Upload folder using huggingface_hub

README.md

@@ -1,7 +1,7 @@
 ---
 base_model:
+- Qwen/Qwen2.5-32B
 - all-hands/openhands-lm-32b-v0.1-ep3
-- all-hands/openhands-lm-32b-v0.1
 library_name: transformers
 tags:
 - mergekit
@@ -20,8 +20,8 @@ This model was merged using the [Linear](https://arxiv.org/abs/2203.05482) merge
 ### Models Merged
 
 The following models were included in the merge:
+* [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B)
 * [all-hands/openhands-lm-32b-v0.1-ep3](https://huggingface.co/all-hands/openhands-lm-32b-v0.1-ep3)
-* [all-hands/openhands-lm-32b-v0.1](https://huggingface.co/all-hands/openhands-lm-32b-v0.1)
 
 ### Configuration
 
@@ -29,7 +29,7 @@ The following YAML configuration was used to produce this model:
 
 ```yaml
 models:
-  - model: all-hands/openhands-lm-32b-v0.1
+  - model: Qwen/Qwen2.5-32B
     parameters:
       weight: 0.5
   - model: all-hands/openhands-lm-32b-v0.1-ep3

config.json

@@ -4,26 +4,21 @@
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
-  "eos_token_id": 151645,
+  "eos_token_id": 151643,
   "hidden_act": "silu",
   "hidden_size": 5120,
   "initializer_range": 0.02,
   "intermediate_size": 27648,
-  "max_position_embeddings": 32768,
+  "max_position_embeddings": 131072,
   "max_window_layers": 64,
   "model_type": "qwen2",
   "num_attention_heads": 40,
   "num_hidden_layers": 64,
   "num_key_value_heads": 8,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": {
-    "factor": 4.0,
-    "original_max_position_embeddings": 32768,
-    "rope_type": "yarn",
-    "type": "yarn"
-  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
   "rope_theta": 1000000.0,
-  "sliding_window": null,
+  "sliding_window": 131072,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
   "transformers_version": "4.51.3",

mergekit_config.yml

@@ -1,5 +1,5 @@
 models:
-  - model: all-hands/openhands-lm-32b-v0.1
+  - model: Qwen/Qwen2.5-32B
     parameters:
       weight: 0.5
   - model: all-hands/openhands-lm-32b-v0.1-ep3

model-00001-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d568cb8ccad77e3428c49622bc7b817be8341868fc02cc244c71702d79634b5
+oid sha256:bdcb8fec1ad752cfc5c014de1aca81806c4c81ca78f601cf830b53347c0ee930
 size 4949338448

model-00002-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7537c99a2ce64c7325aabf50a149a84a88a7467798f68969b56adb56a649e0ea
+oid sha256:310307da753ff2bde6ba596b36e52b1924c8aab465a582bb327b2603ee6b696e
 size 4991425912

model-00003-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2ffcf35de64474d4373c1bfb96abe85d24a289d5458b2d466518b5fa0c0cc08
+oid sha256:da341dce65ea16f8dc0298551f1d6dfae96e6041fa1c4bb063bae9f977823a1f
 size 4876059352

model-00004-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf74cec42d4c8f2630c70879975a59d1e4c727428b022a0371ec4fc184861fc0
+oid sha256:dffe4920b3e360de52c33a4e84f56c9cf4b11dba6aa34d364d154bca3988762b
 size 4876059336

model-00005-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1323e3a6ba742b6ee06eee28f536d6498677e741bcc599e0ffa6ea4a4703374f
+oid sha256:0b8dcea11dcb72757b3573c9e0b00d8dc0c4462443ab8250a4319227b0140413
 size 4876059352

model-00006-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bb4d5e58c49e2cad23e4accdb2c51155a06cd93e050ff298a9c6f0a46e79ab3
+oid sha256:c17458462aadb2391b0fdf6f0724e02b5d5be98d35c5de3e4cf7b016837994eb
 size 4876059336

model-00007-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d967135f1ce31a115b192226a420800228952f2f870343104a87d33cfa74791d
+oid sha256:43f797e2b003021e8faa6625f417d7fa0c6e1d3379bc6e63a4c0ac2b04cac482
 size 4876059352

model-00008-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5233ec586259d9173a59d7880cd7b7e6e9f22b9eb06897efe84bf3bc321c3771
+oid sha256:db649e9ed12de9ad8bb4798ecf4732f5ed73dc93045cecdf21c3144c8d2e893f
 size 4876059336

model-00009-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cede474b9335f1c870e4e1d2899193466a0e85a95642bc12d0fdf87de76a409a
+oid sha256:e2f67b1a1c52257dbc3c62e0222cf9fcb9a80fefc84b4a707cee461708b0e36a
 size 4876059352

model-00010-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:621e97c725e17175e02c32805b86c8f83671d6a75b132ba44ec70b2747b26cea
+oid sha256:517449e6bd4a462062e47d0c395bb55801a37130ba241b883ea2a2e70e3e3814
 size 4876059336

model-00011-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10625adaafd26ad799d51fd6c120a8424e6e1f4cab2901d55a10f8b63a35714f
+oid sha256:699dc612b7a8575049ae378b264f5dc899001305b58c4d8858ca8949183c7b3d
 size 4876059352

model-00012-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c750adf36277a9a6aab26a5cd778a78c31e32583469bf3d1549afcb6450dfc9d
+oid sha256:393a5f5c7d3a3883c6d99ecf8e194b69019ff8e91ad472a0cc754a87a85fb978
 size 4876059336

model-00013-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c0860ebbc27498eaaac8385d202509298ae4f92b8eed3cbe0758693f34509fa
+oid sha256:ffa7b11a1426177118787b0d623be21fe902c2b21300338ae8a043bf6d143b8d
 size 4876059336

model-00014-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:333071ed2ab448f5e071a5577a6282121a7b576d9455a450fe5f14a259b2469a
+oid sha256:aedb206d1fad0b9a7928f286e04d6f45f3bb3f8f1772394871361d721fbf7b6d
 size 1950423704

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896
+oid sha256:c0382117ea329cdf097041132f6d735924b697924d6f6fc3945713e96ce87539
+size 7031645

tokenizer_config.json

@@ -195,14 +195,13 @@
     "<|video_pad|>"
   ],
   "bos_token": null,
-  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<|endoftext|>",
   "errors": "replace",
-  "extra_special_tokens": {},
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null
-}
+}