Upload 8 files

README.md

@@ -1,3 +1,127 @@
----
-license: bsl-1.0
----
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: gptq
+- bits: 4
+- tokenizer: None
+- dataset: None
+- group_size: 128
+- damp_percent: 0.01
+- desc_act: False
+- sym: True
+- true_sequential: True
+- use_cuda_fp16: True
+- model_seqlen: None
+- block_name_to_quantize: None
+- module_name_preceding_first_block: None
+- batch_size: 1
+- pad_token_id: None
+- disable_exllama: True
+- max_input_length: None
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: gptq
+- bits: 4
+- tokenizer: None
+- dataset: None
+- group_size: 128
+- damp_percent: 0.01
+- desc_act: False
+- sym: True
+- true_sequential: True
+- use_cuda_fp16: True
+- model_seqlen: None
+- block_name_to_quantize: None
+- module_name_preceding_first_block: None
+- batch_size: 1
+- pad_token_id: None
+- disable_exllama: True
+- max_input_length: None
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: gptq
+- bits: 4
+- tokenizer: None
+- dataset: None
+- group_size: 128
+- damp_percent: 0.01
+- desc_act: False
+- sym: True
+- true_sequential: True
+- use_cuda_fp16: False
+- model_seqlen: None
+- block_name_to_quantize: None
+- module_name_preceding_first_block: None
+- batch_size: 1
+- pad_token_id: None
+- disable_exllama: True
+- max_input_length: None
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: gptq
+- bits: 4
+- tokenizer: None
+- dataset: None
+- group_size: 128
+- damp_percent: 0.01
+- desc_act: False
+- sym: True
+- true_sequential: True
+- use_cuda_fp16: False
+- model_seqlen: None
+- block_name_to_quantize: None
+- module_name_preceding_first_block: None
+- batch_size: 1
+- pad_token_id: None
+- disable_exllama: True
+- max_input_length: None
+### Framework versions
+
+- PEFT 0.5.0
+- PEFT 0.5.0
+- PEFT 0.5.0
+- PEFT 0.5.0
+- PEFT 0.5.0
+- PEFT 0.5.0
+
+- PEFT 0.5.0

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "TheBloke/Llama-2-7b-Chat-GPTQ",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95781923a08d526874f18bd5f7b416c19cde823229519b774d9532dba99260b4
+size 33646858

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}