Upload files

README.md

@@ -0,0 +1,53 @@
+---
+license: cc-by-nc-sa-4.0
+language:
+- ko
+- zh
+---
+基于[Qwen1.5-14B-Chat](https://huggingface.co/Qwen/Qwen1.5-14B-Chat)，在韩文轻小说翻译数据上微调（包含454本日轻的韩翻和中翻对照以及14本韩轻的中翻）
+
+模型仅支持韩文→简体中文的翻译
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers.generation import GenerationConfig
+
+model_path = 'CjangCjengh/LN-Korean-14B-v0.1'
+tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_path, device_map='auto', trust_remote_code=True).eval()
+model.generation_config = GenerationConfig.from_pretrained(model_path, trust_remote_code=True)
+
+# 段落之间用\n分隔
+text = '''여자애들이 자신들의 첫 경험에 대한 이야기를 하는 걸 들은 적이 있는가.
+물론 여기서 첫 경험이라는 것은 처음으로 야자를 쨌다든가 처음으로 술을 마셔 봤다든가 그런 것이 아니라, 명실공히 그렇고 그런 의미에서의 첫 경험이다.
+“우, 우리가…… 처음으로 그, 그걸 한 거는 말이야.”
+그렇게 말한 것은 소파에 앉아 있는 갈색 교복의 소녀였다. 둥근 얼굴에 커다란 갈색 눈동자를 지닌, 부드러운 머리카락을 어깨 위로 늘어뜨리고 있는 소녀다. 전반적으로 얌전한 모범생 같아 보이는 인상이고 몸집도 아담한 편이지만, 교복 상의를 매혹적으로 부풀어 오르게 하고 있는 가슴만큼은 얌전하지도 아담하지도 않았다. 몸을 움츠린 자세 탓에 두 팔이 가슴을 양옆에서 압박하고 있어, 몸을 움직일 때마다 그 윤곽이 부드럽게 일그러졌다.'''
+
+# 文本长度控制在1024以内
+assert len(text) < 1024
+
+messages = [
+ {'role': 'system', 'content': '你是一个轻小说译者，善于将外文轻小说翻译成中文'},
+ {'role': 'user', 'content': f'翻译成中文：\n{text}'}
+]
+
+text = tokenizer.apply_chat_template(
+ messages,
+ tokenize=False,
+ add_generation_prompt=True
+)
+
+model_inputs = tokenizer([text], return_tensors='pt').to('cuda')
+
+generated_ids = model.generate(
+ model_inputs.input_ids,
+ max_new_tokens=1024
+)
+
+generated_ids = [
+ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(response)
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+ "<|endoftext|>": 151643,
+ "<|im_end|>": 151645,
+ "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,29 @@
+{
+ "_name_or_path": "Sakura-14B-Qwen2beta-Base-v2",
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151643,
+ "eos_token_id": 151645,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 13696,
+ "max_position_embeddings": 32768,
+ "max_window_layers": 35,
+ "model_type": "qwen2",
+ "num_attention_heads": 40,
+ "num_hidden_layers": 40,
+ "num_key_value_heads": 40,
+ "rms_norm_eps": 1e-06,
+ "rope_theta": 1000000.0,
+ "sliding_window": 32768,
+ "tie_word_embeddings": false,
+ "torch_dtype": "bfloat16",
+ "transformers_version": "4.41.2",
+ "use_cache": false,
+ "use_flash_attention": true,
+ "use_sliding_window": false,
+ "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+ "bos_token_id": 151643,
+ "eos_token_id": 151645,
+ "max_new_tokens": 2048,
+ "transformers_version": "4.41.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05ba6e4801fe8768fc54facb405a18ea4aa7c0011bb3ba5b62fb1835652fbf8
+size 4919426680

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55e17d06730d192c77222d98814fd3d08fe811e150bd8a3f86554858aa85eb1a
+size 4991642256

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cfccaad952676fb5c9d15b69c48bd1f075c535ae03d1e6c21c699aa124bd94b
+size 4991631960

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc1f7b1d25ff61f3c88099a38d15d66acb2052c2d308dd4b2b746bef30492dc
+size 4991631960

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5234645514e4885740239e599aa7fc6d2b7738657e6b27670ab080f05675e897
+size 4991631960

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a13ddfa2029c3fe4733e39b07c2409e7bc48253e349821242e76e55f5809b92
+size 3448672536

model.safetensors.index.json

@@ -0,0 +1,490 @@
+{
+ "metadata": {
+ "total_size": 28334581760
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00006-of-00006.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+ "model.norm.weight": "model-00006-of-00006.safetensors"
+ }
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>"
+ ],
+ "eos_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151645": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "additional_special_tokens": [
+ "<|im_start|>",
+ "<|im_end|>"
+ ],
+ "bos_token": null,
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|endoftext|>",
+ "errors": "replace",
+ "model_max_length": 2048,
+ "pad_token": "<|endoftext|>",
+ "padding_side": "right",
+ "split_special_tokens": false,
+ "tokenizer_class": "Qwen2Tokenizer",
+ "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a8dc988acd21de69bff0c1adc87686d4d7ba69ef0bdd7f8e98a6d5e1d9470a0
+size 7480