Instructions to use Devique/Calmiq-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Devique/Calmiq-lora with PEFT:
Task type is invalid.
- Transformers
How to use Devique/Calmiq-lora with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Devique/Calmiq-lora", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use Devique/Calmiq-lora 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 Devique/Calmiq-lora 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 Devique/Calmiq-lora to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Devique/Calmiq-lora to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Devique/Calmiq-lora", max_seq_length=2048, )
Upload LoRA adapters and tokenizer after fine-tuning
Browse files- README.md +1 -0
- adapter_config.json +6 -2
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -207,4 +207,5 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 207 |
[More Information Needed]
|
| 208 |
### Framework versions
|
| 209 |
|
|
|
|
| 210 |
- PEFT 0.16.0
|
|
|
|
| 207 |
[More Information Needed]
|
| 208 |
### Framework versions
|
| 209 |
|
| 210 |
+
- PEFT 0.17.0
|
| 211 |
- PEFT 0.16.0
|
adapter_config.json
CHANGED
|
@@ -1,6 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
-
"auto_mapping":
|
|
|
|
|
|
|
|
|
|
| 4 |
"base_model_name_or_path": "unsloth/gemma-3n-e4b-it-unsloth-bnb-4bit",
|
| 5 |
"bias": "none",
|
| 6 |
"corda_config": null,
|
|
@@ -25,7 +28,8 @@
|
|
| 25 |
"rank_pattern": {},
|
| 26 |
"revision": null,
|
| 27 |
"target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|correction_coefs|prediction_coefs|modality_router|linear_left|linear_right|per_layer_input_gate|per_layer_projection|0|1|2|ffw_layer_1|ffw_layer_2|pos_proj|post|linear_start|linear_end|embedding_projection).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|correction_coefs|prediction_coefs|modality_router|linear_left|linear_right|per_layer_input_gate|per_layer_projection|0|1|2|ffw_layer_1|ffw_layer_2|pos_proj|post|linear_start|linear_end|embedding_projection)))",
|
| 28 |
-
"
|
|
|
|
| 29 |
"trainable_token_indices": null,
|
| 30 |
"use_dora": false,
|
| 31 |
"use_qalora": false,
|
|
|
|
| 1 |
{
|
| 2 |
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "Gemma3nForConditionalGeneration",
|
| 5 |
+
"parent_library": "transformers.models.gemma3n.modeling_gemma3n"
|
| 6 |
+
},
|
| 7 |
"base_model_name_or_path": "unsloth/gemma-3n-e4b-it-unsloth-bnb-4bit",
|
| 8 |
"bias": "none",
|
| 9 |
"corda_config": null,
|
|
|
|
| 28 |
"rank_pattern": {},
|
| 29 |
"revision": null,
|
| 30 |
"target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|correction_coefs|prediction_coefs|modality_router|linear_left|linear_right|per_layer_input_gate|per_layer_projection|0|1|2|ffw_layer_1|ffw_layer_2|pos_proj|post|linear_start|linear_end|embedding_projection).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj|correction_coefs|prediction_coefs|modality_router|linear_left|linear_right|per_layer_input_gate|per_layer_projection|0|1|2|ffw_layer_1|ffw_layer_2|pos_proj|post|linear_start|linear_end|embedding_projection)))",
|
| 31 |
+
"target_parameters": null,
|
| 32 |
+
"task_type": null,
|
| 33 |
"trainable_token_indices": null,
|
| 34 |
"use_dora": false,
|
| 35 |
"use_qalora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 76913008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c854bf35b67bcb829053eb11fae4c6dd965384da382ece2a0f1d83858ed7a74b
|
| 3 |
size 76913008
|