Instructions to use lingadevaruhp/thoshan_Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use lingadevaruhp/thoshan_Flash with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-2-9b-it-bnb-4bit") model = PeftModel.from_pretrained(base_model, "lingadevaruhp/thoshan_Flash") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use lingadevaruhp/thoshan_Flash with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for lingadevaruhp/thoshan_Flash to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for lingadevaruhp/thoshan_Flash to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for lingadevaruhp/thoshan_Flash to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="lingadevaruhp/thoshan_Flash", max_seq_length=2048, )
Upload model trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- README.md +2 -0
- adapter_config.json +12 -3
README.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
---
|
| 2 |
base_model: unsloth/gemma-2-9b-it-bnb-4bit
|
| 3 |
library_name: peft
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
# Model Card for Model ID
|
|
|
|
| 1 |
---
|
| 2 |
base_model: unsloth/gemma-2-9b-it-bnb-4bit
|
| 3 |
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- unsloth
|
| 6 |
---
|
| 7 |
|
| 8 |
# Model Card for Model ID
|
adapter_config.json
CHANGED
|
@@ -1,9 +1,12 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"alpha_pattern": {},
|
|
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "unsloth/gemma-2-9b-it-bnb-4bit",
|
| 5 |
"bias": "none",
|
| 6 |
"corda_config": null,
|
|
|
|
| 7 |
"eva_config": null,
|
| 8 |
"exclude_modules": null,
|
| 9 |
"fan_in_fan_out": false,
|
|
@@ -16,24 +19,30 @@
|
|
| 16 |
"lora_alpha": 16,
|
| 17 |
"lora_bias": false,
|
| 18 |
"lora_dropout": 0,
|
|
|
|
| 19 |
"megatron_config": null,
|
| 20 |
"megatron_core": "megatron.core",
|
| 21 |
"modules_to_save": null,
|
| 22 |
"peft_type": "LORA",
|
|
|
|
|
|
|
| 23 |
"r": 16,
|
| 24 |
"rank_pattern": {},
|
| 25 |
"revision": null,
|
| 26 |
"target_modules": [
|
| 27 |
-
"k_proj",
|
| 28 |
"gate_proj",
|
| 29 |
"up_proj",
|
| 30 |
-
"
|
| 31 |
"v_proj",
|
|
|
|
| 32 |
"o_proj",
|
| 33 |
-
"
|
| 34 |
],
|
|
|
|
| 35 |
"task_type": "CAUSAL_LM",
|
| 36 |
"trainable_token_indices": null,
|
|
|
|
| 37 |
"use_dora": false,
|
|
|
|
| 38 |
"use_rslora": false
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
"auto_mapping": null,
|
| 6 |
"base_model_name_or_path": "unsloth/gemma-2-9b-it-bnb-4bit",
|
| 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,
|
|
|
|
| 19 |
"lora_alpha": 16,
|
| 20 |
"lora_bias": false,
|
| 21 |
"lora_dropout": 0,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
"megatron_config": null,
|
| 24 |
"megatron_core": "megatron.core",
|
| 25 |
"modules_to_save": null,
|
| 26 |
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
"r": 16,
|
| 30 |
"rank_pattern": {},
|
| 31 |
"revision": null,
|
| 32 |
"target_modules": [
|
|
|
|
| 33 |
"gate_proj",
|
| 34 |
"up_proj",
|
| 35 |
+
"k_proj",
|
| 36 |
"v_proj",
|
| 37 |
+
"down_proj",
|
| 38 |
"o_proj",
|
| 39 |
+
"q_proj"
|
| 40 |
],
|
| 41 |
+
"target_parameters": null,
|
| 42 |
"task_type": "CAUSAL_LM",
|
| 43 |
"trainable_token_indices": null,
|
| 44 |
+
"use_bdlora": null,
|
| 45 |
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
"use_rslora": false
|
| 48 |
}
|