Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "NousResearch/llama-2-7b-chat-hf",
+  "_name_or_path": "Droidfanat/llama-2-7b-custom-russian",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -16,6 +16,17 @@
   "num_key_value_heads": 32,
   "pad_token_id": 0,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "tie_word_embeddings": false,

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef39ada52a5e74a9302d871c6a25b4baf6165b31f97680ef7e14c5d311e54754
+size 7006454217