初始化项目，由ModelHub XC社区提供模型

Model: arcee-ai/Mistral-7B-Instruct-v0.2-expanded
Source: Original Platform

.gitattributes

@@ -0,0 +1,43 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+model-00001-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00006-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00007-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00008-of-00008.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,177 @@
+---
+library_name: transformers
+tags:
+- mergekit
+- block expansion
+- progressive mistral
+- arcee cpt
+---
+
+# Mistral-7B-Instruct-v0.2-expanded
+
+This method employs mergekit's passthrough method to expand blocks within the "mistralai/Mistral-7B-Instruct-v0.2" model. For every 5th layer, 
+a new layer is added, with the `o_proj` and `down_proj` parameters of these added layers initialized to zero, mirroring the approach used in LLaMA Pro. 
+
+### It's important to note that this configuration has not undergone fine-tuning. So this won't work. Therefore, when fine-tuning, ensure that only every 5th layer is trainable,while all other layers remain frozen.
+
+## 🧩 Configuration
+
+```yaml
+slices:
+  - sources:
+      - model: mistralai/Mistral-7B-Instruct-v0.2
+        layer_range: [0, 4]
+  - sources:
+      - model: mistralai/Mistral-7B-Instruct-v0.2
+        layer_range: [3, 4]
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+            
+  - sources:
+      - model: mistralai/Mistral-7B-Instruct-v0.2
+        layer_range: [4, 8]
+  - sources:
+      - model: mistralai/Mistral-7B-Instruct-v0.2
+        layer_range: [7, 8]
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+            
+  - sources:
+      - model: mistralai/Mistral-7B-Instruct-v0.2
+        layer_range: [8, 12]
+  - sources:
+      - model: mistralai/Mistral-7B-Instruct-v0.2
+        layer_range: [11, 12]
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+            
+  - sources:
+      - model: mistralai/Mistral-7B-Instruct-v0.2
+        layer_range: [12, 16]
+  - sources:
+      - model: mistralai/Mistral-7B-Instruct-v0.2
+        layer_range: [15, 16]
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+            
+  - sources:
+      - model: mistralai/Mistral-7B-Instruct-v0.2
+        layer_range: [16, 20]
+  - sources:
+      - model: mistralai/Mistral-7B-Instruct-v0.2
+        layer_range: [19, 20]
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+            
+  - sources:
+      - model: mistralai/Mistral-7B-Instruct-v0.2
+        layer_range: [20, 24]
+  - sources:
+      - model: mistralai/Mistral-7B-Instruct-v0.2
+        layer_range: [23, 24]
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+            
+  - sources:
+      - model: mistralai/Mistral-7B-Instruct-v0.2
+        layer_range: [24, 28]
+  - sources:
+      - model: mistralai/Mistral-7B-Instruct-v0.2
+        layer_range: [27, 28]
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+            
+  - sources:
+      - model: mistralai/Mistral-7B-Instruct-v0.2
+        layer_range: [28, 32]
+  - sources:
+      - model: mistralai/Mistral-7B-Instruct-v0.2
+        layer_range: [31, 32]
+        parameters:
+          scale:
+            - filter: o_proj
+              value: 0.0
+            - filter: down_proj
+              value: 0.0
+            - value: 1.0
+
+merge_method: passthrough
+dtype: bfloat16
+```
+
+# Function to freeze layers
+
+```
+from transformers import AutoModelForCausalLM
+
+def enable_grad_only_every_nth(model, n):
+    """
+    This function configures the specified model to enable gradient calculations exclusively for every nth layer, starting 
+    from the first layer (0-indexed), to accommodate newly added blocks for training. Concurrently, it freezes the gradients 
+    for all other components of the model, including the embedding layers and the model's head. This setup is particularly 
+    useful for fine-tuning processes where only a subset of layers are targeted for updates, ensuring efficient training and 
+    adaptation of newly integrated layers while maintaining the pre-trained behavior of other model components.
+    """
+
+    # Freeze embeddings.
+    for param in model.model.embed_tokens.parameters():
+        param.requires_grad = False
+
+    # Freeze lm_head.
+    for param in model.lm_head.parameters():
+        param.requires_grad = False
+
+    # Enable gradients for every nth layer
+    layers = model.model.layers  # Access the ModuleList containing the layers
+
+    for index, layer in enumerate(layers):
+
+        if (index + 1) % n == 0:  # Enables gradients for every nth layer, starting from the layer after the 0th
+            for param in layer.parameters():
+                param.requires_grad = True
+        else:
+            for param in layer.parameters():
+                param.requires_grad = False
+
+model = transformers.AutoModelForCausalLM.from_pretrained(
+    "arcee-ai/Mistral-7B-Instruct-v0.2-expanded"
+    )
+# Update layer gradients, specify the correct value for n based on your model's architecture
+n =5
+enable_grad_only_every_nth(model, n)
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/Users/gayalshamane/Documents/mergekit/mistral_expanded_it",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "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": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad361fecf3311f45cabbf3a05ed75e2cfca9751987a5ebd1689bfd43de593612
+size 4987196936

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:316e547f4729d309b55f00a92ab03087d9e574274696f5a2962c0395f2cac3db
+size 4899116440

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:119ac2d4385fccd8b5ecded02b8fd0ea578d13e2f8139f42c410b17d37033a87
+size 4999813120

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88d5b3b8d8a1b3d0e4a9f0139a5a496358c1ce896cbcd56af4e6e60ce27f84ed
+size 4999813128

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29fb27fb8712bf8cf2677ae45d5b67a792acbc87398260719d4fc3295cbcfc52
+size 4832007496

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25dbe4ec94a69895ea57c8cc55b2f074e1faee0a3d5b72ac1005f5f3f13b5dfa
+size 4999813120

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f2e94f5a6d008431685e37bfa58a6d3bcb06640187c98850b9c12c29f6bdd9
+size 4999813128

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b596a3d979a94a3de5aa1ce94768d636ed90ab50d3c0ea62e92fb8e3ddece2f
+size 1228981008

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 35946512384
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00008-of-00008.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.norm.weight": "model-00008-of-00008.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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}