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 +1,58 @@
+---
+base_model:
+- MaziyarPanahi/calme-2.8-qwen2-7b
+- Weyaxi/Einstein-v7-Qwen2-7B
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [MaziyarPanahi/calme-2.8-qwen2-7b](https://huggingface.co/MaziyarPanahi/calme-2.8-qwen2-7b) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [Weyaxi/Einstein-v7-Qwen2-7B](https://huggingface.co/Weyaxi/Einstein-v7-Qwen2-7B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: MaziyarPanahi/calme-2.8-qwen2-7b
+    parameters:
+      density: 1
+      weight: 1 
+      
+  - model: Weyaxi/Einstein-v7-Qwen2-7B
+    parameters:
+      density: 1
+      weight: 1 
+      
+  - model: MaziyarPanahi/calme-2.8-qwen2-7b
+    parameters:
+      density: 1
+      weight: 1
+      
+  - model: Weyaxi/Einstein-v7-Qwen2-7B
+    parameters:
+      density: 1
+      weight: 1 
+      
+merge_method: ties
+base_model: MaziyarPanahi/calme-2.8-qwen2-7b
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: bfloat16
+
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "MaziyarPanahi/calme-2.8-qwen2-7b",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

mergekit_config.yml

@@ -0,0 +1,27 @@
+models:
+  - model: MaziyarPanahi/calme-2.8-qwen2-7b
+    parameters:
+      density: 1
+      weight: 1 
+      
+  - model: Weyaxi/Einstein-v7-Qwen2-7B
+    parameters:
+      density: 1
+      weight: 1 
+      
+  - model: MaziyarPanahi/calme-2.8-qwen2-7b
+    parameters:
+      density: 1
+      weight: 1
+      
+  - model: Weyaxi/Einstein-v7-Qwen2-7B
+    parameters:
+      density: 1
+      weight: 1 
+      
+merge_method: ties
+base_model: MaziyarPanahi/calme-2.8-qwen2-7b
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: bfloat16

model-00001-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a031a097d04524b3cf99cafa00d16d28e022483c253c478878dd3e79ef3290d
+size 1089994880

model-00002-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aab4727ddccbd37dca5d294764c0ed97979b9054437ce348e69c77fff9425ac9
+size 1089994896

model-00003-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c5f150db60067677d0d832ceaabc44b87b7283474406bc6555b6dbd9aea5b4
+size 466124232

model-00004-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5695b7b82efd6412e555ad1ef97a2987d614d2e963e08c9c857410051d1e2757
+size 466116968

model-00005-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:463b2987d17119ffd616d5be7dd9321f884825590afb731fb870841c6a161080
+size 466116976

model-00006-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6798bd0c894a068eb43205a1503acfc530ea97ea0dfe19d1299954cb0a3f652c
+size 466116976

model-00007-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67707c0033d2855a4453c9511fad8de6cb6809236661749c67e1ef871d8ab1ed
+size 466116976

model-00008-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9886c0afce17f757cb6013c60f084895ba186064783ac81696cd73eebe2d784
+size 466116976

model-00009-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c651ecddf512c83d4a167385d756c193ee50e4d70bba4c002e9f998e4ff16d11
+size 466116976

model-00010-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b29506abc39dccbb719bb33176f85efbcd6ae674443d362771a23a95cb06a931
+size 466116976

model-00011-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c9fb0a124a26e27d67d5e973968c604dba0db9ae147acf83182efffb5ce3796
+size 466116976

model-00012-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86f96e4b1e97f406437c76ce6ddad20e3723acb26e3f71300fa61b096e63d968
+size 466116976

model-00013-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f1b321c2edd2c75375affc6e803ae54901c98bbc606e0b753ca83381a44cdfe
+size 466116976

model-00014-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b98ed7e90e9082166c276780a955dd5deb75baae6d6c6c0e652b95313830da48
+size 466116976

model-00015-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aebbc389c3ca471b07f4bf7b3da9eb44828beea1cc5b753821d431833edbfc5
+size 466116968

model-00016-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:479d5c80e1a1fcd21d8471c35a848f5ec869c47541da14db26692ebdf0777d03
+size 466116976

model-00017-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfaea5e830ba8374235002fb59ecadedc24df55de3f0cb2b933d864892ba0428
+size 466116976

model-00018-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5a9e1c7424d5e9846e2121cdd5df98beb35587694c2efacecbc804143d34b08
+size 466116976

model-00019-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a980e434471c80175e0437d8d202b971816deb3cc85c7b5bac97ed0d85f4f97a
+size 466116976

model-00020-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa970b6999e1aa465d0d08591e762933365b7af24b111f55cd14466a9b0ddfb
+size 466116976

model-00021-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9789ef54b5e863a97e9c921fcd42cc24634b57cb5ea25fb4bf9306c3fe5dffc1
+size 466116976

model-00022-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86613560515a6cc5dd1f5c955b023371ca01d132ef498b14df580e0c82f2e670
+size 466116976

model-00023-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ec329a187847db907096cd7f1f82af4f0763e6ca7bac04c8eb0e29d5e4a2d2d
+size 466116976

model-00024-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f75011ddc683243e394feb3f07a38f4e1a5e2c97f86b0375c3d11736b376d035
+size 466116960

model-00025-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40b186f8899e40a834dd60befddc82c8ce8077c4106c8b994c6eef86ba759465
+size 466116960

model-00026-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05eba91acaa41162ed8db0a64e350abb61508e029e068652ed19a617d57b2a18
+size 466116960

model-00027-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5da540e22d7126d997640406b887f8a5cee757c2051c35d2af7edca458bbbf2
+size 466116960

model-00028-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9d31f9debd607b02757f095106d9cb4b0e70bf09ac25f6790d4c64deee60c07
+size 466116960

model-00029-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8872044e9a913fe884edfdbb0f8d141e79f425137836394ee0a45aaf4109499a
+size 466116960

model-00030-of-00030.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cab733e10e35cdf14278b95ff88ab4821a60fedaa4ddb7f6428c861ab428824
+size 466116944

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 15231233024}, "weight_map": {"lm_head.weight": "model-00001-of-00030.safetensors", "model.embed_tokens.weight": "model-00002-of-00030.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00030.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00030.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00030.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00030.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00030.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00030.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00030.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00030.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00030.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00030.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00030.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00030.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00030.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00004-of-00030.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00030.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00004-of-00030.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00030.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00004-of-00030.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00030.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00030.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00004-of-00030.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00030.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00004-of-00030.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00030.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00030.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00005-of-00030.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00030.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00030.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00030.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00005-of-00030.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00030.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00030.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00005-of-00030.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00030.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00005-of-00030.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00030.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00030.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00006-of-00030.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00030.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00030.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00030.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00006-of-00030.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00030.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00030.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00006-of-00030.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00030.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00006-of-00030.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00030.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00030.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00007-of-00030.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00030.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00007-of-00030.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00030.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00007-of-00030.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00030.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00030.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00007-of-00030.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00030.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00007-of-00030.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00030.safetensors", "model.layers.13.input_layernorm.weight": "model-00007-of-00030.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00008-of-00030.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00030.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00008-of-00030.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00030.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00008-of-00030.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00030.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00030.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00008-of-00030.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00030.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00008-of-00030.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00030.safetensors", "model.layers.14.input_layernorm.weight": "model-00008-of-00030.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00009-of-00030.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00030.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00009-of-00030.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00030.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00009-of-00030.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00030.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00030.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00009-of-00030.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00030.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00009-of-00030.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00030.safetensors", "model.layers.15.input_layernorm.weight": "model-00009-of-00030.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00010-of-00030.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00010-of-00030.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00010-of-00030.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00030.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00010-of-00030.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00030.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00030.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00010-of-00030.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00030.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00010-of-00030.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00010-of-00030.safetensors", "model.layers.16.input_layernorm.weight": "model-00010-of-00030.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00011-of-00030.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00011-of-00030.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00011-of-00030.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00030.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00011-of-00030.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00030.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00030.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00011-of-00030.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00030.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00011-of-00030.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00030.safetensors", "model.layers.17.input_layernorm.weight": "model-00011-of-00030.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00012-of-00030.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00012-of-00030.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00012-of-00030.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00030.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00012-of-00030.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00012-of-00030.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00030.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00012-of-00030.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00012-of-00030.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00012-of-00030.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00012-of-00030.safetensors", "model.layers.18.input_layernorm.weight": "model-00012-of-00030.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00013-of-00030.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00013-of-00030.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00013-of-00030.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00013-of-00030.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00013-of-00030.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00013-of-00030.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00013-of-00030.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00013-of-00030.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00013-of-00030.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00013-of-00030.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00013-of-00030.safetensors", "model.layers.19.input_layernorm.weight": "model-00013-of-00030.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00014-of-00030.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00014-of-00030.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00014-of-00030.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00014-of-00030.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00014-of-00030.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00014-of-00030.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00014-of-00030.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00014-of-00030.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00014-of-00030.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00014-of-00030.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00014-of-00030.safetensors", "model.layers.2.input_layernorm.weight": "model-00014-of-00030.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00015-of-00030.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00015-of-00030.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00015-of-00030.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00015-of-00030.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00015-of-00030.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00015-of-00030.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00015-of-00030.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00015-of-00030.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00015-of-00030.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00015-of-00030.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00015-of-00030.safetensors", "model.layers.20.input_layernorm.weight": "model-00015-of-00030.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00016-of-00030.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00016-of-00030.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00016-of-00030.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00016-of-00030.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00016-of-00030.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00016-of-00030.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00016-of-00030.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00016-of-00030.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00016-of-00030.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00016-of-00030.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00016-of-00030.safetensors", "model.layers.21.input_layernorm.weight": "model-00016-of-00030.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00017-of-00030.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00017-of-00030.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00017-of-00030.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00017-of-00030.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00017-of-00030.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00017-of-00030.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00017-of-00030.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00017-of-00030.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00017-of-00030.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00017-of-00030.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00017-of-00030.safetensors", "model.layers.22.input_layernorm.weight": "model-00017-of-00030.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00018-of-00030.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00018-of-00030.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00018-of-00030.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00018-of-00030.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00018-of-00030.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00018-of-00030.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00018-of-00030.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00018-of-00030.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00030.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00018-of-00030.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00018-of-00030.safetensors", "model.layers.23.input_layernorm.weight": "model-00018-of-00030.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00019-of-00030.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00019-of-00030.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00019-of-00030.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00019-of-00030.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00019-of-00030.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00019-of-00030.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00019-of-00030.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00019-of-00030.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00019-of-00030.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00019-of-00030.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00019-of-00030.safetensors", "model.layers.24.input_layernorm.weight": "model-00019-of-00030.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00020-of-00030.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00020-of-00030.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00020-of-00030.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00020-of-00030.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00020-of-00030.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00020-of-00030.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00020-of-00030.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00020-of-00030.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00020-of-00030.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00020-of-00030.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00020-of-00030.safetensors", "model.layers.25.input_layernorm.weight": "model-00020-of-00030.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00021-of-00030.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00021-of-00030.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00021-of-00030.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00021-of-00030.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00021-of-00030.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00021-of-00030.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00021-of-00030.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00021-of-00030.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00021-of-00030.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00021-of-00030.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00021-of-00030.safetensors", "model.layers.26.input_layernorm.weight": "model-00021-of-00030.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00022-of-00030.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00022-of-00030.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00022-of-00030.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00022-of-00030.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00022-of-00030.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00022-of-00030.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00022-of-00030.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00022-of-00030.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00022-of-00030.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00022-of-00030.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00022-of-00030.safetensors", "model.layers.27.input_layernorm.weight": "model-00022-of-00030.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00023-of-00030.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00023-of-00030.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00023-of-00030.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00023-of-00030.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00023-of-00030.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00023-of-00030.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00023-of-00030.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00023-of-00030.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00023-of-00030.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00023-of-00030.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00023-of-00030.safetensors", "model.layers.3.input_layernorm.weight": "model-00023-of-00030.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00024-of-00030.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00024-of-00030.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00024-of-00030.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00024-of-00030.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00024-of-00030.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00024-of-00030.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00024-of-00030.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00024-of-00030.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00024-of-00030.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00024-of-00030.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00024-of-00030.safetensors", "model.layers.4.input_layernorm.weight": "model-00024-of-00030.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00025-of-00030.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00025-of-00030.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00025-of-00030.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00025-of-00030.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00025-of-00030.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00025-of-00030.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00025-of-00030.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00025-of-00030.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00025-of-00030.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00025-of-00030.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00025-of-00030.safetensors", "model.layers.5.input_layernorm.weight": "model-00025-of-00030.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00026-of-00030.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00026-of-00030.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00026-of-00030.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00026-of-00030.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00026-of-00030.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00026-of-00030.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00026-of-00030.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00026-of-00030.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00026-of-00030.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00026-of-00030.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00026-of-00030.safetensors", "model.layers.6.input_layernorm.weight": "model-00026-of-00030.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00027-of-00030.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00027-of-00030.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00027-of-00030.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00027-of-00030.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00027-of-00030.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00027-of-00030.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00027-of-00030.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00027-of-00030.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00027-of-00030.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00027-of-00030.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00027-of-00030.safetensors", "model.layers.7.input_layernorm.weight": "model-00027-of-00030.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00028-of-00030.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00028-of-00030.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00028-of-00030.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00028-of-00030.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00028-of-00030.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00028-of-00030.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00028-of-00030.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00028-of-00030.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00028-of-00030.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00028-of-00030.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00028-of-00030.safetensors", "model.layers.8.input_layernorm.weight": "model-00028-of-00030.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00029-of-00030.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00029-of-00030.safetensors", "model.layers.9.input_layernorm.weight": "model-00029-of-00030.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00030-of-00030.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00030-of-00030.safetensors", "model.norm.weight": "model-00030-of-00030.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "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:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}