Upload model

README.md

@@ -199,6 +199,41 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 
 
+## Training procedure
+
+
+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: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
+### Framework versions
+
+
+- PEFT 0.6.2
+## Training procedure
+
+
+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: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+
 ### Framework versions
 
-- PEFT 0.7.2.dev0
+
+- PEFT 0.6.2

adapter_config.json

@@ -1,31 +1,17 @@
 {
-  "alpha_pattern": {},
   "auto_mapping": null,
   "base_model_name_or_path": "deepseek-ai/deepseek-coder-1.3b-instruct",
-  "bias": "none",
-  "fan_in_fan_out": false,
+  "encoder_dropout": 0.0,
+  "encoder_hidden_size": 250,
+  "encoder_num_layers": 2,
+  "encoder_reparameterization_type": "MLP",
   "inference_mode": true,
-  "init_lora_weights": true,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 128,
-  "lora_dropout": 0.1,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 64,
-  "rank_pattern": {},
+  "num_attention_heads": 16,
+  "num_layers": 24,
+  "num_transformer_submodules": 1,
+  "num_virtual_tokens": 50,
+  "peft_type": "P_TUNING",
   "revision": null,
-  "target_modules": [
-    "up_proj",
-    "k_proj",
-    "gate_proj",
-    "q_proj",
-    "down_proj",
-    "v_proj"
-  ],
   "task_type": "CAUSAL_LM",
-  "use_rslora": false
+  "token_dim": 2048
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55ea4013ae1aa6d2396b15bfbb8779f41752fb078446ebfd2094474cc00adf3a
-size 214734488
+oid sha256:79acdcc1b8e57db310c2b04aab07db81dd60615a67b42d7a105b2b40f171d1e8
+size 409720