Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,27 @@
+---
+license: apache-2.0
+base_model: TildeAI/TildeOpen-30b
+language:
+- de
+tags:
+- fitness
+- coach
+- llama-3
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# TildePink 30B - SoftSkill-Coach-Alpha
+
+TildePink is a fine-tuned version of TildeOpen-30b, optimized to act as a professional German-speaking fitness coach.
+
+## Model Details
+- **Developed by:** Werner Bogula **
+- **Language:** German (Primary)
+- **Persona:** Motivating SoftskillCoach, answering concise and helpful
+- **Base Model:** TildeOpen-30b
+- **Training Epochs:** 3.0
+- **Final Loss:** ~0.41
+
+## Intended Use
+This model is designed to check how a base model can be finetuned to follow instructions

chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 48,
+  "dtype": "bfloat16",
+  "eos_token_id": 131072,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.005,
+  "intermediate_size": 21504,
+  "max_position_embeddings": 65536,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 60,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 3e-06,
+  "rope_parameters": {
+    "rope_theta": 200000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "vocab_size": 131074
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_new_tokens": 1024,
+  "pad_token_id": 128001,
+  "repetition_penalty": 1.1,
+  "temperature": 0.3,
+  "top_p": 0.9,
+  "transformers_version": "4.40.0"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dce5998c4c5c5d64f8c849a5d94cba5d61aea3a146423a368566742e09dff9f5
+size 4957769480

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b74214dff740a4005ef1877edad0333efdc060a5d766a6e3bae2dc3252d6f0
+size 4844549224

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2ab64ff6a9b745386797a57dc1032606a45201762d0dd96f4b576edce59402b
+size 4844549248

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e9b0dbb10c5e9788e35f016af9bf5ba47bb33769c2abe1faffc27d38b55d23
+size 4844549272

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e167a02b065ea5bc9961f486124f960e95d3a461a325ecad0a809cd21b8baf7
+size 4844549272

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da302deae84580a8985f74b0bb836cd3b195fe6d968e690ad0a29ea3ea02559d
+size 4844549272

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f8f51b4ed4ec9975beb1ef626371ddc664ec56f84390f60ad73bdb755de475e
+size 4844549272

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d30141baf19cdf1ffddf3aedf6afddfef86a691405ad164646ad5399e0dd61d
+size 4844549272

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9863ed1119398ce2089a78f65f494e18aed38735d16319e9b4b154e41e952ab
+size 4844549272

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e6d9fe07490ccd1046c71bc75f8085d61beff188a88ee09fede5f11b626a634
+size 4844549272

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33a373a7a6f1e4e35da0df956ef160982b40c53f651ddb39d5bf8cdbd7e2131a
+size 4844549272

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d23c19d648f507a1952dd5fcc6be26d8c1a06f8d0eae1110c86d26e5d83409
+size 4844549272

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa72d71b31833c3a0f4ad795c775e6b43681a89fe775f7507317c93a42b028ce
+size 3108067016

model.safetensors.index.json

@@ -0,0 +1,550 @@
+{
+  "metadata": {
+    "total_size": 61355814912
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00013-of-00013.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00013.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00013-of-00013.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00013.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00013.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00013.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00013-of-00013.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00013.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00013.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00013.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00013.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00013.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.norm.weight": "model-00013-of-00013.safetensors"
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa1adf4b075de8d110b83a1ca842e90f572eee78d55f978b078668dcd9483b44
+size 17674232

tokenizer_config.json

@@ -0,0 +1,213 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": [
+    "<s>",
+    "</s>",
+    "<|instruct|>",
+    "<|begin_header|>",
+    "<|end_header|>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|begin_instruction|>",
+    "<|end_instruction|>",
+    "<|instruction|>",
+    "<|begin_context|>",
+    "<|end_context|>",
+    "<|context|>",
+    "<|begin_message|>",
+    "<|end_message|>",
+    "<|message|>",
+    "<|begin_response|>",
+    "<|end_response|>",
+    "<|response|>",
+    "<|begin_text|>",
+    "<|end_text|>",
+    "<|text|>",
+    "<|begin_user_info|>",
+    "<|end_user_info|>",
+    "<|user_info|>",
+    "<|eod|>",
+    "<|bod|>",
+    "<|sep|>",
+    "<|begin_summary|>",
+    "<|end_summary|>",
+    "<|begin_source|>",
+    "<|end_source|>",
+    "<|begin_target|>",
+    "<|end_target|>",
+    "<|begin_html|>",
+    "<|end_html|>",
+    "<|begin_latex|>",
+    "<|end_latex|>",
+    "<|begin_json|>",
+    "<|end_json|>",
+    "<|begin_csv|>",
+    "<|end_csv|>",
+    "<|begin_code|>",
+    "<|end_code|>",
+    "<|begin_link|>",
+    "<|end_link|>",
+    "<|endoftext|>",
+    "<|padding|>",
+    "<|extra_0|>",
+    "<|extra_1|>",
+    "<|extra_2|>",
+    "<|extra_3|>",
+    "<|extra_4|>",
+    "<|extra_5|>",
+    "<|extra_6|>",
+    "<|extra_7|>",
+    "<|extra_8|>",
+    "<|extra_9|>",
+    "<|extra_10|>",
+    "<|extra_11|>",
+    "<|extra_12|>",
+    "<|extra_13|>",
+    "<|extra_14|>",
+    "<|extra_15|>",
+    "<|extra_16|>",
+    "<|extra_17|>",
+    "<|extra_18|>",
+    "<|extra_19|>",
+    "<|extra_20|>",
+    "<|extra_21|>",
+    "<|extra_22|>",
+    "<|extra_23|>",
+    "<|extra_24|>",
+    "<|extra_25|>",
+    "<|extra_26|>",
+    "<|extra_27|>",
+    "<|extra_28|>",
+    "<|extra_29|>",
+    "<|extra_30|>",
+    "<|extra_31|>",
+    "<|extra_32|>",
+    "<|extra_33|>",
+    "<|extra_34|>",
+    "<|extra_35|>",
+    "<|extra_36|>",
+    "<|extra_37|>",
+    "<|extra_38|>",
+    "<|extra_39|>",
+    "<|extra_40|>",
+    "<|extra_41|>",
+    "<|extra_42|>",
+    "<|extra_43|>",
+    "<|extra_44|>",
+    "<|extra_45|>",
+    "<|extra_46|>",
+    "<|extra_47|>",
+    "<|extra_48|>",
+    "<|extra_49|>",
+    "<|extra_50|>",
+    "<|extra_51|>",
+    "<|extra_52|>",
+    "<|extra_53|>",
+    "<|extra_54|>",
+    "<|extra_55|>",
+    "<|extra_56|>",
+    "<|extra_57|>",
+    "<|extra_58|>",
+    "<|extra_59|>",
+    "<|extra_60|>",
+    "<|extra_61|>",
+    "<|extra_62|>",
+    "<|extra_63|>",
+    "<|extra_64|>",
+    "<|extra_65|>",
+    "<|extra_66|>",
+    "<|extra_67|>",
+    "<|extra_68|>",
+    "<|extra_69|>",
+    "<|extra_70|>",
+    "<|extra_71|>",
+    "<|extra_72|>",
+    "<|extra_73|>",
+    "<|extra_74|>",
+    "<|extra_75|>",
+    "<|extra_76|>",
+    "<|extra_77|>",
+    "<|extra_78|>",
+    "<|extra_79|>",
+    "<|extra_80|>",
+    "<|extra_81|>",
+    "<|extra_82|>",
+    "<|extra_83|>",
+    "<|extra_84|>",
+    "<|extra_85|>",
+    "<|extra_86|>",
+    "<|extra_87|>",
+    "<|extra_88|>",
+    "<|extra_89|>",
+    "<|extra_90|>",
+    "<|extra_91|>",
+    "<|extra_92|>",
+    "<|extra_93|>",
+    "<|extra_94|>",
+    "<|extra_95|>",
+    "<|extra_96|>",
+    "<|extra_97|>",
+    "<|extra_98|>",
+    "<|extra_99|>",
+    "<|extra_100|>",
+    "<|extra_101|>",
+    "<|extra_102|>",
+    "<|extra_103|>",
+    "<|extra_104|>",
+    "<|extra_105|>",
+    "<|extra_106|>",
+    "<|extra_107|>",
+    "<|extra_108|>",
+    "<|extra_109|>",
+    "<|extra_110|>",
+    "<|extra_111|>",
+    "<|extra_112|>",
+    "<|extra_113|>",
+    "<|extra_114|>",
+    "<|extra_115|>",
+    "<|extra_116|>",
+    "<|extra_117|>",
+    "<|extra_118|>",
+    "<|extra_119|>",
+    "<|extra_120|>",
+    "<|extra_121|>",
+    "<|extra_122|>",
+    "<|extra_123|>",
+    "<|extra_124|>",
+    "<|extra_125|>",
+    "<|extra_126|>",
+    "<|extra_127|>",
+    "<|extra_128|>",
+    " ",
+    "  ",
+    "   ",
+    "    ",
+    "        ",
+    "                ",
+    "\n",
+    "\n\n",
+    "\n\n\n",
+    "\n\n\n\n",
+    "\n\n\n\n\n\n\n\n",
+    "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+    "\t",
+    "\t\t",
+    "\t\t\t",
+    "\t\t\t\t",
+    "\t\t\t\t\t\t\t\t",
+    "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t"
+  ],
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}