Upload 11 files

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "Qwen/Qwen-1_8B",
+  "architectures": [
+    "QWenLMHeadModel"
+  ],
+  "attn_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "Qwen/Qwen-1_8B--configuration_qwen.QWenConfig",
+    "AutoModelForCausalLM": "Qwen/Qwen-1_8B--modeling_qwen.QWenLMHeadModel"
+  },
+  "bf16": false,
+  "emb_dropout_prob": 0.0,
+  "fp16": true,
+  "fp32": false,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "kv_channels": 128,
+  "layer_norm_epsilon": 1e-06,
+  "max_position_embeddings": 8192,
+  "model_type": "qwen",
+  "no_bias": true,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "onnx_safe": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "scale_attn_weights": true,
+  "seq_length": 8192,
+  "softmax_in_fp32": false,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "QWenTokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "use_cache_kernel": false,
+  "use_cache_quantization": false,
+  "use_dynamic_ntk": true,
+  "use_flash_attn": true,
+  "use_logn_attn": true,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "chat_format": "raw",
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 512,
+  "pad_token_id": 151643,
+  "stop_words_ids": [
+    [
+      151643
+    ]
+  ],
+  "top_k": 0,
+  "top_p": 0.8,
+  "transformers_version": "4.36.2"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0a434d1a592f514aff0be4eddb11c4b36442b42840c02294b97ccb4e5f03860
+size 3681638330

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf9897ba27c7c7d4a55efbb3698596b160ee9bc296b1cb6c783c43951c901cf
+size 3673721686

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ee9b73399c28d7e668360bf1d5a4d11095c4738bf96c13f7bb6fbff59f8ccb
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1babb7a93eb5f3c171480f0b9a80f018c4133ee1db662f766dcce90c39b80b4
+size 1064

special_tokens_map.json

@@ -0,0 +1,3 @@
+{
+  "pad_token": "<|extra_0|>"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "added_tokens_decoder": {},
+  "auto_map": {
+    "AutoTokenizer": [
+      "Qwen/Qwen-1_8B--tokenization_qwen.QWenTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 8192,
+  "pad_token": "<|extra_0|>",
+  "padding_side": "left",
+  "tokenizer_class": "QWenTokenizer"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20175d1d3513589ebd8d2222e189aa71eb446646638da40057b5ed5b444f5a53
+size 4728