group_model_task_arith
Browse files- chat_template.jinja +1 -0
- config.json +4 -4
- generation_config.json +8 -2
- model.safetensors +2 -2
chat_template.jinja
CHANGED
|
@@ -1,3 +1,4 @@
|
|
|
|
|
| 1 |
{%- if tools %}
|
| 2 |
{{- '<|im_start|>system\n' }}
|
| 3 |
{%- if messages[0].role == 'system' %}
|
|
|
|
| 1 |
+
{%- set enable_thinking = true %}
|
| 2 |
{%- if tools %}
|
| 3 |
{{- '<|im_start|>system\n' }}
|
| 4 |
{%- if messages[0].role == 'system' %}
|
config.json
CHANGED
|
@@ -4,8 +4,8 @@
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id":
|
| 8 |
-
"dtype": "
|
| 9 |
"eos_token_id": 151645,
|
| 10 |
"head_dim": 128,
|
| 11 |
"hidden_act": "silu",
|
|
@@ -48,7 +48,7 @@
|
|
| 48 |
"num_attention_heads": 16,
|
| 49 |
"num_hidden_layers": 28,
|
| 50 |
"num_key_value_heads": 8,
|
| 51 |
-
"pad_token_id":
|
| 52 |
"rms_norm_eps": 1e-06,
|
| 53 |
"rope_parameters": {
|
| 54 |
"rope_theta": 1000000,
|
|
@@ -57,7 +57,7 @@
|
|
| 57 |
"sliding_window": null,
|
| 58 |
"tie_word_embeddings": true,
|
| 59 |
"transformers_version": "5.7.0",
|
| 60 |
-
"use_cache":
|
| 61 |
"use_sliding_window": false,
|
| 62 |
"vocab_size": 151936
|
| 63 |
}
|
|
|
|
| 4 |
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
"eos_token_id": 151645,
|
| 10 |
"head_dim": 128,
|
| 11 |
"hidden_act": "silu",
|
|
|
|
| 48 |
"num_attention_heads": 16,
|
| 49 |
"num_hidden_layers": 28,
|
| 50 |
"num_key_value_heads": 8,
|
| 51 |
+
"pad_token_id": null,
|
| 52 |
"rms_norm_eps": 1e-06,
|
| 53 |
"rope_parameters": {
|
| 54 |
"rope_theta": 1000000,
|
|
|
|
| 57 |
"sliding_window": null,
|
| 58 |
"tie_word_embeddings": true,
|
| 59 |
"transformers_version": "5.7.0",
|
| 60 |
+
"use_cache": true,
|
| 61 |
"use_sliding_window": false,
|
| 62 |
"vocab_size": 151936
|
| 63 |
}
|
generation_config.json
CHANGED
|
@@ -1,7 +1,13 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"do_sample": true,
|
| 3 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"top_k": 20,
|
| 5 |
-
"top_p": 0.
|
| 6 |
"transformers_version": "5.7.0"
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
"transformers_version": "5.7.0"
|
| 13 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a75f9b99d56a79f31aaa6cc032faffd9c7b81e3277653e36b29aa82aa20361af
|
| 3 |
+
size 6882335328
|