Upload folder using huggingface_hub

README.md

@@ -15,12 +15,12 @@ This is a merge of pre-trained language models created using [mergekit](https://
 ## Merge Details
 ### Merge Method
 
-This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [beomi/Llama-3-Open-Ko-8B](https://huggingface.co/beomi/Llama-3-Open-Ko-8B) as a base.
+This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [ProbeMedicalYonseiMAILab/medllama3-v20](https://huggingface.co/ProbeMedicalYonseiMAILab/medllama3-v20) as a base.
 
 ### Models Merged
 
 The following models were included in the merge:
-* [ProbeMedicalYonseiMAILab/medllama3-v20](https://huggingface.co/ProbeMedicalYonseiMAILab/medllama3-v20)
+* [beomi/Llama-3-Open-Ko-8B](https://huggingface.co/beomi/Llama-3-Open-Ko-8B)
 
 ### Configuration
 
@@ -28,13 +28,13 @@ The following YAML configuration was used to produce this model:
 
 ```yaml
 models:
-  - model: beomi/Llama-3-Open-Ko-8B
   - model: ProbeMedicalYonseiMAILab/medllama3-v20
+  - model: beomi/Llama-3-Open-Ko-8B
     parameters:
       density: 0.8
       weight: 0.45
 merge_method: dare_ties
-base_model: beomi/Llama-3-Open-Ko-8B
+base_model: ProbeMedicalYonseiMAILab/medllama3-v20
 parameters:
   int8_mask: true
 dtype: bfloat16

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "beomi/Llama-3-Open-Ko-8B",
+  "_name_or_path": "ProbeMedicalYonseiMAILab/medllama3-v20",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "eos_token_id": 128009,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,

mergekit_config.yml

@@ -1,11 +1,11 @@
 models:
-  - model: beomi/Llama-3-Open-Ko-8B
   - model: ProbeMedicalYonseiMAILab/medllama3-v20
+  - model: beomi/Llama-3-Open-Ko-8B
     parameters:
       density: 0.8
       weight: 0.45
 merge_method: dare_ties
-base_model: beomi/Llama-3-Open-Ko-8B
+base_model: ProbeMedicalYonseiMAILab/medllama3-v20
 parameters:
   int8_mask: true
 dtype: bfloat16

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee694bebd7dba64f0a1a3fd3483572dde890ddfaad51987466a141eda88f6be4
+oid sha256:a9ffab6c97ecfb98666e923fef62a82dea0cd9a1e2386e944cca88969b94319a
 size 2973804928

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4d49609f16426a9da659d8be8e10b89abb88d584ac227d03e6d067a208673cb
+oid sha256:1a35084ac65c951d0fe52455bc90aac0e58049c3537d4df35a2aa4b6b13457ad
 size 2978069224

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e00a19baf0680d9d19be72ffcb56060c43753215a19c758ee00fa74d50dd3efe
+oid sha256:cc6fb58c99db0e870678df0397bdf48e41c1fa485ea8d25c05627bb26d61342e
 size 2927737664

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:623b082658c30086979d5e7e786009a1966b5547aab391d7a437509aad2e3f8c
+oid sha256:2a15217eb6d887afe4c335ad83311ed6a8f8d241709274470474f25a0148399f
 size 2936134720

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74ada68e5e0a02df70e99682bc658885af10bc05cb7e20a9309636c23ecef659
+oid sha256:f68ebb9aa96a5925e32a754b6b8683b28527af9ebc779d7835216db55f0c8fd3
 size 2936134688

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa5abdf1b6b3aaf6ad20ab7bdb01e9a2ed721346fe389251fb1da64615808406
+oid sha256:1f421ca5dd6c355b492a6341b094787dd230294657316d25042b522728e73f3a
 size 1308675104

special_tokens_map.json

@@ -7,7 +7,14 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|end_of_text|>",
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|eot_id|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -2407,7 +2407,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
-    "ignore_merges": true,
+    "ignore_merges": false,
     "vocab": {
       "!": 0,
       "\"": 1,

tokenizer_config.json

@@ -2050,13 +2050,14 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ message['content'] }}{% elif message['role'] == 'user' %}{{ '\n\nHuman: ' + message['content'] +  eos_token }}{% elif message['role'] == 'assistant' %}{{ '\n\nAssistant: '  + message['content'] +  eos_token  }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '\n\nAssistant: ' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|end_of_text|>",
+  "eos_token": "<|eot_id|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }