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 +1,49 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- huihui-ai/DeepSeek-R1-Distill-Qwen-7B-abliterated-v2
+- mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1
+- Triangle104/DSR1-Distill-Qwen-7B-RP
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+---
+
+# ZeroXClem/Qwen2.5-7B-DistilPrism
+
+ZeroXClem/Qwen2.5-7B-DistilPrism is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [huihui-ai/DeepSeek-R1-Distill-Qwen-7B-abliterated-v2](https://huggingface.co/huihui-ai/DeepSeek-R1-Distill-Qwen-7B-abliterated-v2)
+* [mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1](https://huggingface.co/mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1)
+* [Triangle104/DSR1-Distill-Qwen-7B-RP](https://huggingface.co/Triangle104/DSR1-Distill-Qwen-7B-RP)
+* [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B)
+
+## 🧩 Configuration
+
+```yaml
+# Merge configuration for ZeroXClem/Qwen2.5-7B-DistilPrism using Model Stock
+
+name: ZeroXClem-Qwen2.5-7B-DistilPrism
+merge_method: model_stock
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+tokenizer_source: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+dtype: bfloat16
+parameters:
+  normalize: true
+  rescale: true
+models:
+  - model: huihui-ai/DeepSeek-R1-Distill-Qwen-7B-abliterated-v2
+    parameters:
+      weight: 0.3
+  - model: mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1
+    parameters:
+      weight: 0.25
+  - model: Triangle104/DSR1-Distill-Qwen-7B-RP
+    parameters:
+      weight: 0.2
+  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+    parameters:
+      weight: 0.25
+
+
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "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": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151665
+}

mergekit_config.yml

@@ -0,0 +1,26 @@
+
+# Merge configuration for ZeroXClem/Qwen2.5-7B-DistilPrism using Model Stock
+
+name: ZeroXClem-Qwen2.5-7B-DistilPrism
+merge_method: model_stock
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+tokenizer_source: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+dtype: bfloat16
+parameters:
+  normalize: true
+  rescale: true
+models:
+  - model: huihui-ai/DeepSeek-R1-Distill-Qwen-7B-abliterated-v2
+    parameters:
+      weight: 0.3
+  - model: mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1
+    parameters:
+      weight: 0.25
+  - model: Triangle104/DSR1-Distill-Qwen-7B-RP
+    parameters:
+      weight: 0.2
+  - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+    parameters:
+      weight: 0.25
+
+

model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adf85d55ec84d492bd957e09813e816a911ce09e4f050abf9f904d02b9a1c6f4
+size 1087134848

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc1ce02a60cd62f8792e0f91d0ae0454a223320b3ac7065e2fa53d2c3e2f3672
+size 1087134864

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:295e3b980a9725fdabdf49b8513a85d614ac02892090e0b657f32ddeda3eb9ab
+size 932241160

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09270868166e488322894b6a1c1b49bee06eae85b1db8d04a244a8d989b4c454
+size 932233912

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2ddfaea4fdfcd13fa0f847f048850e3dfbeedaf953f7b999ad70476e811e518
+size 932233912

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40bbc1dfb9ecd0ba1cd6e9c648d916aa2959e7ec98c01d6695a29166205b9888
+size 932233912

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f41fb7164b3fa72f43c7c2398fc226551a5d8e076b700f86898418940513327
+size 932233912

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50be7c224b9137ecdcfd84fa938b3d43fd208244d750564a45129bfcb9509af8
+size 932233912

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:290d245d0799538410a6d3a34edcda60e0eaa4008cf30f16ea56e43631f3f7c3
+size 932233904

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76b7e692cb3175346feee7ef1eed86b5a5c9dc656d2ee7675c4a0c4b0fdd12ef
+size 932233912

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f519274e401f949938800d7141a698c12fa05bf39383752410c584f2af8eb9e
+size 932233912

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:715d365d0bb4d99ba2cba57e1a3118f16219e5541fa3b06d2fe7d3a252d2eb37
+size 932233912

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c07d39d67c2b92028f76e2232be823a3d1685268288dfaacadcf4c4e677bcd
+size 932233904

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ba914468561aa3517a0d880d06fcd3888cfade0528226305bd3b3250d7f4d6b
+size 932233888

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a26dcbe13a0b6434f77696adb70c12d9a600948a74ae0acb4a250e7667dcc7d
+size 932233888

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9489630338e426f2a511b1f291f3bbd82f992749a76689a8034b0361de791fe8
+size 932233872

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.0"}, "weight_map": {"lm_head.weight": "model-00001-of-00016.safetensors", "model.embed_tokens.weight": "model-00002-of-00016.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00016.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00016.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00016.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00016.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00003-of-00016.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00016.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00016.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00016.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00016.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00016.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00006-of-00016.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00006-of-00016.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00007-of-00016.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00007-of-00016.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00008-of-00016.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.2.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00009-of-00016.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00009-of-00016.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00009-of-00016.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.20.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00009-of-00016.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00009-of-00016.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00009-of-00016.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00010-of-00016.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00010-of-00016.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00010-of-00016.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.22.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00010-of-00016.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00010-of-00016.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00010-of-00016.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.23.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00011-of-00016.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.24.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00011-of-00016.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00011-of-00016.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00011-of-00016.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.25.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00012-of-00016.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00012-of-00016.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00012-of-00016.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.26.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00012-of-00016.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00012-of-00016.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00012-of-00016.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.27.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.3.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00013-of-00016.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00013-of-00016.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00013-of-00016.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00014-of-00016.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.6.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00015-of-00016.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.8.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00016-of-00016.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.input_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.norm.weight": "model-00016-of-00016.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "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:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778

tokenizer_config.json

@@ -0,0 +1,195 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin��>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}