Upload folder using huggingface_hub

README.md

@@ -0,0 +1,72 @@
+---
+license: other
+license_name: deepseek
+license_link: https://github.com/deepseek-ai/DeepSeek-Math/blob/main/LICENSE-MODEL
+---
+
+
+<p align="center">
+<img width="500px" alt="DeepSeek Chat" src="https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/images/logo.png?raw=true">
+</p>
+<p align="center"><a href="https://www.deepseek.com/">[🏠Homepage]</a>  |  <a href="https://chat.deepseek.com/">[🤖 Chat with DeepSeek LLM]</a>  |  <a href="https://discord.gg/Tc7c45Zzu5">[Discord]</a>  |  <a href="https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/images/qr.jpeg">[Wechat(微信)]</a> </p>
+
+<p align="center">
+  <a href="https://arxiv.org/pdf/2402.03300.pdf"><b>Paper Link</b>👁️</a>
+</p>
+
+<hr>
+
+
+
+
+
+### 1. Introduction to DeepSeekMath
+See the [Introduction](https://github.com/deepseek-ai/DeepSeek-Math) for more details.
+
+### 2. How to Use
+Here give some examples of how to use our model.
+
+**Chat Completion**
+
+
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
+
+model_name = "deepseek-ai/deepseek-math-7b-rl"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
+model.generation_config = GenerationConfig.from_pretrained(model_name)
+model.generation_config.pad_token_id = model.generation_config.eos_token_id
+
+messages = [
+    {"role": "user", "content": "what is the integral of x^2 from 0 to 2?"}
+]
+input_tensor = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt")
+outputs = model.generate(input_tensor.to(model.device), max_new_tokens=100)
+
+result = tokenizer.decode(outputs[0][input_tensor.shape[1]:], skip_special_tokens=True)
+print(result)
+```
+
+Avoiding the use of the provided function `apply_chat_template`, you can also interact with our model following the sample template. Note that `messages` should be replaced by your input.
+
+```
+User: {messages[0]['content']}
+
+Assistant: {messages[1]['content']}<｜end▁of▁sentence｜>User: {messages[2]['content']}
+
+Assistant:
+```
+
+**Note:** By default (`add_special_tokens=True`), our tokenizer automatically adds a `bos_token` (`<｜begin▁of▁sentence｜>`) before the input text. Additionally, since the system prompt is not compatible with this version of our models, we DO NOT RECOMMEND including the system prompt in your input.
+
+### 3. License
+This code repository is licensed under the MIT License. The use of DeepSeekMath models is subject to the Model License. DeepSeekMath supports commercial use.
+
+See the [LICENSE-MODEL](https://github.com/deepseek-ai/DeepSeek-Math/blob/main/LICENSE-MODEL) for more details.
+
+### 4. Contact
+
+If you have any questions, please raise an issue or contact us at [[email protected]](mailto:[email protected]).
+

cal_data.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41be37cb39280ccb28b2872bd2ce70980ee950fd453083a4ca90fdb227b176f7
+size 1638488

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "moe_intermediate_size": 11008,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.1",
+  "use_cache": true,
+  "vocab_size": 102400
+}

hidden_states.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87f9d092966fa597133a904cedd354a59c9aa445fcd33ddbd9b5ec93eac9e54f
+size 1677730376

huggingface-metadata.txt

@@ -0,0 +1,6 @@
+url: https://huggingface.co/deepseek-ai/deepseek-math-7b-rl
+branch: main
+download date: 2024-02-19 03:15:05
+sha256sum:
+    133cf22e197ad3145a47e786733ece3428845a876f53734b698cd8c3a333f822 pytorch_model-00001-of-000002.bin
+    ed67f683f774f8b98a08a0591c39d53d63c53da77657b29a4df4c4e665ba3e5f pytorch_model-00002-of-000002.bin

model.safetensors.index.json

@@ -0,0 +1,280 @@
+{
+    "metadata": {
+        "total_size": 13820731392
+    },
+    "weight_map": {
+        "model.embed_tokens.weight": "model-00001-of-000002.safetensors",
+        "model.norm.weight": "model-00001-of-000002.safetensors",
+        "lm_head.weight": "model-00001-of-000002.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00001-of-000002.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00001-of-000002.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00002-of-000002.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00002-of-000002.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00002-of-000002.safetensors"
+    }
+}

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac6fc7bb7e931f731839b47a20fd16dc10a5c0a75b4ae32b2a2e1100d2b3be2
+size 7239869328

tokenizer_config.json

@@ -0,0 +1,27 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": true,
+  "model_max_length": 4096,
+  "sp_model_kwargs": {},
+  "unk_token": null,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
+}