Upload folder using huggingface_hub

README.md

@@ -0,0 +1,100 @@
+---
+license: other
+license_name: helpingai
+license_link: https://helpingai.co/license
+pipeline_tag: text-generation
+language:
+- en
+tags:
+- HelpingAI
+- Emotionally-Intelligent
+- EQ-focused
+- Conversational
+- SLM
+library_name: transformers
+---
+
+# HelpingAI3
+
+## Model Description
+
+**HelpingAI3** is an advanced language model developed to excel in emotionally intelligent conversations. Building upon the foundations of HelpingAI2.5, this model offers enhanced emotional understanding and contextual awareness.
+
+## Model Details
+
+- **Developed by**: HelpingAI
+- **Model type**: Decoder-only large language model
+- **Language**: English
+- **License**: [HelpingAI License](https://helpingai.co/license)
+
+## Training Data
+
+HelpingAI3 was trained on a diverse dataset comprising:
+
+- **Emotional Dialogues**: 15 million rows to enhance conversational intelligence.
+- **Therapeutic Exchanges**: 3 million rows aimed at providing advanced emotional support.
+- **Cultural Conversations**: 250,000 rows to improve global awareness.
+- **Crisis Response Scenarios**: 1 million rows to better handle emergency situations.
+
+## Training Procedure
+
+The model underwent the following training processes:
+
+- **Base Model**: Initiated from HelpingAI2.5.
+- **Emotional Intelligence Training**: Employed Reinforcement Learning for Emotion Understanding (RLEU) and context-aware conversational fine-tuning.
+- **Optimization**: Utilized mixed-precision training and advanced token efficiency techniques.
+
+## Intended Use
+
+HelpingAI3 is designed for:
+
+- **AI Companionship & Emotional Support**: Offering empathetic interactions.
+- **Therapy & Wellbeing Guidance**: Assisting in mental health support.
+- **Personalized Learning**: Tailoring educational content to individual needs.
+- **Professional AI Assistance**: Enhancing productivity in professional settings.
+
+## Limitations
+
+While HelpingAI3 strives for high emotional intelligence, users should be aware of potential limitations:
+
+- **Biases**: The model may inadvertently reflect biases present in the training data.
+- **Understanding Complex Emotions**: There might be challenges in accurately interpreting nuanced human emotions.
+- **Not a Substitute for Professional Help**: For serious emotional or psychological issues, consulting a qualified professional is recommended.
+
+## How to Use
+
+### Using Transformers
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# Load the HelpingAI3 model
+model = AutoModelForCausalLM.from_pretrained("HelpingAI/HAI3-RAW")
+# Load the tokenizer
+tokenizer = AutoTokenizer.from_pretrained("HelpingAI/HAI3-RAW")
+
+# Define the chat input
+chat = [
+    {"role": "system", "content": "You are HelpingAI, an emotional AI. Always answer my questions in the HelpingAI style."},
+    {"role": "user", "content": "Introduce yourself."}
+]
+
+inputs = tokenizer.apply_chat_template(
+    chat,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to(model.device)
+
+# Generate text
+outputs = model.generate(
+    inputs,
+    max_new_tokens=256,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
+)
+
+response = outputs[0][inputs.shape[-1]:]
+print(tokenizer.decode(response, skip_special_tokens=True))
+```

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "eos_token_id": 11,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 23040,
+  "max_position_embeddings": 32768,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 4,
+  "pad_token_id": 2023,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000042,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 11,
+  "max_length": 32768,
+  "pad_token_id": 2023,
+  "transformers_version": "4.49.0",
+  "use_cache": false
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5818f97ad6e9630038e64cdc124e8d6c1138ae77aaed3ef1b19e7638da60e4e
+size 4938900352

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95edf25de4cbe8a77fe8399bd5c7f4fff1c34b6db5efcafc6d03045468973e5a
+size 4942085064

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1839f5bae1fb9c50d61060e4c2ade0e23358cd0fd3f4bf21ef7864bbbe07bede
+size 4891740448

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:765a6fd5e723564eeee36d625534b3402bc24eca44eec62ae986b906edb35473
+size 4891740448

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b518b443b496a3000e665b073c6584f06e1e0813a6988b76d70bbd808f6615e
+size 946883112

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+    "metadata": {
+        "total_size": 20611307520
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00005-of-00005.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.norm.weight": "model-00005-of-00005.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|pad|>"
+}