(Trained with Unsloth)
Browse files- chat_template.jinja +15 -0
- config.json +29 -0
- generation_config.json +8 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% if 'role' in messages[0] %}{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user
|
| 2 |
+
' + message['content'] + '<|im_end|>
|
| 3 |
+
'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant
|
| 4 |
+
' + message['content'] + '<|im_end|>
|
| 5 |
+
' }}{% else %}{{ '<|im_start|>system
|
| 6 |
+
' + message['content'] + '<|im_end|>
|
| 7 |
+
' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 8 |
+
' }}{% endif %}{% else %}{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user
|
| 9 |
+
' + message['value'] + '<|im_end|>
|
| 10 |
+
'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant
|
| 11 |
+
' + message['value'] + '<|im_end|>
|
| 12 |
+
' }}{% else %}{{ '<|im_start|>system
|
| 13 |
+
' + message['value'] + '<|im_end|>
|
| 14 |
+
' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 15 |
+
' }}{% endif %}{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MistralForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"head_dim": 128,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 14336,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"model_type": "mistral",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_hidden_layers": 32,
|
| 17 |
+
"num_key_value_heads": 8,
|
| 18 |
+
"pad_token_id": 770,
|
| 19 |
+
"rms_norm_eps": 1e-05,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 1000000.0,
|
| 22 |
+
"sliding_window": null,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "float16",
|
| 25 |
+
"transformers_version": "4.55.1",
|
| 26 |
+
"unsloth_version": "2025.8.6",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 32768
|
| 29 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"max_length": 32768,
|
| 6 |
+
"pad_token_id": 770,
|
| 7 |
+
"transformers_version": "4.55.1"
|
| 8 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "<|im_end|>",
|
| 4 |
+
"pad_token": "[control_768]",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|