Upload model

README.md

@@ -1,6 +1,6 @@
 ---
 library_name: peft
-base_model: google/flan-t5-large
+base_model: meta-llama/Llama-2-7b-chat-hf
 ---
 
 # Model Card for Model ID
@@ -18,6 +18,7 @@ base_model: google/flan-t5-large
 
 
 - **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
 - **Shared by [optional]:** [More Information Needed]
 - **Model type:** [More Information Needed]
 - **Language(s) (NLP):** [More Information Needed]
@@ -76,7 +77,7 @@ Use the code below to get started with the model.
 
 ### Training Data
 
-<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 
 [More Information Needed]
 
@@ -107,7 +108,7 @@ Use the code below to get started with the model.
 
 #### Testing Data
 
-<!-- This should link to a Data Card if possible. -->
+<!-- This should link to a Dataset Card if possible. -->
 
 [More Information Needed]
 
@@ -200,20 +201,18 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Training procedure
 
-
 The following `bitsandbytes` quantization config was used during training:
 - quant_method: bitsandbytes
-- load_in_8bit: True
-- load_in_4bit: False
+- 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_quant_type: nf4
 - bnb_4bit_use_double_quant: False
-- bnb_4bit_compute_dtype: float32
+- bnb_4bit_compute_dtype: bfloat16
 
 ### Framework versions
 
-
-- PEFT 0.6.0.dev0
+- PEFT 0.7.0

adapter_config.json

@@ -1,23 +1,31 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/flan-t5-large",
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "lora_alpha": 32,
+  "loftq_config": {},
+  "lora_alpha": 16,
   "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q",
-    "v"
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj"
   ],
-  "task_type": "SEQ_2_SEQ_LM"
+  "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25b277708658e3250ef9a3759cc97230aa54da5adddd42cfc5b9e5c815de4ec1
+size 80013120