初始化项目，由ModelHub XC社区提供模型

Model: guardrail/llama-2-7b-guanaco-instruct-sharded
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 +1,19 @@
+---
+license: apache-2.0
+datasets:
+- timdettmers/openassistant-guanaco
+pipeline_tag: text-generation
+---
+Model that is fine-tuned in 4-bit precision using QLoRA on [timdettmers/openassistant-guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco) and sharded to be used on a free Google Colab instance that can be loaded with 4bits. 
+
+It can be easily imported using the `AutoModelForCausalLM` class from `transformers`:
+
+```
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained(
+          "guardrail/llama-2-7b-guanaco-instruct-sharded",
+          load_in_4bit=True)
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "mlabonne/llama-2-7b-guanaco",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.32.0.dev0"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a41d272f4e9a51d3a2f6a1552af5cb288e0483a6b8ca60f8c02a77dea5f44d91
+size 1962969632

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0636628f5a18268c393a26f937cc832a38af5ff66d17d5a8ad439754e7d7de3e
+size 1933675832

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03253579cea8e8fcc9804b5c67e7d97abc5f91660b06ad73b6cf4788acf92db5
+size 1933643208

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d08ad6162178743dbdf3039182ec360e2d35951f96072824aa00c5b746f499a
+size 1979813064

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71461b62c44aa62274e41c4aa674b9f9316d01fd491a050a58d4e2c7d74ccbd1
+size 1887506000

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c345ea911c676bd4ad8f97790846519d9fcf2028ea858f1f77b50efde27d7f
+size 1979780088

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:356630c6a5ecfb5a01318bdc8a308f4f0ecec75824bb0ab16028e5dc063ceb08
+size 1933675856

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d8057e63c9b2af1d0300e05f71369bad9128cb7451dbe3d4628fb53c938dbb7
+size 1933643232

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cee4d3ba9368e5e4e19b44f56d911481af0d79512ab44099e753975ed402559c
+size 1979813088

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6969cb26b4d5a5da0d6a40a57b87ff4f5eeebab51b2d2a43245fac3101a1f662
+size 1887506008

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7953a734623feab350a948e03749bb41d8f2ee8fc8b341fe74abae3ad3b37ba0
+size 1979780088

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d8ee7d7c0bcc31ed32651881c9903559516d5f240c57f73fddb9e9246477b05
+size 1933675856

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:590bd00dc954d4b0c37d08a371dd4fa471122ac9c7eb814e8ba3797c8008baaf
+size 1933643232

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d5800f10a1a4c3aa054ed62a8b403168e833d05685c2dd593f747c07b031e6
+size 1694582816

model.safetensors.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 26953670656
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00005-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00005-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00006-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00006-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00007-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00007-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00008-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00008-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00008-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00009-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00009-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00010-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00010-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00010-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00011-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00011-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00012-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00012-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00013-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00013-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00013-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00014-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00003-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00003-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00004-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00004-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00005-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}