Upload folder using huggingface_hub

README.md

@@ -1,33 +1,34 @@
 ---
 base_model:
-- crestf411/L3.1-8B-sunfall-v0.6.1-dpo
+- Undi95/Meta-Llama-3.1-8B-Claude
 library_name: transformers
 tags:
 - mergekit
 - merge
 
 ---
-# lemoist
+# stablerp
 
 This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
 ## Merge Details
 ### Merge Method
 
-This model was merged using the linear [DARE](https://arxiv.org/abs/2311.03099) merge method using [crestf411/L3.1-8B-sunfall-v0.6.1-dpo](https://huggingface.co/crestf411/L3.1-8B-sunfall-v0.6.1-dpo) as a base.
+This model was merged using the linear [DARE](https://arxiv.org/abs/2311.03099) merge method using [Undi95/Meta-Llama-3.1-8B-Claude](https://huggingface.co/Undi95/Meta-Llama-3.1-8B-Claude) as a base.
 
 ### Models Merged
 
 The following models were included in the merge:
-* merge/lemoist.b
-* merge/lemoist.a
+* merge/stablerp.c
+* merge/stablerp.a
+* merge/stablerp.b
 
 ### Configuration
 
 The following YAML configuration was used to produce this model:
 
 ```yaml
-base_model: crestf411/L3.1-8B-sunfall-v0.6.1-dpo
+base_model: Undi95/Meta-Llama-3.1-8B-Claude
 dtype: float32
 merge_method: dare_linear
 out_dtype: bfloat16
@@ -37,14 +38,18 @@ parameters:
 slices:
 - sources:
   - layer_range: [0, 32]
-    model: merge/lemoist.b
+    model: merge/stablerp.b
     parameters:
-      weight: 0.5
+      weight: [1.0, 0.2]
   - layer_range: [0, 32]
-    model: merge/lemoist.a
+    model: merge/stablerp.a
     parameters:
-      weight: 0.6
+      weight: [0.1, 0.5]
   - layer_range: [0, 32]
-    model: crestf411/L3.1-8B-sunfall-v0.6.1-dpo
+    model: merge/stablerp.c
+    parameters:
+      weight: [0.1, 0.5]
+  - layer_range: [0, 32]
+    model: Undi95/Meta-Llama-3.1-8B-Claude
 tokenizer_source: base
 ```

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "crestf411/L3.1-8B-sunfall-v0.6.1-dpo",
+  "_name_or_path": "Undi95/Meta-Llama-3.1-8B-Claude",
   "architectures": [
     "LlamaForCausalLM"
   ],

mergekit_config.yml

@@ -1,4 +1,4 @@
-base_model: crestf411/L3.1-8B-sunfall-v0.6.1-dpo
+base_model: Undi95/Meta-Llama-3.1-8B-Claude
 dtype: float32
 merge_method: dare_linear
 out_dtype: bfloat16
@@ -8,13 +8,17 @@ parameters:
 slices:
 - sources:
   - layer_range: [0, 32]
-    model: merge/lemoist.b
+    model: merge/stablerp.b
     parameters:
-      weight: 0.5
+      weight: [1.0, 0.2]
   - layer_range: [0, 32]
-    model: merge/lemoist.a
+    model: merge/stablerp.a
     parameters:
-      weight: 0.6
+      weight: [0.1, 0.5]
   - layer_range: [0, 32]
-    model: crestf411/L3.1-8B-sunfall-v0.6.1-dpo
+    model: merge/stablerp.c
+    parameters:
+      weight: [0.1, 0.5]
+  - layer_range: [0, 32]
+    model: Undi95/Meta-Llama-3.1-8B-Claude
 tokenizer_source: base

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7922e2d89aebed031e43c79c3e4cd0e73c496ac6f3489bebf63cdb819c06e3f3
+oid sha256:5ed44f3f8fae973becdb6b0fa185ce906ba885442b24dda399a34e3d9b8afd60
 size 2973804928

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0ac2265545acf59558f0f4b6c609ab9dc117e5b49b74e6a51bf2898dff4a2fe
+oid sha256:aa4308798be701284de395d2cecf3c39193a8d8a7c6cb45043e4374793fae43d
 size 2978069224

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e72901f4081dc874a31c327f0643121ef06c3b72f0d019dcdf1faa03c89480cd
+oid sha256:52a7049cd0657ebb78a38a5b84252906948dd42d2628d10926b5530037bb9134
 size 2927737664

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c59bbd4bf737fe225eabaad8d53cc95c579e9147ff945ba8639081c6d0143be2
+oid sha256:32ea55be452886499ff7fa8c2eefd02fdd942dfc2e1c7d6dbd78a57603e60069
 size 2936134720

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae70c1cb6d1c526bb9c0cc9a99cb1dc4043503a9d971cfa792f38e86d47324b7
+oid sha256:587c055310cd18b4e881e5e20a7bfcf10f33eecace9c9740198d154560cb1675
 size 2936134688

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d22b09cb5f704994e9b91ef605a08bbd7e33f34d22ed93ba3774184764841fe1
+oid sha256:38bde6312d031a03211f14a787829da6ab645718fbcc2bc61f6f189ee4f08c33
 size 1308675104

special_tokens_map.json

@@ -12,12 +12,5 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  },
-  "pad_token": {
-    "content": "<|end_of_text|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
   }
 }

tokenizer_config.json

@@ -2050,7 +2050,7 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
   "model_input_names": [
@@ -2058,6 +2058,5 @@
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "pad_token": "<|end_of_text|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }