Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,40 @@
+---
+library_name: transformers
+license: cc-by-nc-4.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+base_model:
+- Delta-Vector/Francois-PE-V2-Huali-12B
+- Sao10K/MN-12B-Lyra-v4
+- Sicarius-Prototyping/Impish_Longtail_12B
+- GreenerPastures/Golden-Curry-12B
+- DavidAU/MN-CaptainErisNebula-12B-Chimera-v1.1-heretic-uncensored-abliterated
+---
+
+# Kitsch_Early-TEST
+
+Kitsch_Early-TEST is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [Delta-Vector/Francois-PE-V2-Huali-12B](https://huggingface.co/Delta-Vector/Francois-PE-V2-Huali-12B)
+* [Sao10K/MN-12B-Lyra-v4](https://huggingface.co/Sao10K/MN-12B-Lyra-v4)
+* [Sicarius-Prototyping/Impish_Longtail_12B](https://huggingface.co/Sicarius-Prototyping/Impish_Longtail_12B)
+* [GreenerPastures/Golden-Curry-12B](https://huggingface.co/GreenerPastures/Golden-Curry-12B)
+* [DavidAU/MN-CaptainErisNebula-12B-Chimera-v1.1-heretic-uncensored-abliterated](https://huggingface.co/DavidAU/MN-CaptainErisNebula-12B-Chimera-v1.1-heretic-uncensored-abliterated)
+
+## 🧩 Configuration
+
+```yamly
+models:
+  - model: Delta-Vector/Francois-PE-V2-Huali-12B
+  - model: Sao10K/MN-12B-Lyra-v4
+  - model: Sicarius-Prototyping/Impish_Longtail_12B
+  - model: GreenerPastures/Golden-Curry-12B
+  - model: DavidAU/MN-CaptainErisNebula-12B-Chimera-v1.1-heretic-uncensored-abliterated
+merge_method: model_stock
+base_model: Delta-Vector/Francois-PE-V2-Huali-12B
+tokenizer:
+  source: Delta-Vector/Francois-PE-V2-Huali-12B
+normalize: false
+dtype: bfloat16
+```

chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": false,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,13 @@
+
+models:
+  - model: Delta-Vector/Francois-PE-V2-Huali-12B
+  - model: Sao10K/MN-12B-Lyra-v4
+  - model: Sicarius-Prototyping/Impish_Longtail_12B
+  - model: GreenerPastures/Golden-Curry-12B
+  - model: DavidAU/MN-CaptainErisNebula-12B-Chimera-v1.1-heretic-uncensored-abliterated
+merge_method: model_stock
+base_model: Delta-Vector/Francois-PE-V2-Huali-12B
+tokenizer:
+  source: Delta-Vector/Francois-PE-V2-Huali-12B
+normalize: false
+dtype: bfloat16

model-00001-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80a7bfeb32717f181ef7c61d0ff0df88650eb8b83c534872de091c7b912c8309
+size 1342177408

model-00002-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68090848437c679743b2a67a40318a1f99edaccf19975a1dc40f890fbf849b04
+size 1342177424

model-00003-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb9b3b4f3fc4ff4f729a329659af51ced2cf435e2756a8e9cc4d60419d3dbd6
+size 996189888

model-00004-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c34f5efc4c542cfee3f3b68eb3f7ef9b486f664721cf802b7a0f91eb398185f8
+size 933265104

model-00005-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ba616ca663d94482a9c7de60396c85d71e678050b6ee6a8f13c0c506c44134e
+size 943761344

model-00006-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92c051df88db27152c13babdfce6ca2fe1e727832d6de195010dba1914615ec
+size 943761344

model-00007-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35ed54dff53b68f04285beb824144ad1023126df452aa1b7e34fc379c00f3652
+size 996179560

model-00008-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b1a9fc98e3797ec734a627def5bda1039cf565828d7c417bb9fb9599efde439
+size 933265104

model-00009-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24282f84580c4c1c4aae9dca6a3fdbee960cf5f928cb9ebd7ed4408b89c38c9f
+size 943761344

model-00010-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b8e1309c82d28054aa80674d39a4ad054d5f759f0f73edb3a1c6cda9ad5c511
+size 943761344

model-00011-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:733ff1e170bb105f061d75a4a42dee37d6dab48c7d43b82f5a876397197284b2
+size 996179560

model-00012-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:335b2453cec6dbe5cd57a5758aef8b9c38f961d43576fee6bbede2ab0db6f6ac
+size 933265104

model-00013-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:033962fa89106902e5a8d2e347d16efb49f68e0efedb11adf1ddde5922f9a326
+size 943761344

model-00014-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd0ec5c01860f61c914f95cd9c8c263f98ec51b16a3bb7e3d17fe02e962c4602
+size 943761344

model-00015-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7e6056e4a61f992f767092e310ed993337d78b27ba7d524810b9948cf95bea
+size 996179560

model-00016-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26c333d95933187f9eae6cdcf52601eaf423eb2310fc20e739c5505279d8de02
+size 933265096

model-00017-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e26e2acdc75512458674f11d858ccf238b685be80f8b29fb8158470071969450
+size 943761344

model-00018-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eeb3ba0daa3335bf5d21b2bd4571ba3e121c9e913430073a17860d0b1c37709
+size 943761344

model-00019-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f9d05067ae35bb216be0c8bae12728afdc10a77aaec616a2faf12b30735cd01
+size 996179560

model-00020-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f7ced1b0247a00f108abd5bb93c5db397b282ff067d6fa7f1841c6c7657aac5
+size 933265104

model-00021-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe6ddc171a804249b089329c2547de1a378b20e6bd6f097f6f54f078a6fec830
+size 943761344

model-00022-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d594ba746bfb516ea1ee14473feb41c23412ddc28316509ee29f3c4037780315
+size 943761336

model-00023-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2398194826d46479168a7e3e4fdd7d8f7b9a4c0725fdef909a708a4bbd0777f5
+size 996179552

model-00024-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ec4354c581a859f574afc96422aef896659073d44c33a8c16de0468cae34d4
+size 933265088

model-00025-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae72fb80013d4146f589d2bba2829868cf1069702fe5349b96fb87a727d24a0c
+size 796960560

model.safetensors.index.json

@@ -0,0 +1,371 @@
+{
+  "metadata": {
+    "total_size": 24495564800,
+    "mergekit_version": "0.1.3"
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00025.safetensors",
+    "model.embed_tokens.weight": "model-00002-of-00025.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00003-of-00025.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00025.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00003-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-00004-of-00025.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00025.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-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-00005-of-00025.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00025.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-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-00006-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-00007-of-00025.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00025.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00007-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-00008-of-00025.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00008-of-00025.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00008-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-00009-of-00025.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00009-of-00025.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00009-of-00025.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00025.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00010-of-00025.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00025.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00012-of-00025.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00025.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00013-of-00025.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00025.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00025.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00014-of-00025.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00015-of-00025.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00016-of-00025.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00016-of-00025.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00017-of-00025.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00017-of-00025.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00018-of-00025.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00018-of-00025.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00025.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00020-of-00025.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00020-of-00025.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00021-of-00025.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00021-of-00025.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00022-of-00025.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00022-of-00025.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00023-of-00025.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00023-of-00025.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00023-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-00024-of-00025.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00024-of-00025.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00024-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-00025-of-00025.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00025-of-00025.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00025-of-00025.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00025-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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee57bd3271d8c200a06df40f9d7c94f8bb8f085b5cfb2d40907a794560df2ec3
+size 17078342