upload files

.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

.gitignore

@@ -0,0 +1 @@
+.env

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+datasets:
+- cerebras/SlimPajama-627B
+- bigcode/starcoderdata
+- HuggingFaceH4/ultrachat_200k
+- HuggingFaceH4/ultrafeedback_binarized
+language:
+- en
+widget:
+  - example_title: Fibonacci (Python)
+    messages:
+    - role: system
+      content: You are a chatbot who can help code!
+    - role: user
+      content: Write me a function to calculate the first 10 digits of the fibonacci sequence in Python and print it out to the CLI.
+---
+<div align="center">
+
+# TinyLlama-1.1B
+</div>
+
+https://github.com/jzhang38/TinyLlama
+
+The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. 
+
+
+We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.
+
+#### This Model
+This is the chat model finetuned on top of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T). **We follow [HF's Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha)'s training recipe.** The model was " initially fine-tuned on a variant of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. 
+We then further aligned the model with [🤗 TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contain 64k prompts and model completions that are ranked by GPT-4." 
+
+
+#### How to use
+You will need the transformers>=4.34
+Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information.
+
+```python
+# Install transformers from source - only needed for versions <= v4.34
+# pip install git+https://github.com/huggingface/transformers.git
+# pip install accelerate
+
+import torch
+from transformers import pipeline
+
+pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", torch_dtype=torch.bfloat16, device_map="auto")
+
+# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
+messages = [
+    {
+        "role": "system",
+        "content": "You are a friendly chatbot who always responds in the style of a pirate",
+    },
+    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
+]
+prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+# <|system|>
+# You are a friendly chatbot who always responds in the style of a pirate.</s>
+# <|user|>
+# How many helicopters can a human eat in one sitting?</s>
+# <|assistant|>
+# ...
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_logits/chosen": -2.707406759262085,
+    "eval_logits/rejected": -2.656524419784546,
+    "eval_logps/chosen": -370.1297607421875,
+    "eval_logps/rejected": -296.0738525390625,
+    "eval_loss": 0.513750433921814,
+    "eval_rewards/accuracies": 0.738095223903656,
+    "eval_rewards/chosen": -0.02744222804903984,
+    "eval_rewards/margins": 1.0087225437164307,
+    "eval_rewards/rejected": -1.03616464138031,
+    "eval_runtime": 93.5908,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 21.37,
+    "eval_steps_per_second": 0.673
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.0"
+}

model.safetensors.index.json

@@ -0,0 +1,1766 @@
+{
+  "lm_head.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      32000,
+      2048
+    ],
+    "offset": 0,
+    "length": 65536000
+  },
+  "model.embed_tokens.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      32000,
+      2048
+    ],
+    "offset": 0,
+    "length": 65536000
+  },
+  "model.layers.0.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.0.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.0.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.0.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.0.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.0.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.0.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.0.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.0.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.1.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.1.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.1.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.1.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.1.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.1.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.1.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.1.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.1.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.10.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.10.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.10.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.10.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.10.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.10.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.10.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.10.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.10.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.11.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.11.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.11.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.11.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.11.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.11.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.11.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.11.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.11.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.12.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.12.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.12.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.12.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.12.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.12.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.12.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.12.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.12.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.13.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.13.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.13.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.13.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.13.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.13.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.13.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.13.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.13.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.14.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.14.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.14.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.14.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.14.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.14.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.14.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.14.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.14.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.15.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.15.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.15.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.15.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.15.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.15.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.15.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.15.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.15.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.16.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.16.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.16.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.16.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.16.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.16.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.16.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.16.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.16.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.17.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.17.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.17.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.17.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.17.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.17.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.17.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.17.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.17.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.18.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.18.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.18.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.18.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.18.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.18.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.18.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.18.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.18.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.19.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.19.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.19.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.19.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.19.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.19.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.19.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.19.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.19.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.2.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.2.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.2.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.2.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.2.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.2.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.2.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.2.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.2.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.20.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.20.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.20.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.20.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.20.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.20.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.20.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.20.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.20.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.21.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.21.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.21.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.21.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.21.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.21.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.21.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.21.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.21.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.3.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.3.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.3.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.3.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.3.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.3.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.3.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.3.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.3.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.4.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.4.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.4.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.4.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.4.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.4.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.4.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.4.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.4.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.5.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.5.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.5.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.5.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.5.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.5.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.5.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.5.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.5.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.6.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.6.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.6.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.6.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.6.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.6.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.6.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.6.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.6.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.7.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.7.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.7.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.7.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.7.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.7.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.7.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.7.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.7.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.8.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.8.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.8.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.8.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.8.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.8.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.8.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.8.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.8.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.9.input_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.9.mlp.down_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      5632
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.9.mlp.gate_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.9.mlp.up_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      5632,
+      2048
+    ],
+    "offset": 0,
+    "length": 11534336
+  },
+  "model.layers.9.post_attention_layernorm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  },
+  "model.layers.9.self_attn.k_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.layers.9.self_attn.o_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.9.self_attn.q_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048,
+      2048
+    ],
+    "offset": 0,
+    "length": 4194304
+  },
+  "model.layers.9.self_attn.v_proj.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      256,
+      2048
+    ],
+    "offset": 0,
+    "length": 524288
+  },
+  "model.norm.weight": {
+    "dtype": "torch.bfloat16",
+    "shape": [
+      2048
+    ],
+    "offset": 0,
+    "length": 2048
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}