Upload folder using huggingface_hub

README.md

@@ -1,7 +1,7 @@
 ---
 base_model:
-- Aspik101/llama10
-- cilantro9246/673ee71
+- kiwikiw/llama5
+- tomaszki/llama-16
 library_name: transformers
 tags:
 - mergekit
@@ -20,8 +20,8 @@ This model was merged using the SLERP merge method.
 ### Models Merged
 
 The following models were included in the merge:
-* [Aspik101/llama10](https://huggingface.co/Aspik101/llama10)
-* [cilantro9246/673ee71](https://huggingface.co/cilantro9246/673ee71)
+* [kiwikiw/llama5](https://huggingface.co/kiwikiw/llama5)
+* [tomaszki/llama-16](https://huggingface.co/tomaszki/llama-16)
 
 ### Configuration
 
@@ -31,12 +31,12 @@ The following YAML configuration was used to produce this model:
 
 slices:
   - sources:
-      - model: cilantro9246/673ee71
+      - model: kiwikiw/llama5
         layer_range: [0, 32]
-      - model: Aspik101/llama10
+      - model: tomaszki/llama-16
         layer_range: [0, 32]
 merge_method: slerp
-base_model: Aspik101/llama10
+base_model: kiwikiw/llama5
 parameters:
   t:
     - filter: self_attn

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Aspik101/llama10",
+  "_name_or_path": "kiwikiw/llama5",
   "architectures": [
     "LlamaForCausalLM"
   ],

mergekit_config.yml

@@ -1,12 +1,12 @@
 
 slices:
   - sources:
-      - model: cilantro9246/673ee71
+      - model: kiwikiw/llama5
         layer_range: [0, 32]
-      - model: Aspik101/llama10
+      - model: tomaszki/llama-16
         layer_range: [0, 32]
 merge_method: slerp
-base_model: Aspik101/llama10
+base_model: kiwikiw/llama5
 parameters:
   t:
     - filter: self_attn

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebadd7fc1602b3e7d1145f3253f96529596b0df97d3641b17c5cf7b992f63c55
+oid sha256:7b54980ca6e010c15f4f0bf2d43c60e648c8c66682bdf6e9337c603afad34ef9
 size 9953405736

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1343521f19980a286ea027d0b239602057a142cbfe793b467a061806b1f9131f
+oid sha256:09cff084962328b1413ae3d3ade066e074a0b753e40aa296fb315861b6b02d1e
 size 6107150624

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 2048,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {
@@ -2407,7 +2412,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
-    "ignore_merges": false,
+    "ignore_merges": true,
     "vocab": {
       "!": 0,
       "\"": 1,

tokenizer_config.json

@@ -2053,11 +2053,15 @@
   "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 %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
+  "max_length": 2048,
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|end_of_text|>",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first"
 }