b668c179a1378982f7595facfc7dadd309a0c769f953da24556de0
+size 996190032

model-00013-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e3ff9f3206105d8e103faa33c6e8750ac50c9eedaead7578b4dfdc935eedf4
+size 865096864

model-00014-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed54a829c0a0c3ae3555427d22f47a43618b2397f6f05e7d2e7fd68b3cd7883c
+size 865096864

model-00015-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3810e40d495989031febf17f27451faab35ac2ed757d3ea06f058ebee1fa4fd
+size 996190032

model-00016-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4344dc9837dd53244c468b5e8b1d50f4d4ef9013cf5d3fa8a90c7111c66b019b
+size 865096864

model-00017-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7554405b28b0b6308127a0395cc67719b7613321caf7afc263fbfae3da045269
+size 865096864

model-00018-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e149d837f7bb8db0e88ade0b8318718540738ddd21f060d25d5413c01e75ed0
+size 996190032

model-00019-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea99a6125b26af555c0d487cabc4bc271c6abb6deb87c90304c10277999ba62
+size 865096856

model-00020-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa7a8e4e0e30a1a1ffd1aa2647613acf055230017b338a09ce0cd8e0b1e9edce
+size 865096864

model-00021-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38a17a4dd1248890d180aa9db24e6b8f97e715166ac897ce5674bdbacf93e362
+size 996190024

model-00022-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:126166cc358ce6d2f1d68087d5a75f7f54f93425ba458812583fc7697a80972a
+size 865096856

model-00023-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7371f6640183e9a2925216b5c38e8ab85efcd4dba8786ac41fb9200de84d589
+size 865096856

model-00024-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04cf493506362c588b356afd40fa79b98af2fe75f91148a3b2a1224e61096523
+size 996190016

model-00025-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac71098efa1f2e2eed53d8aefb671e618742925e34ec15c87bc3e8716570ee4
+size 681595920

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 22467717120}, "weight_map": {"lm_head.weight": "model-00001-of-00025.safetensors", "model.embed_tokens.weight": "model-00001-of-00025.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00025.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00025.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00025.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00025.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00025.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00025.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00025.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00025.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00025.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00025.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00025.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00025.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00025.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00025.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00025.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00025.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00025.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00025.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00025.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00025.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00025.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00025.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00025.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00025.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00025.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00009-of-00025.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00025.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00025.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00025.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.input_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00010-of-00025.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00025.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00010-of-00025.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00025.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00025.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00025.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00025.safetensors", "model.layers.2.input_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00010-of-00025.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00011-of-00025.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00011-of-00025.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00011-of-00025.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00011-of-00025.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00011-of-00025.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00011-of-00025.safetensors", "model.layers.20.input_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00011-of-00025.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00011-of-00025.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00012-of-00025.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00025.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00025.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.21.input_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00012-of-00025.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00012-of-00025.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00012-of-00025.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00012-of-00025.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00012-of-00025.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.22.input_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00013-of-00025.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00013-of-00025.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00013-of-00025.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00025.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00025.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00025.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00025.safetensors", "model.layers.23.input_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00013-of-00025.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00025.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00014-of-00025.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00025.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00025.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00025.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00025.safetensors", "model.layers.24.input_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00014-of-00025.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00014-of-00025.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00015-of-00025.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00025.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00025.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00025.safetensors", "model.layers.25.input_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00015-of-00025.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00015-of-00025.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00015-of-00025.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00025.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00025.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00025.safetensors", "model.layers.26.input_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00016-of-00025.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00016-of-00025.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00016-of-00025.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00025.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00025.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00025.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00025.safetensors", "model.layers.27.input_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00016-of-00025.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00017-of-00025.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00017-of-00025.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00017-of-00025.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00017-of-00025.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00017-of-00025.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00017-of-00025.safetensors", "model.layers.28.input_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00017-of-00025.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00017-of-00025.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00018-of-00025.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.29.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00018-of-00025.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00018-of-00025.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00018-of-00025.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.3.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00019-of-00025.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00019-of-00025.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00019-of-00025.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00019-of-00025.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00019-of-00025.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00019-of-00025.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00019-of-00025.safetensors", "model.layers.30.input_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00019-of-00025.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00020-of-00025.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00020-of-00025.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00020-of-00025.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00020-of-00025.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00020-of-00025.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00020-of-00025.safetensors", "model.layers.31.input_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00020-of-00025.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00020-of-00025.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00021-of-00025.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.4.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00021-of-00025.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00021-of-00025.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00021-of-00025.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.5.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00022-of-00025.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00022-of-00025.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00022-of-00025.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00022-of-00025.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00022-of-00025.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00022-of-00025.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00022-of-00025.safetensors", "model.layers.6.input_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00022-of-00025.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00023-of-00025.safetensors", "model.layers.7.input_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00023-of-00025.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00023-of-00025.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.9.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00025-of-00025.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00025-of-00025.safetensors", "model.norm.weight": "model-00025-of-00025.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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|placeholder6|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<|placeholder6|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}