Upload Qwen2ForCausalLM

README.md

@@ -1,6 +1,8 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- trl
+- sft
 ---
 
 # Model Card for Model ID

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-14B-Instruct",
+  "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": 13824,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "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": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

model-00001-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b3a7173f283eea786814575a9961dc637414cf160990defe68ca2e3263e5546
+size 1557135504

model-00002-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2f2407e3814639ec7740a100a93dd4b378841b8d1c9849f773cabb798f4b363
+size 499439179

model-00003-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a6f1f6edacad9fbe722fe3e38482c45076c7815138ee774ea20e521104a93e
+size 465896736

model-00004-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b472ef2469a9010e4a49a46db81aa9a64cf7b2b44bdeb37626cbcfa3b368e1ff
+size 499480389

model-00005-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:431774d657e83bfee588046805d6bbaa59c3395cde2a394ac245e9f0a92ad54b
+size 465896904

model-00006-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61f8fd48f92abc2f5f2fef1a012e7aa53dc1a120c7cccc48c850bd3126f11fd7
+size 465896908

model-00007-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79be45ab827a53eccf1e72141dd928fcee21a8041538225540cf99b0450b7db
+size 499480562

model-00008-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d691f4f89a549094e1dd03df69ee5e38e5441c7ee825c5827419cb58790a3f62
+size 465896907

model-00009-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:136fdf83814905fa286eaceb97668772d94e44b5cd3e9daa86a20896d068351e
+size 465896907

model-00010-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdffe13f0c305f109794b4722dac713c7b8b7399dec3ac04dd3d92f178de165f
+size 499480565

model-00011-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7963338bebe83c8318d38356b880b53714824e1f9d874276bbf7821c344647d4
+size 465896907

model-00012-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1698a676afdbc136fcb5f037850c1eb1b71049e12fd5d4fa590d69fba3c43a72
+size 465896897

model-00013-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9b2eba18a7efd5986a7ff6af39eea8b8878efa88096129bbf79dfa3dacd06ab
+size 499480567

model-00014-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24a6a4783354eafeb808f14a7d5c95864530330fcadfe4be8cf9c3c52f96b5bf
+size 465896907

model-00015-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0542fd4472a7f158531b025d0b211e50d372ff591cd46031d5f1d09472da8967
+size 465896900

model-00016-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:577d0d56e0619a26340ae403b1af5c2c179796f9abe288b0fdec04082e545ab0
+size 1557135488

model-00017-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:671b575b03da7e3e839989630f7ad3196262bd46ed8ca5b2810b5cf7e2e03bf6
+size 179703749