NotoriousH2/test2_solar_10.7b_v1.0

README.md

@@ -1,8 +1,9 @@
 ---
-license: cc-by-nc-4.0
-base_model: 42dot/42dot_LLM-SFT-1.3B
+license: apache-2.0
+library_name: peft
 tags:
 - generated_from_trainer
+base_model: upstage/SOLAR-10.7B-v1.0
 model-index:
 - name: outputs
   results: []
@@ -13,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # outputs
 
-This model is a fine-tuned version of [42dot/42dot_LLM-SFT-1.3B](https://huggingface.co/42dot/42dot_LLM-SFT-1.3B) on an unknown dataset.
+This model is a fine-tuned version of [upstage/SOLAR-10.7B-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-v1.0) on an unknown dataset.
 
 ## Model description
 
@@ -33,7 +34,7 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 32
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -42,9 +43,14 @@ The following hyperparameters were used during training:
 - num_epochs: 3
 - mixed_precision_training: Native AMP
 
+### Training results
+
+
+
 ### Framework versions
 
+- PEFT 0.7.2.dev0
 - Transformers 4.37.0.dev0
 - Pytorch 2.1.2+cu121
 - Datasets 2.16.0
-- Tokenizers 0.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "upstage/SOLAR-10.7B-v1.0",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af498c0deb32a47c7a6da0d82ef437b39e6b1874b3ac50f64ee04e5cd9c43b58
+size 125918320

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:675b34ba787799ca256cd1985d3a70d5b56a1ba36e5440852835755e8cd5ce88
+oid sha256:01feefb0db9ce6eac49ccb0845e04d9503e5977a0b8e85a998fa4c9671e90e5a
 size 4664