Upload folder using huggingface_hub
Browse files- chat_template.jinja +26 -1
- config.json +3 -1
- generation_config.json +2 -1
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
- special_tokens_map.json +1 -1
- tokenizer_config.json +3 -2
chat_template.jinja
CHANGED
|
@@ -14,6 +14,14 @@
|
|
| 14 |
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
{%- endif %}
|
| 16 |
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
{%- for message in messages %}
|
| 18 |
{%- if message.content is string %}
|
| 19 |
{%- set content = message.content %}
|
|
@@ -23,7 +31,24 @@
|
|
| 23 |
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 24 |
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 25 |
{%- elif message.role == "assistant" %}
|
| 26 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
{%- if message.tool_calls %}
|
| 28 |
{%- for tool_call in message.tool_calls %}
|
| 29 |
{%- if (loop.first and content) or (not loop.first) %}
|
|
|
|
| 14 |
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
{%- endif %}
|
| 16 |
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
{%- for message in messages %}
|
| 26 |
{%- if message.content is string %}
|
| 27 |
{%- set content = message.content %}
|
|
|
|
| 31 |
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
{%- if message.tool_calls %}
|
| 53 |
{%- for tool_call in message.tool_calls %}
|
| 54 |
{%- if (loop.first and content) or (not loop.first) %}
|
config.json
CHANGED
|
@@ -4,7 +4,6 @@
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": 151643,
|
| 8 |
"dtype": "float16",
|
| 9 |
"eos_token_id": 151645,
|
| 10 |
"head_dim": 128,
|
|
@@ -56,12 +55,15 @@
|
|
| 56 |
"num_attention_heads": 32,
|
| 57 |
"num_hidden_layers": 36,
|
| 58 |
"num_key_value_heads": 8,
|
|
|
|
| 59 |
"rms_norm_eps": 1e-06,
|
| 60 |
"rope_scaling": null,
|
| 61 |
"rope_theta": 5000000,
|
| 62 |
"sliding_window": null,
|
| 63 |
"tie_word_embeddings": true,
|
| 64 |
"transformers_version": "4.57.3",
|
|
|
|
|
|
|
| 65 |
"use_cache": true,
|
| 66 |
"use_sliding_window": false,
|
| 67 |
"vocab_size": 151936
|
|
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
|
|
|
| 7 |
"dtype": "float16",
|
| 8 |
"eos_token_id": 151645,
|
| 9 |
"head_dim": 128,
|
|
|
|
| 55 |
"num_attention_heads": 32,
|
| 56 |
"num_hidden_layers": 36,
|
| 57 |
"num_key_value_heads": 8,
|
| 58 |
+
"pad_token_id": 151654,
|
| 59 |
"rms_norm_eps": 1e-06,
|
| 60 |
"rope_scaling": null,
|
| 61 |
"rope_theta": 5000000,
|
| 62 |
"sliding_window": null,
|
| 63 |
"tie_word_embeddings": true,
|
| 64 |
"transformers_version": "4.57.3",
|
| 65 |
+
"unsloth_fixed": true,
|
| 66 |
+
"unsloth_version": "2025.12.7",
|
| 67 |
"use_cache": true,
|
| 68 |
"use_sliding_window": false,
|
| 69 |
"vocab_size": 151936
|
generation_config.json
CHANGED
|
@@ -5,7 +5,8 @@
|
|
| 5 |
151645,
|
| 6 |
151643
|
| 7 |
],
|
| 8 |
-
"
|
|
|
|
| 9 |
"temperature": 0.7,
|
| 10 |
"top_k": 20,
|
| 11 |
"top_p": 0.8,
|
|
|
|
| 5 |
151645,
|
| 6 |
151643
|
| 7 |
],
|
| 8 |
+
"max_length": 262144,
|
| 9 |
+
"pad_token_id": 151654,
|
| 10 |
"temperature": 0.7,
|
| 11 |
"top_k": 20,
|
| 12 |
"top_p": 0.8,
|
model-00001-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4967215128
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb68a58103798c6c4689589ba63db8f4651c5fb7de5567caefc96c2674431a8e
|
| 3 |
size 4967215128
|
model-00002-of-00002.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3077766464
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a04395cb2a450d7f6c9eadc32e60c1c7550ebfa7fde652bbf37220dec99170b
|
| 3 |
size 3077766464
|
special_tokens_map.json
CHANGED
|
@@ -22,7 +22,7 @@
|
|
| 22 |
"single_word": false
|
| 23 |
},
|
| 24 |
"pad_token": {
|
| 25 |
-
"content": "<|
|
| 26 |
"lstrip": false,
|
| 27 |
"normalized": false,
|
| 28 |
"rstrip": false,
|
|
|
|
| 22 |
"single_word": false
|
| 23 |
},
|
| 24 |
"pad_token": {
|
| 25 |
+
"content": "<|vision_pad|>",
|
| 26 |
"lstrip": false,
|
| 27 |
"normalized": false,
|
| 28 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -231,8 +231,9 @@
|
|
| 231 |
"eos_token": "<|im_end|>",
|
| 232 |
"errors": "replace",
|
| 233 |
"extra_special_tokens": {},
|
| 234 |
-
"model_max_length":
|
| 235 |
-
"pad_token": "<|
|
|
|
|
| 236 |
"split_special_tokens": false,
|
| 237 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
"unk_token": null
|
|
|
|
| 231 |
"eos_token": "<|im_end|>",
|
| 232 |
"errors": "replace",
|
| 233 |
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|vision_pad|>",
|
| 236 |
+
"padding_side": "left",
|
| 237 |
"split_special_tokens": false,
|
| 238 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
"unk_token": null
|