Initial commit

README.md

@@ -1,3 +1,46 @@
 ---
 license: apache-2.0
+pipeline_tag: text-generation
+language:
+  - en
+tags:
+- pretrained
+inference:
+  parameters:
+    temperature: 0.7
 ---
+
+# Model Card for Mistral-7B-v0.1
+
+The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. 
+Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks we tested.
+
+For full details of this model please read our [paper](https://arxiv.org/abs/2310.06825) and [release blog post](https://mistral.ai/news/announcing-mistral-7b/).
+
+## Model Architecture
+
+Mistral-7B-v0.1 is a transformer model, with the following architecture choices:
+- Grouped-Query Attention
+- Sliding-Window Attention
+- Byte-fallback BPE tokenizer
+
+## Troubleshooting
+
+- If you see the following error:
+```
+KeyError: 'mistral'
+```
+- Or:
+```
+NotImplementedError: Cannot copy out of meta tensor; no data!
+```
+
+Ensure you are utilizing a stable version of Transformers, 4.34.0 or newer.
+
+## Notice
+
+Mistral 7B is a pretrained base model and therefore does not have any moderation mechanisms.
+
+## The Mistral AI Team
+ 
+Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lélio Renard Lavaud, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.34.0"
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e63666c31e75faf26dc59ca48ebb4c8d31726e459cfc6650038d19a38a0398d
+size 899696328

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce4c2a1bbdfec1162463fcb8c2c93b8c22b500b620190b1d2257b8f1fada2e82
+size 989890696

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d8a8174cd3e7b6120c75abb735903f0eee7dc1b9f9f219fa7646002354600f4
+size 989907312

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f46ebe76d76cfb9eb2539e880952a65b3d091e37c0a5d2e8a282c7402041495b
+size 956336616

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787951436d0cbc1373dce22e6afeb00a14d8dcebf20be767e78614ccdf6eb45e
+size 989890712

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8947210702cd6a1eab64bf9f0b6885b19cc078a506735dd71bf054ccfa05709
+size 989890712

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b4eaa936c153df53179fa761c4e69d4c6a78d9c83cbe2351d8587ac3707453f
+size 989907328

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:518f248c19815a174117b90474ca5b1e03ba50c17d691b78d12325e36367045c
+size 956336632

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d558d97666af1e3f74b2c2b353549f0e4ce6a53974c4fb10206b06898f45ef05
+size 989890720

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec1411dee60273862e70d19a5f76246f1251130ce9ce837b04aaa4530a551768
+size 989890712

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10755bd20e0caa1a04968509a4c9c118178005aa3014aed6114419641471548d
+size 989907328

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c76d04028fdccd9e0c45ef851c913c43fc5fb8d6fb1f05033d48a285eaca946
+size 956336632

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09b318c5f371cfe0ae8b1b6c352f44459012eea3190b2db91bbcf5dfae6f4f55
+size 989890720

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a6bd92a0e9c8543e3014393d629a25c745b948fce6b7263422f21031507d0ab
+size 989890712

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdcb52ff3790860b90e3a0d4a1029ed718d8cac2718130a7dc95c56022014ab7
+size 815834680

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00015-of-00015.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00015.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.norm.weight": "model-00015-of-00015.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,10 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}