Upload folder using huggingface_hub

README.md

@@ -0,0 +1,28 @@
+---
+license: apache-2.0
+tags:
+- merge
+- OpenPipe/mistral-ft-optimized-1218
+- mlabonne/NeuralHermes-2.5-Mistral-7B
+---
+
+# mistral-7b-merged-passthrough
+
+mistral-7b-merged-passthrough is a merge of the following models:
+* [OpenPipe/mistral-ft-optimized-1218](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218)
+* [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B)
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+    - model: OpenPipe/mistral-ft-optimized-1218
+      layer_range: [0, 32]
+  - sources:
+    - model: mlabonne/NeuralHermes-2.5-Mistral-7B
+      layer_range: [24, 32]
+merge_method: passthrough
+dtype: bfloat16
+
+```

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mlabonne/NeuralHermes-2.5-Mistral-7B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": false,
+  "vocab_size": 32002
+}

mergekit_config.yml

@@ -0,0 +1,11 @@
+
+slices:
+  - sources:
+    - model: OpenPipe/mistral-ft-optimized-1218
+      layer_range: [0, 32]
+  - sources:
+    - model: mlabonne/NeuralHermes-2.5-Mistral-7B
+      layer_range: [24, 32]
+merge_method: passthrough
+dtype: bfloat16
+

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46200cfe67ce2a05229022a20595b25022fb62b446aa436c4e9e06ab096a140c
+size 1946227376

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3cc0f761e85e4c90053d01385284d43043cbfc63aea1adcf095d21afc83467e
+size 1979789776

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de55ee8985b8b6db2f2b515b2bc26c40b489b68b86076057ed058abc4091d8d8
+size 1946235664

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb1a9f305907cea3d4e9ce5304f67d95903983f107c044c7959437a486fd6548
+size 1979789736

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e7bb892edb70b379040ee99b28f93f0a8c970240e5d64b2a6ff254707a28444
+size 1828795000

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7538348b2c8eafea81e31ccd24d889ca64e64be9f3684a034d8a9a3bf9adb51
+size 1973481464

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b370e387bbc754d59aca46605104f58b88310ea7ccbd891a75f89b529d10509f
+size 1895903680

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:919e2a16413a89f725d91648a8d000bc65594f4fe325b77655b234b9ad1cc295
+size 1923182416

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32ac0b7fb986ef3c19bd338fb536cd0c88c2f1c6a48f2a5ff123d6683702fb0f
+size 1979789776

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c43098ca21f944897275b8636fcbab363e9b86d3f4e8cb6807b587ffe04f2cba
+size 520119904

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.embed_tokens.weight": "model-00006-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00010.safetensors", "lm_head.weight": "model-00008-of-00010.safetensors", "model.norm.weight": "model-00008-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00010-of-00010.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% 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|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}