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 +1,61 @@
+---
+base_model:
+- prithivMLmods/Calme-Ties2-78B
+- MaziyarPanahi/calme-3.1-instruct-78b
+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 [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [prithivMLmods/Calme-Ties2-78B](https://huggingface.co/prithivMLmods/Calme-Ties2-78B)
+* [MaziyarPanahi/calme-3.1-instruct-78b](https://huggingface.co/MaziyarPanahi/calme-3.1-instruct-78b)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+- sources:
+  - model: MaziyarPanahi/calme-3.1-instruct-78b
+    layer_range:
+    - 0
+    - 28
+  - model: prithivMLmods/Calme-Ties2-78B
+    layer_range:
+    - 0
+    - 28
+merge_method: slerp
+base_model: MaziyarPanahi/calme-3.1-instruct-78b
+parameters:
+  t:
+  - filter: self_attn
+    value:
+    - 0
+    - 0.5
+    - 0.3
+    - 0.7
+    - 1
+  - filter: mlp
+    value:
+    - 1
+    - 0.5
+    - 0.7
+    - 0.3
+    - 0
+  - value: 0.5
+dtype: bfloat16
+```

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-3.1-instruct-78b",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 80,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

mergekit_config.yml

@@ -0,0 +1,30 @@
+slices:
+- sources:
+  - model: MaziyarPanahi/calme-3.1-instruct-78b
+    layer_range:
+    - 0
+    - 28
+  - model: prithivMLmods/Calme-Ties2-78B
+    layer_range:
+    - 0
+    - 28
+merge_method: slerp
+base_model: MaziyarPanahi/calme-3.1-instruct-78b
+parameters:
+  t:
+  - filter: self_attn
+    value:
+    - 0
+    - 0.5
+    - 0.3
+    - 0.7
+    - 1
+  - filter: mlp
+    value:
+    - 1
+    - 0.5
+    - 0.7
+    - 0.3
+    - 0
+  - value: 0.5
+dtype: bfloat16

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3065c1960fe1bea9d747a79c22452558581a5db200ac6ab938ec2157edbf9a79
+size 4969152856

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6df19eac14dbd3b028931b55c24d824bdd4fa57e22782a342f1c9cdca30ce315
+size 4980864400

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49ede9086fd8ff57b44b3772d2f58e77fd5ed25a4e47b24a61644a0ebef7531f
+size 4764874368

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b7bdc1656360722c59178ca0e21fab37e55603793e669f428675a8c431248b6
+size 4781670352

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e92f66c570b589dc5d041f31a10eda73d4008bc34743404d3844174f55de21f
+size 4781670368

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:793808b01b894a3f8e1fd3f206453b72991122c0924e0c12e1dbfc512d63c72e
+size 4980864408

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abfd58d67b0f3fb59dfc29287e88731e14a71a3fc2f811c60b3bab142c78a025
+size 4764874368

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bfc2605c26b8a988c66e5fc09e74443fbfd669e6cd876f50e62de255f1bd6a7
+size 4781670352

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e37987010f45c497adabe5e39ec26acbf40b7d0279748d9b92939e2125b15a
+size 4781670352

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cba0dcf42f6804a72a4905e5c1e537045ff4943235ee5adfeaeff314b0b7f583
+size 4980864392

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78aec9e86be9d57aafcce38b6727a09e4c8c165971812c40971ca845c78a5e8f
+size 4764874336

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e18c3f125bcaf1c353b61bfa2a9f42d86fe7346b7f975102a0b9dd737eceffa
+size 786486384

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.6", "total_size": 54119497728}, "weight_map": {"lm_head.weight": "model-00001-of-00012.safetensors", "model.embed_tokens.weight": "model-00001-of-00012.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00012.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00012.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00012.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00012.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00012.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00012.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00012.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00012.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00012.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00012.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00012.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00012.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00012.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00012.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00012.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00004-of-00012.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00004-of-00012.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00004-of-00012.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00012.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00012.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00012.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00012.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00012.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00012.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00005-of-00012.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00005-of-00012.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00005-of-00012.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00005-of-00012.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00005-of-00012.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00005-of-00012.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00012.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00012.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00012.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00012.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00012.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00012.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00006-of-00012.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00006-of-00012.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00006-of-00012.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00006-of-00012.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00012.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00006-of-00012.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00012.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00006-of-00012.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00012.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00012.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00012.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00012.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00012.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00006-of-00012.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00012.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00012.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00012.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00007-of-00012.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00007-of-00012.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00007-of-00012.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00012.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00007-of-00012.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00012.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00012.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00007-of-00012.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00012.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00007-of-00012.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00012.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00012.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00012.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00012.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00012.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00012.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00012.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00008-of-00012.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00008-of-00012.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00008-of-00012.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.25.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00012.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00012.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00008-of-00012.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00012.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00012.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00008-of-00012.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00012.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00008-of-00012.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00012.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00012.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00012.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00009-of-00012.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00009-of-00012.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00009-of-00012.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00009-of-00012.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00009-of-00012.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00009-of-00012.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.3.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00009-of-00012.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00009-of-00012.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00009-of-00012.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00009-of-00012.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00009-of-00012.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00009-of-00012.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00009-of-00012.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00009-of-00012.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00009-of-00012.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00009-of-00012.safetensors", "model.layers.4.input_layernorm.weight": "model-00009-of-00012.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00010-of-00012.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00010-of-00012.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00010-of-00012.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00012.safetensors", "model.layers.6.input_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00010-of-00012.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00010-of-00012.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00010-of-00012.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00010-of-00012.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00011-of-00012.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00011-of-00012.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00011-of-00012.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.9.input_layernorm.weight": "model-00011-of-00012.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00011-of-00012.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00011-of-00012.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00012-of-00012.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00012-of-00012.safetensors", "model.norm.weight": "model-00012-of-00012.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 +1,44 @@
+{
+  "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",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}