Upload model

README.md

@@ -1,6 +1,6 @@
 ---
 library_name: peft
-base_model: alexsherstinsky/Mistral-7B-v0.1-sharded
+base_model: mistralai/Mistral-7B-v0.1
 ---
 
 # Model Card for Model ID
@@ -210,7 +210,7 @@ The following `bitsandbytes` quantization config was used during training:
 - 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_use_double_quant: False
 - bnb_4bit_compute_dtype: bfloat16
 
 ### Framework versions
@@ -229,7 +229,7 @@ The following `bitsandbytes` quantization config was used during training:
 - 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_use_double_quant: False
 - bnb_4bit_compute_dtype: bfloat16
 
 ### Framework versions

adapter_config.json

@@ -1,28 +1,26 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "alexsherstinsky/Mistral-7B-v0.1-sharded",
+  "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,
-  "lora_alpha": 64,
+  "lora_alpha": 16,
   "lora_dropout": 0.1,
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "v_proj",
     "q_proj",
-    "down_proj",
-    "o_proj",
     "k_proj",
-    "gate_proj"
+    "gate_proj",
+    "o_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c894f0b250e8fdc1f07107f8ab34c6b41367e833c268f3c640b0baeea05f89bc
-size 167832240
+oid sha256:0c7bf244e71561a3d7fa1285d7487ae4a9963be6f57b8f3af5e9ff3ec3b4ad90
+size 369142184