Upload folder using huggingface_hub

README.md

@@ -3,30 +3,30 @@ tags:
 - merge
 - mergekit
 - lazymergekit
+- OpenPipe/mistral-ft-optimized-1218
 - notzero/model_combined
-- EmbeddedLLM/Mistral-7B-Merge-14-v0.5
 base_model:
+- OpenPipe/mistral-ft-optimized-1218
 - notzero/model_combined
-- EmbeddedLLM/Mistral-7B-Merge-14-v0.5
 ---
 
 # test_merge
 
 test_merge is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [OpenPipe/mistral-ft-optimized-1218](https://huggingface.co/OpenPipe/mistral-ft-optimized-1218)
 * [notzero/model_combined](https://huggingface.co/notzero/model_combined)
-* [EmbeddedLLM/Mistral-7B-Merge-14-v0.5](https://huggingface.co/EmbeddedLLM/Mistral-7B-Merge-14-v0.5)
 
 ## 🧩 Configuration
 
 ```yaml
 slices:
   - sources:
-      - model: notzero/model_combined
+      - model: OpenPipe/mistral-ft-optimized-1218
         layer_range: [0, 32]
-      - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.5
+      - model: notzero/model_combined
         layer_range: [0, 32]
 merge_method: slerp
-base_model: notzero/model_combined
+base_model: OpenPipe/mistral-ft-optimized-1218
 parameters:
   t:
     - filter: self_attn

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "notzero/model_combined",
+  "_name_or_path": "OpenPipe/mistral-ft-optimized-1218",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -21,7 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.2",
-  "unsloth_version": "2024.2",
   "use_cache": true,
-  "vocab_size": 48384
+  "vocab_size": 32000
 }

mergekit_config.yml

@@ -1,12 +1,12 @@
 
 slices:
   - sources:
-      - model: notzero/model_combined
+      - model: OpenPipe/mistral-ft-optimized-1218
         layer_range: [0, 32]
-      - model: EmbeddedLLM/Mistral-7B-Merge-14-v0.5
+      - model: notzero/model_combined
         layer_range: [0, 32]
 merge_method: slerp
-base_model: notzero/model_combined
+base_model: OpenPipe/mistral-ft-optimized-1218
 parameters:
   t:
     - filter: self_attn

model-00001-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbfcd5118db412ed9250a4627cadd0f0d76c8a9f22d8e4daa95198b12a98e489
+oid sha256:6bf48c6feec4050a9801e21ffd04e397685f0fe6e56bf7e8a3e0fae55dc17f16
 size 1946227344

model-00002-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bdf09e81f65cee8f9c69aea7c37e70878b36075d10eef906dba7b9914bc669c
+oid sha256:8be67e4abb48b92c9157a96b67b1430b581abacba42029dcbf21aeaf97f48d2b
 size 1979781432

model-00003-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:313123915390af6824f338bfb14deaddf1247449db5630b2de33a305cc48bc00
-size 1889603432
+oid sha256:20770224a8ab3f912e8540ee37f3c491327f57fb3e5e4607b54ec587fe07904c
+size 1889587048

model-00004-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2c02ec726ce851346cf8c10ae2ba744cf052afb5686acc9c06b06834db9d805
+oid sha256:a8a34b1f103c487fb28cd05fddddb81dc979e7c9e3360b8ba002fc5eb6a4e4a8
 size 1946243984

model-00005-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c07af49535816b87fc9709008e6fc8680298404035754c6195b16a360b687adf
+oid sha256:5dafa07d0358b3d8f0910615e3fd317f2a7ed3b471e325aacd8b79bc08da2282
 size 1979798064

model-00006-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f52c511d718c9586cc1072ca739363124f8c7bada8295f1d4a84e04cb1a4e10
-size 1973506120
+oid sha256:a161653a4cbe203533cb34531b00b761e78e5d3fbd69910bdac95e2801c00fb0
+size 1973489736

model-00007-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:471550d410f77b9f459418c27af107de3c573cf640ec91420688e886f44fc4e5
+oid sha256:665961920f442c78e9fe45e5f2e9ba0b038e4d25c85da6480c0c4246e724c811
 size 1895903680

model-00008-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da5f8b0b33650a3dc1ecd669b7763f7e0d7b663c1603eb929a33ccd06a13451a
+oid sha256:e01166f9fe2a17347343e0eb0922cd6381d08558d0216b8221393cf0bd2c864f
 size 872466704

special_tokens_map.json

@@ -13,13 +13,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d88bdadaa2a065aa7c6e18a4b5999ce4c76cec14d9fea882102e7b4931d7ef0
-size 779539
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -29,13 +29,11 @@
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '</s>'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,
-  "model_max_length": 32768,
-  "pad_token": "</s>",
-  "padding_side": "right",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",