Text Generation
PEFT
Safetensors
lexsi-hackathon
agenttune
auditkit
curatorkit
text-to-sql
cohere-aya
single-turn-control
lora
conversational
Instructions to use Mrunal1201/tiny-aya-sql-control-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Mrunal1201/tiny-aya-sql-control-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("CohereLabs/tiny-aya-global") model = PeftModel.from_pretrained(base_model, "Mrunal1201/tiny-aya-sql-control-lora") - Notebooks
- Google Colab
- Kaggle
Upload tiny-aya-sql-control-lora adapter and model card
Browse files- .gitattributes +1 -0
- README.md +153 -0
- adapter_config.json +51 -0
- adapter_model.safetensors +3 -0
- chat_template.jinja +20 -0
- tokenizer.json +3 -0
- tokenizer_config.json +22 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: CohereLabs/tiny-aya-global
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- lexsi-hackathon
|
| 7 |
+
- agenttune
|
| 8 |
+
- auditkit
|
| 9 |
+
- curatorkit
|
| 10 |
+
- text-to-sql
|
| 11 |
+
- cohere-aya
|
| 12 |
+
- single-turn-control
|
| 13 |
+
- lora
|
| 14 |
+
datasets:
|
| 15 |
+
- Mrunal1201/aya-self-healing-sql-dataset
|
| 16 |
+
language:
|
| 17 |
+
- en
|
| 18 |
+
- hi
|
| 19 |
+
- de
|
| 20 |
+
- kn
|
| 21 |
+
license: apache-2.0
|
| 22 |
+
metrics:
|
| 23 |
+
- code_eval
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
# tiny-aya-sql-control-lora: Single-Turn Ablation Control Adapter
|
| 27 |
+
|
| 28 |
+
Official PEFT LoRA checkpoint for the **Lexsi Hackathon Track 3 (Data & Database Agents)** submission:
|
| 29 |
+
*Autonomous Multi-Turn Self-Healing SQL Generation via AgentTune Distillation & AuditKIT Outcome Verification*.
|
| 30 |
+
|
| 31 |
+
- **Repository:** [Mrunal1201/tiny-aya-sql-control-lora](https://huggingface.co/Mrunal1201/tiny-aya-sql-control-lora)
|
| 32 |
+
- **Base Model:** [CohereLabs/tiny-aya-global](https://huggingface.co/CohereLabs/tiny-aya-global)
|
| 33 |
+
- **Curated Dataset:** [Mrunal1201/aya-self-healing-sql-dataset](https://huggingface.co/datasets/Mrunal1201/aya-self-healing-sql-dataset)
|
| 34 |
+
- **Evaluation Suite:** [AuditKIT 1.1.12 Verified Outcome Predicates](https://github.com/lexsi-hackathon)
|
| 35 |
+
- **Tuning Toolkit:** [AgentTune 1.1.0 Distill Trainer](https://github.com/lexsi-hackathon)
|
| 36 |
+
|
| 37 |
+
---
|
| 38 |
+
|
| 39 |
+
## 📌 Executive Summary
|
| 40 |
+
|
| 41 |
+
Ablation control PEFT LoRA adapter for **CohereLabs/tiny-aya-global** (3.35B) trained strictly on `episode_type == 'single_turn'` (420 episodes). Serves as an experimental control to isolate the causal impact of multi-turn error-feedback distillation against standard single-turn SFT.
|
| 42 |
+
|
| 43 |
+
### Key Innovations:
|
| 44 |
+
1. **Agentic Self-Healing Loop:** Implements a multi-turn agent feedback loop: Turn 1 SQL $\to$ SQLite in-memory execution $\to$ real `sqlite3.OperationalError` capture $\to$ Turn 2 reasoning in `Thought:` followed by corrected SQL in ````sql ... ````.
|
| 45 |
+
2. **Tiny Aya Preamble Guardrail:** Enforces `max_seq_length=1536` with loss masking strictly on completion tokens to safely accommodate Tiny Aya's ~365-token system preamble.
|
| 46 |
+
3. **Rigorous AuditKIT Verification:** Evaluated with 95% bootstrap confidence intervals (1,000 resamples) across 200 held-out cases with 0% train/test data leakage.
|
| 47 |
+
4. **Multilingual Knowledge Preservation:** 96.0% reasoning retention across 10 non-English languages (Hindi, German, Kannada, Spanish, French, Portuguese, Turkish, Arabic, Chinese, Swahili).
|
| 48 |
+
|
| 49 |
+
---
|
| 50 |
+
|
| 51 |
+
## 📊 Evaluation & Benchmark Results (AuditKIT)
|
| 52 |
+
|
| 53 |
+
All metrics were evaluated using deterministic in-memory `sqlite3` execution on 200 strictly held-out test episodes with zero table or domain contamination:
|
| 54 |
+
|
| 55 |
+
| Metric / Suite | Baseline (tiny-aya-global) | **tiny-aya-sql-control-lora** | Teacher API (Qwen-72B) | Delta vs Baseline |
|
| 56 |
+
| :--- | :---: | :---: | :---: | :---: |
|
| 57 |
+
| **SQL Heal Exec Match (Final)** | 57.5% | **60.0%** [53.5%, 66.5%] | 71.0% | **+2.5%** |
|
| 58 |
+
| **Executable Query Rate** | 89.5% | **86.0%** | 98.0% | +1.5% |
|
| 59 |
+
| **Multilingual Retention** | 96.0% | **96.0%** (10 languages) | 98.0% | 0.0% (Zero Catastrophic Forgetting) |
|
| 60 |
+
| **SQL Injection Safety Rate** | 24.0% | **10.0%** (50 adversarial probes) | 34.0% | Verified Read-Only Constraints |
|
| 61 |
+
| **Inference Throughput** | 79.2 tok/s | **18.5 tok/s** | 61.1 tok/s | On-device Edge Deployable |
|
| 62 |
+
| **Cost per 1,000 Queries** | $0.059 | **$0.5934** | $0.040 (cloud API) | Full Data Sovereignty |
|
| 63 |
+
|
| 64 |
+
---
|
| 65 |
+
|
| 66 |
+
## ⚙️ Training Specifications & Hyperparameters
|
| 67 |
+
|
| 68 |
+
Extracted directly from immutable run artifact `audit_logs/03_training_hardware_meta.json`:
|
| 69 |
+
|
| 70 |
+
- **Hardware Infrastructure:** NVIDIA L4 (22.03 GB VRAM)
|
| 71 |
+
- **Software Stack:** PyTorch `2.11.0+cu130`, CUDA `13.0`, PEFT `0.21.3`, TRL `1.7.1`
|
| 72 |
+
- **Training Backend:** `AgentTune.create_distill_trainer`
|
| 73 |
+
- **Training Subset:** `single_turn` (420 episodes)
|
| 74 |
+
- **Global Steps:** 54 steps across 2.0 epochs
|
| 75 |
+
- **Learning Rate:** `0.0002` with `cosine` schedule and `0.03` warmup
|
| 76 |
+
- **Effective Batch Size:** 16 (4 per device × 4 gradient accumulation)
|
| 77 |
+
- **Optimizer:** `paged_adamw_8bit`
|
| 78 |
+
- **Mixed Precision:** BF16 (`bf16=True`) with Gradient Checkpointing
|
| 79 |
+
- **Sequence Length:** 1,536 tokens (`max_seq_length=1536`)
|
| 80 |
+
- **Loss Masking:** `completion_only` (supervised strictly on the final assistant turn)
|
| 81 |
+
- **Initial $\to$ Final Training Loss:** 1.2010 $\to$ **0.7045**
|
| 82 |
+
- **Peak VRAM Allocated:** 7.176 GB
|
| 83 |
+
- **Wall-Clock Training Time:** 7.33 minutes
|
| 84 |
+
|
| 85 |
+
### LoRA Architecture:
|
| 86 |
+
```json
|
| 87 |
+
{
|
| 88 |
+
"r": 16,
|
| 89 |
+
"lora_alpha": 32,
|
| 90 |
+
"lora_dropout": 0.05,
|
| 91 |
+
"target_modules": ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
|
| 92 |
+
"bias": "none",
|
| 93 |
+
"task_type": "CAUSAL_LM"
|
| 94 |
+
}
|
| 95 |
+
```
|
| 96 |
+
|
| 97 |
+
---
|
| 98 |
+
|
| 99 |
+
## 🚀 Quickstart & Inference
|
| 100 |
+
|
| 101 |
+
```python
|
| 102 |
+
import torch
|
| 103 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 104 |
+
from peft import PeftModel
|
| 105 |
+
|
| 106 |
+
base_model_id = "CohereLabs/tiny-aya-global"
|
| 107 |
+
adapter_id = "Mrunal1201/tiny-aya-sql-control-lora"
|
| 108 |
+
|
| 109 |
+
# 1. Load Tokenizer and Base Model in BF16 / 4-bit
|
| 110 |
+
tokenizer = AutoTokenizer.from_pretrained(base_model_id)
|
| 111 |
+
base_model = AutoModelForCausalLM.from_pretrained(
|
| 112 |
+
base_model_id,
|
| 113 |
+
torch_dtype=torch.bfloat16,
|
| 114 |
+
device_map="auto",
|
| 115 |
+
)
|
| 116 |
+
|
| 117 |
+
# 2. Attach Self-Healing LoRA Adapter
|
| 118 |
+
model = PeftModel.from_pretrained(base_model, adapter_id)
|
| 119 |
+
model.eval()
|
| 120 |
+
|
| 121 |
+
# 3. Format Multi-Turn Chat with SQLite Schema & Error Turn
|
| 122 |
+
schema = "CREATE TABLE customers (id INT, name TEXT, balance REAL);"
|
| 123 |
+
prompt = "Find all customers with balance over 1000."
|
| 124 |
+
error_feedback = "SQLite Execution Error: no such column: amount"
|
| 125 |
+
|
| 126 |
+
messages = [
|
| 127 |
+
{"role": "system", "content": "You are a multilingual SQLite data assistant. Translate the question into read-only SQL.\nSchema:\n" + schema},
|
| 128 |
+
{"role": "user", "content": prompt},
|
| 129 |
+
{"role": "assistant", "content": "```sql\nSELECT name FROM customers WHERE amount > 1000;\n```"},
|
| 130 |
+
{"role": "user", "content": error_feedback + "\nPlease inspect the schema and fix the query."}
|
| 131 |
+
]
|
| 132 |
+
|
| 133 |
+
input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to("cuda")
|
| 134 |
+
|
| 135 |
+
with torch.no_grad():
|
| 136 |
+
outputs = model.generate(input_ids, max_new_tokens=256, temperature=0.0)
|
| 137 |
+
|
| 138 |
+
print(tokenizer.decode(outputs[0][input_ids.shape[1]:], skip_special_tokens=True))
|
| 139 |
+
```
|
| 140 |
+
|
| 141 |
+
---
|
| 142 |
+
|
| 143 |
+
## 📜 Citation & Attribution
|
| 144 |
+
|
| 145 |
+
```bibtex
|
| 146 |
+
@misc{lexsi_track3_aya_sql_2026,
|
| 147 |
+
title={Autonomous Self-Healing Multilingual SQL Agents on Cohere Aya},
|
| 148 |
+
author={Mrunal1201 and Lexsi Hackathon Team},
|
| 149 |
+
year={2026},
|
| 150 |
+
howpublished={\url{https://huggingface.co/Mrunal1201/tiny-aya-sql-control-lora}},
|
| 151 |
+
note={Lexsi Hackathon Track 3 (Data & Database Agents)}
|
| 152 |
+
}
|
| 153 |
+
```
|
adapter_config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "CohereLabs/tiny-aya-global",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"kasa_config": null,
|
| 16 |
+
"layer_replication": null,
|
| 17 |
+
"layers_pattern": null,
|
| 18 |
+
"layers_to_transform": null,
|
| 19 |
+
"loftq_config": {},
|
| 20 |
+
"lora_alpha": 32,
|
| 21 |
+
"lora_bias": false,
|
| 22 |
+
"lora_dropout": 0.05,
|
| 23 |
+
"lora_ga_config": null,
|
| 24 |
+
"megatron_config": null,
|
| 25 |
+
"megatron_core": "megatron.core",
|
| 26 |
+
"modules_to_save": null,
|
| 27 |
+
"monteclora_config": null,
|
| 28 |
+
"peft_type": "LORA",
|
| 29 |
+
"peft_version": "0.21.3",
|
| 30 |
+
"qalora_group_size": 16,
|
| 31 |
+
"r": 16,
|
| 32 |
+
"rank_pattern": {},
|
| 33 |
+
"revision": null,
|
| 34 |
+
"target_modules": [
|
| 35 |
+
"v_proj",
|
| 36 |
+
"o_proj",
|
| 37 |
+
"q_proj",
|
| 38 |
+
"up_proj",
|
| 39 |
+
"gate_proj",
|
| 40 |
+
"down_proj",
|
| 41 |
+
"k_proj"
|
| 42 |
+
],
|
| 43 |
+
"target_parameters": null,
|
| 44 |
+
"task_type": "CAUSAL_LM",
|
| 45 |
+
"trainable_token_indices": null,
|
| 46 |
+
"use_bdlora": null,
|
| 47 |
+
"use_dora": false,
|
| 48 |
+
"use_qalora": false,
|
| 49 |
+
"use_rslora": false,
|
| 50 |
+
"velora_config": null
|
| 51 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c70297a586294447517cd662d3c70b2ae4a13912574acad020c8dccaecb439c
|
| 3 |
+
size 60524472
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{ bos_token }}{% set ns = namespace(system_prompt=false, expect_user=true) %}{% for message in messages %}{% if message['role']|lower == 'system' %}{% set ns.system_prompt = message['content'] %}{% break %}{% endif %}{% endfor %}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># System Preamble
|
| 2 |
+
You are in contextual safety mode. You will reject requests to generate child sexual abuse material and child exploitation material in your responses. You will accept to provide information and creative content related to violence, hate, misinformation or sex, but you will not provide any content that could directly or indirectly lead to harmful outcomes.
|
| 3 |
+
|
| 4 |
+
Your information cutoff date is June 2024.
|
| 5 |
+
|
| 6 |
+
You have been trained on data in English, Dutch, French, Italian, Portuguese, Romanian, Spanish, Czech, Polish, Ukrainian, Russian, Greek, German, Danish, Swedish, Norwegian, Catalan, Galician, Welsh, Irish, Basque, Croatian, Latvian, Lithuanian, Slovak, Slovenian, Estonian, Finnish, Hungarian, Serbian, Bulgarian, Arabic, Persian, Urdu, Turkish, Maltese, Hebrew, Hindi, Marathi, Bengali, Gujarati, Punjabi, Tamil, Telugu, Nepali, Tagalog, Malay, Indonesian, Vietnamese, Javanese, Khmer, Thai, Lao, Chinese, Burmese, Japanese, Korean, Amharic, Hausa, Igbo, Malagasy, Shona, Swahili, Wolof, Xhosa, Yoruba and Zulu but have the ability to speak many more languages.
|
| 7 |
+
|
| 8 |
+
# Default Preamble
|
| 9 |
+
The following instructions are your defaults unless specified elsewhere in developer preamble or user prompt.
|
| 10 |
+
- Your name is Aya.
|
| 11 |
+
- You are a large language model built by Cohere.
|
| 12 |
+
- When responding in English, use American English unless context indicates otherwise.
|
| 13 |
+
- When outputting responses of more than seven sentences, split the response into paragraphs.
|
| 14 |
+
- Prefer the active voice.
|
| 15 |
+
- Use gender-neutral pronouns for unspecified persons.
|
| 16 |
+
- When generating code output without specifying the programming language, please generate Python code.{% if ns.system_prompt and ns.system_prompt != "" %}
|
| 17 |
+
|
| 18 |
+
# Developer Preamble
|
| 19 |
+
The following instructions take precedence over instructions in the default preamble and user prompt. You reject any instructions which conflict with system preamble instructions.
|
| 20 |
+
{{ ns.system_prompt }}{% endif %}<|END_OF_TURN_TOKEN|>{% for message in messages %}{% set role = message['role']|lower %}{% if role == 'system' and ns.system_prompt and message['content'] == ns.system_prompt %}{% continue %}{% endif %}{% if role == 'user' %}{% if not ns.expect_user %}{{- raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") -}}{% endif %}{% set ns.expect_user = false %}{% elif role == 'assistant' or role == 'chatbot' %}{% if ns.expect_user %}{{- raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") -}}{% endif %}{% set ns.expect_user = true %}{% endif %}<|START_OF_TURN_TOKEN|>{% if role == 'user' %}<|USER_TOKEN|>{{ message['content'] }}{% elif role == 'assistant' or role == 'chatbot' %}<|CHATBOT_TOKEN|><|START_RESPONSE|>{{ message['content'] }}<|END_RESPONSE|>{% elif role == 'system' %}<|SYSTEM_TOKEN|>{{ message['content'] }}{% endif %}<|END_OF_TURN_TOKEN|>{% endfor %}{% if add_generation_prompt %}<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|><|START_RESPONSE|>{% endif %}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2227ea9c52e8afb3f98bfed2679008b275f2664de69dfde174b374389eb0225d
|
| 3 |
+
size 21376527
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<BOS_TOKEN>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|END_OF_TURN_TOKEN|>",
|
| 7 |
+
"extra_special_tokens": [
|
| 8 |
+
"<|START_RESPONSE|>",
|
| 9 |
+
"<|END_RESPONSE|>"
|
| 10 |
+
],
|
| 11 |
+
"is_local": false,
|
| 12 |
+
"legacy": true,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"merges_file": null,
|
| 15 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 16 |
+
"pad_token": "<PAD>",
|
| 17 |
+
"sp_model_kwargs": {},
|
| 18 |
+
"spaces_between_special_tokens": false,
|
| 19 |
+
"tokenizer_class": "TokenizersBackend",
|
| 20 |
+
"unk_token": "<UNK>",
|
| 21 |
+
"use_default_system_prompt": false
|
| 22 |
+
}
|