Upload Qwen2ForCausalLM

README.md

@@ -41,7 +41,7 @@ import json
 import torch 
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_name = "MadeAgents/Hammer-1.5b"
+model_name = "MadeAgents/Hammer-7b"
 model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype="auto", trust_remote_code=True)
 tokenizer = AutoTokenizer.from_pretrained(model_name) 
 

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/home/notebook/data/group/ComplexTaskDecision/Hammer/ckpt/select_caller/xlam_1b/xlam_mask3_0.33_hammer_qwen1.5b_batch32/merge_step4220",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb957615ebe2f1cc490e4fe8401d94aac0bd972f6eba9f30a5fb7ac40483bb67
+size 3086576264