Upload folder using huggingface_hub

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+language:
+- ja
+- en
+tags:
+- japanese
+- causal-lm
+inference: false
+---
+# CyberAgentLM3-22B-Chat (CALM3-22B-Chat)
+
+## Model Description
+
+CyberAgentLM3 is a decoder-only language model pre-trained on 2.0 trillion tokens from scratch.  
+CyberAgentLM3-Chat is a fine-tuned model specialized for dialogue use cases.
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+
+model = AutoModelForCausalLM.from_pretrained("cyberagent/calm3-22b-chat", device_map="auto", torch_dtype="auto")
+tokenizer = AutoTokenizer.from_pretrained("cyberagent/calm3-22b-chat")
+streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+
+messages = [
+    {"role": "system", "content": "あなたは親切なAIアシスタントです。"},
+    {"role": "user", "content": "AIによって私たちの暮らしはどのように変わりますか？"}
+]
+
+input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
+output_ids = model.generate(input_ids,
+                            max_new_tokens=1024,
+                            temperature=0.5,
+                            streamer=streamer)
+```
+
+## Prompt Format
+CALM3-Chat uses ChatML as the prompt format.
+```
+<|im_start|>system
+あなたは親切なAIアシスタントです。<|im_end|>
+<|im_start|>user
+AIによって私たちの暮らしはどのように変わりますか？<|im_end|>
+<|im_start|>assistant
+```
+
+## Model Details
+
+* **Model size**: 22B
+* **Context length**: 16384
+* **Model type**: Transformer-based Language Model
+* **Language(s)**: Japanese, English
+* **Developed by**: [CyberAgent, Inc.](https://www.cyberagent.co.jp/)
+* **License**: Apache-2.0
+
+## Author
+
+[Ryosuke Ishigami](https://huggingface.co/rishigami)
+
+## How to cite
+
+```tex
+@misc{cyberagent-calm3-22b-chat,
+      title={cyberagent/calm3-22b-chat},
+      url={https://huggingface.co/cyberagent/calm3-22b-chat},
+      author={Ryosuke Ishigami},
+      year={2024},
+}
+```

config.json

@@ -0,0 +1,41 @@
+{
+    "_name_or_path": "calm3-22b-chat",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 0,
+    "eos_token_id": 65001,
+    "hidden_act": "silu",
+    "hidden_size": 6144,
+    "initializer_range": 0.02,
+    "intermediate_size": 16384,
+    "max_position_embeddings": 16384,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 48,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 48,
+    "pad_token_id": 1,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 1000000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.42.3",
+    "use_cache": true,
+    "vocab_size": 65024,
+    "quantization_config": {
+        "quant_method": "exl2",
+        "version": "0.1.6",
+        "bits": 5.0,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 115,
+            "length": 2048,
+            "dataset": "(default)"
+        }
+    }
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": 65001,
+  "pad_token_id": 1,
+  "transformers_version": "4.42.3"
+}

model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 45085765632
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00010-of-00010.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.norm.weight": "model-00010-of-00010.safetensors"
+  }
+}

output-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd2d6b6905f1a186d3898772c7ab4a8702add756c020e984c1908c9cedf1f65d
+size 8587234776

output-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:096c8c5dca934be0b2a94935f36eed93e992dc2fa7dcdd2b7553b842a9794f49
+size 6118146950

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|padding|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65001": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "65002": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}