Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# SOLAR-19.2B-Instruct-v1.0
+
+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 passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* /Users/jsarnecki/opt/upstage/SOLAR-10.7B-Instruct-v1.0
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+dtype: float16
+merge_method: passthrough
+# Layer Interleaving of SOLAR-10.7B-Instruct-v1.0 (Instruction Fine-tuned SOLAR-10.7B-v1.0)
+# where n = 48 (The number of layers the model originally had)
+#       m = 12 (The number of layers the interleaved into model per row)
+#       M = 36 = 3m (The number of layers interlaced into the model)
+#       s = 84 = n + M (The number of layers the model will have after the layer interleaving)
+#       P = ~19.2B = 19.17B parameters = (s/n)*10.7B (The number of parameters the model will have after the DUS and layer interleaving)
+slices:
+- sources:
+  - layer_range: [0, 12]
+    model: /Users/jsarnecki/opt/upstage/SOLAR-10.7B-Instruct-v1.0
+
+# Interleaved Layer
+- sources:
+  - layer_range: [6, 18]
+    model: /Users/jsarnecki/opt/upstage/SOLAR-10.7B-Instruct-v1.0 
+
+- sources:
+  - layer_range: [12, 24]
+    model: /Users/jsarnecki/opt/upstage/SOLAR-10.7B-Instruct-v1.0 
+
+# Interleaved Layer
+- sources:
+  - layer_range: [18, 30]
+    model: /Users/jsarnecki/opt/upstage/SOLAR-10.7B-Instruct-v1.0 
+
+- sources:
+  - layer_range: [24, 36]
+    model: /Users/jsarnecki/opt/upstage/SOLAR-10.7B-Instruct-v1.0 
+
+# Interleaved Layer
+- sources:
+  - layer_range: [30, 42]
+    model: /Users/jsarnecki/opt/upstage/SOLAR-10.7B-Instruct-v1.0 
+
+- sources:
+  - layer_range: [36, 48]
+    model: /Users/jsarnecki/opt/upstage/SOLAR-10.7B-Instruct-v1.0 
+
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/Users/jsarnecki/opt/upstage/SOLAR-10.7B-Instruct-v1.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "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": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 84,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,39 @@
+dtype: float16
+merge_method: passthrough
+# Layer Interleaving of SOLAR-10.7B-Instruct-v1.0 (Instruction Fine-tuned SOLAR-10.7B-v1.0)
+# where n = 48 (The number of layers the model originally had)
+#       m = 12 (The number of layers the interleaved into model per row)
+#       M = 36 = 3m (The number of layers interlaced into the model)
+#       s = 84 = n + M (The number of layers the model will have after the layer interleaving)
+#       P = ~19.2B = 19.17B parameters = (s/n)*10.7B (The number of parameters the model will have after the DUS and layer interleaving)
+slices:
+- sources:
+  - layer_range: [0, 12]
+    model: /Users/jsarnecki/opt/upstage/SOLAR-10.7B-Instruct-v1.0
+
+# Interleaved Layer
+- sources:
+  - layer_range: [6, 18]
+    model: /Users/jsarnecki/opt/upstage/SOLAR-10.7B-Instruct-v1.0 
+
+- sources:
+  - layer_range: [12, 24]
+    model: /Users/jsarnecki/opt/upstage/SOLAR-10.7B-Instruct-v1.0 
+
+# Interleaved Layer
+- sources:
+  - layer_range: [18, 30]
+    model: /Users/jsarnecki/opt/upstage/SOLAR-10.7B-Instruct-v1.0 
+
+- sources:
+  - layer_range: [24, 36]
+    model: /Users/jsarnecki/opt/upstage/SOLAR-10.7B-Instruct-v1.0 
+
+# Interleaved Layer
+- sources:
+  - layer_range: [30, 42]
+    model: /Users/jsarnecki/opt/upstage/SOLAR-10.7B-Instruct-v1.0 
+
+- sources:
+  - layer_range: [36, 48]
+    model: /Users/jsarnecki/opt/upstage/SOLAR-10.7B-Instruct-v1.0 

model-00001-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6fba7e6ba17fad1ca8a839126ad2f1f978e93c21f0a8e9f301356f4c8810399
+size 3993100760

model-00002-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c319055e7cfc94718ff19721c89c8bfeb7383d5516476df4032f1b187c39ee3
+size 3986826936

model-00003-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04112008585a969eacc93dd4f684158afb20812c11b4fd017babfcde6fbde869
+size 3909247928

model-00004-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283beeefec1de5f18487ca4e061244763a8dc9e682a0cdfd8df28cb7a1972b2c
+size 3976357384

model-00005-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b0389a9634d918a1af1cb96322344aab7ba2bb8584fecd7f1ccc2b331c9a4a
+size 3993150608

model-00006-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28bf96a17de5f0f0fd70e3cc242625dd7b70b270644ed80cf72d00ac4d01e48b
+size 3892471288

model-00007-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947cc1dcf249832580aef3cfff4abda9fecbc151d6e4b32bf6b0fa344de62b2a
+size 3959579448

model-00008-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca44d2e4a1acf3e5074b739e785979b85694a3e4d207bb602945330e9fbe4749
+size 3926025360

model-00009-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ef11c085cef8aa8e5e4d3c27c9153b314f7e903c309383f83062c54e6103993
+size 3842155432

model-00010-of-00010.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c5d41da8842dc88d901d6ef73cc54e5c0a18ef2962c293e6ad2cdf0864788cd
+size 1688284744

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 37167112192}, "weight_map": {"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.embed_tokens.weight": "model-00002-of-00010.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.62.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.56.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.61.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.55.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.60.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.54.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.53.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.52.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.51.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.45.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.50.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.44.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.49.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.43.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.48.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.42.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.41.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.40.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.79.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.78.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.77.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.71.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.76.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.70.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.75.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.69.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.74.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.68.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.73.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.67.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.72.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.66.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.65.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.59.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.64.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.58.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.63.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.57.input_layernorm.weight": "model-00009-of-00010.safetensors", "lm_head.weight": "model-00010-of-00010.safetensors", "model.norm.weight": "model-00010-of-00010.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.83.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.82.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00010-of-00010.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00010-of-00010.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.81.input_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.80.input_layernorm.weight": "model-00010-of-00010.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_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.model

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

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": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n'  + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}