Upload model weights (en_ru v3, step-133500)

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": null,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 13312,
+  "max_position_embeddings": 131072,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 16.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "use_cache": true,
+  "vocab_size": 65536
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab9d219663df8dc4120958fcd489bcf7972e66ac684b764ced9dedcc3ac89e95
+size 12583408728

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "bos_token": null,
+  "eos_token": "<|endoftext|>",
+  "unk_token": null,
+  "pad_token": null,
+  "clean_up_tokenization_spaces": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}