初始化项目，由ModelHub XC社区提供模型

Model: DevQuasar/unsloth-Phi-3-medium-Brainstorm
Source: Original Platform

.gitattributes

@@ -0,0 +1,49 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm 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 +1,15 @@
+---
+license: mit
+datasets:
+- DevQuasar/brainstorm-v3.1_vicnua_1k
+base_model:
+- unsloth/Phi-3-medium-4k-instruct-bnb-4bit
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+[<img src="https://raw.githubusercontent.com/csabakecskemeti/devquasar/main/dq_logo_black-transparent.png" width="200"/>](https://devquasar.com)
+
+'Make knowledge free for everyone'
+
+<a href='https://ko-fi.com/L4L416YX7C' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi6.png?v=6' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "unsloth/Phi-3-medium-4k-instruct",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 4096,
+  "model_type": "mistral",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "pad_token_id": 32009,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 2048,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 32064
+}

configuration.json

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

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    32000,
+    32001,
+    32007
+  ],
+  "max_length": 4096,
+  "pad_token_id": 32009,
+  "transformers_version": "4.46.2"
+}

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a1f103c27b599ec92e70bb2da322166df92afe5303554471a47aee0a09b3e41
+size 4903529984

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1f39e0330195a64107618a7948cc08d95852db208695e0dfbef196bbbcda949
+size 4928433544

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d012bcc4cb3b5e3539c4a5505e6fe1ace68ea0e0dc49eb6c61665a93c7bf58bc
+size 4718759768

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17c48cfe9a87eec014b05bba651e0f626ee050961a7462b91d0b0dee34e75a72
+size 4823575856

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e16fb7d9aed19f47dc38338e3921b8b5d39e766c9e2d19a4562b8368682bd4f1
+size 4718759800

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:018bb1b2572e8b51afa58c01fd9ab9d499c1344855b872fce3c342a9a93c6b8b
+size 4823575856

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a21cd4a4ad3c81f14181f4716de400a9759ec4205f00bed9535c62697a70937
+size 4718759800

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b88585f04f7b7ef21bd1f515f5db89cf149c9a088b7512a470b08c53dc9dd89
+size 4823575856

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67c0bac7c3706ea1d92f922417e23ade02111068e0c735baf0bcfe7f7026a000
+size 4718759800

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4289fa3dcbaf19e1047415c67830f4cfa5e66c1a943a8149557bc3fd80eae6d
+size 4823575856

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc2fae30c15b00781fe999e997ac9c8c91b32abcbfce8ffee35a533b8f97ae67
+size 4718759800

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:415371ba70ed40a1e62518b49d0950c2316033e7e05ad391cf6b47953783c97e
+size 3120928552

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 55840952320
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00012-of-00012.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00012-of-00012.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00012.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00012.safetensors",
+    "model.norm.weight": "model-00012-of-00012.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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|placeholder6|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49e6a63ecd78bc98840830eba8deb4cfb0c10b5f6d4952a13331a35225a3bd20
+size 3620658

tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<|placeholder6|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}