初始化项目，由ModelHub XC社区提供模型

Model: deqing/llama-300M-v3-muon-original
Source: Original Platform

ckpt-8-2b/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "float32",
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 500000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.1.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

ckpt-8-2b/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001
+  ],
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.1.0",
+  "use_cache": true
+}

ckpt-8-2b/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abfda4052945da85b8bd9f55c60eb50c55a95fdf4e8c1210cb87b3d0a409821c
+size 1280426144

ckpt-8-2b/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c1ebb7de49bedbc90aa6ec27679886da478a3393e987c392022a0ef5d23465
+size 1805894027

ckpt-8-2b/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62bf4109bb1f7996aaa86885445885c3970978e71d9de55d598ead736b2e0340
+size 14917

ckpt-8-2b/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2295db4a59f5fea920e34eddf64f5118dc09c7be8e89e630d91edc1eb7bd870a
+size 14917

ckpt-8-2b/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f112c282e72bbf4b8b37c678e3cbb0a0f4fde1d204545a79f9aeadb1cb38f8ab
+size 1465

ckpt-8-2b/tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "tokenizer_class": "TokenizersBackend"
+}

ckpt-8-2b/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555e861805d23ffd849ea370cfdde89fa1a892e3e3fbecfaf0bd36e61ec5b39e
+size 5329