Upload model

README.md

@@ -0,0 +1,28 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: gptq
+- bits: 8
+- tokenizer: None
+- dataset: None
+- group_size: 32
+- damp_percent: 0.1
+- desc_act: True
+- sym: True
+- true_sequential: True
+- use_cuda_fp16: False
+- model_seqlen: 4096
+- block_name_to_quantize: model.layers
+- module_name_preceding_first_block: ['model.embed_tokens']
+- batch_size: 1
+- pad_token_id: None
+- disable_exllama: True
+- max_input_length: None
+### Framework versions
+
+
+- PEFT 0.5.0

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "TheBloke/zephyr-7B-beta-GPTQ",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb45b0e39fc1e82f20fb661a914f5951451557ee03efd76add36aff361041aad
+size 27308941