初始化项目，由ModelHub XC社区提供模型

Model: Delcos/Mistral-Pygmalion-7b
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,56 @@
+---
+license: cc-by-nc-nd-4.0
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- Mistral
+- Pygmalion
+- llama-2
+- llama-2-7b
+---
+
+
+# MistralPy-7b
+
+This is a merger focusing on preserving the roleplay abilities of Pygmalion while gaining the improved results from Mistral. This model works best for roleplay but is still fairly capable assistant. The smaller (7b) size does mean it isn't perfect at more complex reasoning tasks, but this should be addressed in the larger version that I'll upload soon (when I can get Mistral to play along).
+
+[GGUF version done by TheBloke](https://huggingface.co/TheBloke/Mistral-Pygmalion-7B-GGUF)
+
+
+
+# LLM Leaderboard Evaluation
+
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 44.58   |
+| ARC (25-shot)         | 54.44          |
+| HellaSwag (10-shot)   | 78.48    |
+| MMLU (5-shot)         | 49.23         |
+| TruthfulQA (0-shot)   | 41.82   |
+| Winogrande (5-shot)   | 75.3   |
+| GSM8K (5-shot)        | 6.82        |
+| DROP (3-shot)         | 5.94         |
+
+
+### Prompt Template
+```
+### Instruction:
+{Prompt & Backstory}
+### Assistant:
+{Output}
+```
+Example:
+
+```
+### Instruction:
+You are Sally, a fun 19 year old woman. Her favorite animal is "cat". Her favoritate color is "blue". She enjoys grape juice and cake.
+### Assistant:
+Sally: Hi, how are you?
+User: Okay, you?
+```
+
+# Send a message
+[Steam](https://steamcommunity.com/id/delcos/)
+#### Discord: delcos69

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "Delcos/Mistral-Pygmalion-7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.34.0"
+}

pytorch_model-00001-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6e292658c735121d3fdcf3b32a212221d2cb93697b5da355f3a47e45ae9cb07
+size 2015442764

pytorch_model-00002-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dd9c3687a3a413d8f361cf301b620eae7be2b1e386b93284f44080df081335f
+size 2023849108

pytorch_model-00003-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d08e9d7fb285a27a7a9f6101cfca61885e6393f69d7478e524336f69a11b5f2a
+size 2023849108

pytorch_model-00004-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66bc5d907dca1764e4adea18506799016b6aacaff9373f7e3d1a4b83c7d9debf
+size 2023849108

pytorch_model-00005-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c85e5b8cda73eaa4a04374fb5b7119c5cbb16478381389cb65aa175932055a9
+size 2023849108

pytorch_model-00006-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaeb9b6a3e861cd941b75a290c2aa9fcd6947028358b5fc0bf60e0d6e0cbf979
+size 2023849108

pytorch_model-00007-of-00007.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff0b6530fd5a0743ad2dd149bfdfb566ccfc5ddef61e847c355a2f9851069fe
+size 1342243500

pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13476831232
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00007-of-00007.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
+    "model.norm.weight": "pytorch_model-00007-of-00007.bin"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}