tools

README.md

@@ -1,75 +1,3 @@
----
-license: apache-2.0
-language:
-- en
-library_name: transformers
-pipeline_tag: text-generation
-tags:
-- Vidyut
-- Rapnss
----
-
-# *First Indian text-generation llm model with 7.24B parameters*
-VIA-01 by Rapnss
-VIA-01 is a state-of-the-art language model crafted by Rapnss, designed for exceptional performance in conversational tasks and code generation. Engineered for speed and versatility, VIA-01 delivers precise, high-quality responses across diverse applications, from answering complex questions to generating efficient code snippets.
-Features
-
-Dual-Purpose Excellence: Seamlessly blends natural language understanding with robust code generation, ideal for developers and conversational AI use cases.
-Optimized Performance: Lightweight design ensures fast inference, even in resource-constrained environments.
-Easy Integration: Compatible with Hugging Face Transformers for straightforward deployment.
-Rapnss Innovation: A unique AI built to inspire creativity and productivity.
-
-Usage
-Get started with VIA-01 using the following Python code:
-```python
-from transformers import pipeline
-import torch
-
-# Initialize the pipeline
-
-pipe = pipeline(
-    "text-generation",
-    model="rapnss/VIA-01",
-    torch_dtype=torch.float16,
-    device_map="auto",
-    max_new_tokens=15
-)
-
-# Generate a response
-prompt = "Write a Python function to sort a list:"
-response = pipe(prompt)[0]['generated_text']
-print(response)
-```
-Example Output:
-```
-Write a Python function to sort a list:
-
-def sort_list(arr):
-    return sorted(arr)
-
-```
-```
-## Installation
-Install required dependencies:
-```bash
-pip install transformers torch accelerate gradio
-```
-# Performance
-
-Inference Speed: Optimized for low-latency responses, typically ~20-40 seconds on standard CPU hardware (e.g., Hugging Face free Space). For sub-10-second responses, use a GPU-enabled environment (e.g., Hugging Face Pro Space).
-Model Size: ~8GB, balanced for efficiency and performance.
-Capabilities: Excels in conversational queries, technical problem-solving, and code generation tasks like writing functions or debugging snippets.
-
-# Try It Out
-Interact with VIA-01 via our Hugging Face Space, featuring a Gradio interface for real-time testing.
-Limitations
-
-Response Length: Short responses (up to 15 tokens) recommended for optimal speed on free-tier hosting.
-Hardware: CPU-based inference may be slower than GPU; performance varies with deployment setup.
-
-# License
-Licensed under the Apache 2.0 License, enabling flexible use and redistribution.
-Contact
-Created by Rapnss. For inquiries or feedback, reach out via Hugging Face or the VIA-01 Space.
-
-Made with ❤️ by Rapnss.
+---
+license: mit
+---

config.json

@@ -1,25 +0,0 @@
-{
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "hidden_act": "silu",
-  "hidden_size": 4096,
-  "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 32768,
-  "model_type": "mistral",
-  "architecture_name": "Vidyut",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
-  "rms_norm_eps": 1e-05,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float16",
-  "transformers_version": "4.36.0",
-  "use_cache": true,
-  "vocab_size": 32000,
-  "_name_or_path": "rapnss/VIA-1",
-  "xai_artifact_id": "0da495d6-6324-4798-ba57-b343611a0231"
-}

generation_config.json

@@ -1,6 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "transformers_version": "4.36.0"
-}

model-00001-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:63654d601820b88b1fa8b4a98df5714f700fbc5b3df2cc4ecbabdced35096d31
-size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a42716540ecb2385d371f2109835921ff535406cac8fe8ff28f2f0b5fc7895bd
-size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5f86e15cb3ed9078e30ae6e72445e109d0e337d9cde59b9aeea4ce8e44e54a5d
-size 4540516344

model.py

@@ -0,0 +1,7 @@
+from model_loader import route_query
+
+def infer(prompt: str) -> str:
+    """
+    Main interface that Hugging Face Hub uses.
+    """
+    return route_query(prompt)

model.safetensors.index.json

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

model_loader.py

@@ -0,0 +1,24 @@
+from tools.code_generator import generate_code
+from tools.web_search import search_web
+from tools.rag_engine import answer_from_docs
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Default general model (TinyLlama)
+tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+model.eval()
+
+def route_query(prompt):
+    prompt_lower = prompt.lower()
+
+    if "code:" in prompt_lower:
+        return generate_code(prompt)
+    elif "search:" in prompt_lower:
+        return search_web(prompt)
+    elif "doc:" in prompt_lower:
+        return answer_from_docs(prompt)
+    else:
+        inputs = tokenizer(prompt, return_tensors="pt")
+        outputs = model.generate(**inputs, max_new_tokens=200)
+        return tokenizer.decode(outputs[0], skip_special_tokens=True)

pytorch_model-00001-of-00003.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d8836f675fe1c4c43f3ff4e93f4cc0e97ef7a13e8c240fb39ad02d37ff303ef5
-size 4943184288

pytorch_model-00002-of-00003.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:58a7ddffb463397de5dbe1f1e2ec1ccf6aae2b549565f83f3ded124e0b4c5069
-size 4999843272

pytorch_model-00003-of-00003.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:75824d68dcf82d02b731b2bdfd3a9711acb7c58b8d566f4c0d3e9efac52f9a21
-size 5064824210

pytorch_model.bin.index.json

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

special_tokens_map.json

@@ -1,23 +0,0 @@
-{
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

tokenizer.model

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

tokenizer_config.json

@@ -1,46 +0,0 @@
-{
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": null,
-  "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [],
-  "bos_token": "<s>",
-  "chat_template": "{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set loop_messages = messages[1:] %}\n{%- else %}\n    {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n    {%- endif %}\n    {%- if message['role'] == 'user' %}\n        {%- if loop.first and system_message is defined %}\n            {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n        {%- else %}\n            {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n        {%- endif %}\n    {%- elif message['role'] == 'assistant' %}\n        {{- ' ' + message['content'] + eos_token}}\n    {%- else %}\n        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n    {%- endif %}\n{%- endfor %}\n",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": false,
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
-  "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false,
-  "name_or_path": "rapnss/VIA-1",
-  "model": "VIA-1 by Rapnss"
-}