Upload LlamaForCausalLM

README.md

@@ -1,15 +1,15 @@
 ---
-license: llama3
-language:
-- en
-tags:
-- biology
-- medical
 datasets:
 - EleutherAI/pile
 - Open-Orca/OpenOrca
 - GAIR/lima
 - WizardLM/WizardLM_evol_instruct_V2_196k
+language:
+- en
+license: llama3
+tags:
+- biology
+- medical
 ---
 # Instruction Pre-Training: Language Models are Supervised Multitask Learners
 This repo contains the **biomedicine model developed from Llama3-8B** in our paper [Instruction Pre-Training: Language Models are Supervised Multitask Learners](https://huggingface.co/papers/2406.14491).

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "hf_mirror/medicine-Llama3-8B",
+  "_name_or_path": "hf_mirror/medicine-Llama3-8B/shards",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -12,6 +12,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 14336,
   "max_position_embeddings": 8192,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -22,7 +23,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.34.0",
+  "transformers_version": "4.41.2",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -5,5 +5,5 @@
   "max_length": 4096,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.34.0"
+  "transformers_version": "4.41.2"
 }