Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- BASE_MODEL.txt +1 -0
- README.md +25 -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
- training_args.bin +3 -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
|
BASE_MODEL.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
CohereLabs/tiny-aya-global
|
README.md
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-nc-4.0
|
| 3 |
+
base_model: CohereLabs/tiny-aya-global
|
| 4 |
+
tags:
|
| 5 |
+
- lexsi-hackathon
|
| 6 |
+
- track-3
|
| 7 |
+
- lora
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Lexsi DataAgent — Tiny Aya LoRA (Track 3, Statement 6)
|
| 11 |
+
|
| 12 |
+
LoRA adapter (r=16) fine-tuned on 26 verified question-to-SQL examples for a
|
| 13 |
+
read-only business-data agent (synthetic SQLite shop database: 5 customers,
|
| 14 |
+
4 products, 10 orders). The adapter teaches Tiny Aya Global to emit a single
|
| 15 |
+
read-only SELECT for six narrow question patterns (revenue by product, top
|
| 16 |
+
customer, order counts by status, average order value, revenue in a date
|
| 17 |
+
range, orders for a customer).
|
| 18 |
+
|
| 19 |
+
Training data: `umarshareef0165/lexsi-dataagent-sft` (every example's SQL was
|
| 20 |
+
executed against the seed database and verified before training). Evaluation:
|
| 21 |
+
12 held-out task questions (exact eval questions never appear in training),
|
| 22 |
+
base vs LoRA, scored by executing the generated SQL and checking the answer
|
| 23 |
+
— see `lexsi-dataagent-model-eval.json` in the dataset repo and the
|
| 24 |
+
write-up. This is a prototype-scale adapter (26 examples); it is not a
|
| 25 |
+
general text-to-SQL model, and that limit is stated in the write-up.
|
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": "0.21.2",
|
| 30 |
+
"qalora_group_size": 16,
|
| 31 |
+
"r": 16,
|
| 32 |
+
"rank_pattern": {},
|
| 33 |
+
"revision": null,
|
| 34 |
+
"target_modules": [
|
| 35 |
+
"up_proj",
|
| 36 |
+
"q_proj",
|
| 37 |
+
"o_proj",
|
| 38 |
+
"gate_proj",
|
| 39 |
+
"k_proj",
|
| 40 |
+
"down_proj",
|
| 41 |
+
"v_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 sha256:2dfac76434eca62b7faa9ac8d7336738b9aaaf289e1bad9e2451b2d0276d43b3
|
| 3 |
+
size 120981200
|
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:d80fa65cdce1ebb9e13b3de476d58ef60fde9533f0cacec1d758c59bba0447a2
|
| 3 |
+
size 21376625
|
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 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80d866ece3f7970f71bfac54c9373aa9c8df7b88fe89af526363424f6c9964ca
|
| 3 |
+
size 5457
|