Upload 3 files

README.md

@@ -1,3 +1,73 @@
 ---
-license: apache-2.0
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
 ---
+
+# Model Card for Model ID
+
+Trained with [Ludwig.ai](https://ludwig.ai) and [Prdibase](https://predibase.com)!
+
+Given a passage from a news report generates a headline.
+
+Trained on: https://huggingface.co/datasets/JulesBelveze/tldr_news
+
+
+
+## Model Details
+
+### Model Description
+
+Ludwig config (v0.9.3):
+
+```yaml
+model_type: llm
+input_features:
+  - name: prompt
+    type: text
+    preprocessing:
+      max_sequence_length: null
+    column: prompt
+output_features:
+  - name: headline
+    type: text
+    preprocessing:
+      max_sequence_length: null
+    column: headline
+prompt:
+  template: >-
+    The following passage is content from a news report. Please summarize this
+    passage in one sentence or less.
+
+
+    Passage: {content}
+
+
+    Summary: 
+preprocessing:
+  split:
+    type: fixed
+    column: split
+  global_max_sequence_length: 2048
+adapter:
+  type: lora
+generation:
+  max_new_tokens: 64
+trainer:
+  type: finetune
+  epochs: 3
+  optimizer:
+    type: paged_adam
+  batch_size: 1
+  eval_steps: 100
+  learning_rate: 0.0002
+  eval_batch_size: 2
+  steps_per_checkpoint: 1000
+  learning_rate_scheduler:
+    decay: cosine
+    warmup_fraction: 0.03
+  gradient_accumulation_steps: 16
+  enable_gradient_checkpointing: true
+base_model: mistralai/Mistral-7B-v0.1
+quantization:
+  bits: 4
+```

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "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": 16,
+  "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": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1bb49c6636b54f10d6c7676dbb8ec96897cf6c283d49a17f5ea89585c248972
+size 13648432