ovokpus/llama381binstruct_summarize_short
Browse files
README.md
CHANGED
@@ -27,17 +27,17 @@ print(output["generated_text"])
|
|
27 |
|
28 |
## Training procedure
|
29 |
|
30 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ovokpus/huggingface/runs/
|
31 |
|
32 |
|
33 |
This model was trained with SFT.
|
34 |
|
35 |
### Framework versions
|
36 |
|
37 |
-
- TRL: 0.
|
38 |
-
- Transformers: 4.
|
39 |
- Pytorch: 2.6.0+cu124
|
40 |
-
- Datasets: 3.
|
41 |
- Tokenizers: 0.21.1
|
42 |
|
43 |
## Citations
|
|
|
27 |
|
28 |
## Training procedure
|
29 |
|
30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/ovokpus/huggingface/runs/tyv79v8k)
|
31 |
|
32 |
|
33 |
This model was trained with SFT.
|
34 |
|
35 |
### Framework versions
|
36 |
|
37 |
+
- TRL: 0.19.0
|
38 |
+
- Transformers: 4.52.4
|
39 |
- Pytorch: 2.6.0+cu124
|
40 |
+
- Datasets: 3.6.0
|
41 |
- Tokenizers: 0.21.1
|
42 |
|
43 |
## Citations
|
adapter_config.json
CHANGED
@@ -24,13 +24,13 @@
|
|
24 |
"rank_pattern": {},
|
25 |
"revision": null,
|
26 |
"target_modules": [
|
|
|
|
|
27 |
"v_proj",
|
28 |
-
"q_proj",
|
29 |
"down_proj",
|
30 |
-
"
|
31 |
-
"k_proj",
|
32 |
"up_proj",
|
33 |
-
"
|
34 |
],
|
35 |
"task_type": "CAUSAL_LM",
|
36 |
"trainable_token_indices": null,
|
|
|
24 |
"rank_pattern": {},
|
25 |
"revision": null,
|
26 |
"target_modules": [
|
27 |
+
"k_proj",
|
28 |
+
"o_proj",
|
29 |
"v_proj",
|
|
|
30 |
"down_proj",
|
31 |
+
"gate_proj",
|
|
|
32 |
"up_proj",
|
33 |
+
"q_proj"
|
34 |
],
|
35 |
"task_type": "CAUSAL_LM",
|
36 |
"trainable_token_indices": null,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20929019d4dced5c6fc250098271eb49d546860ba0a2a66dd5007f73f5c2baa3
|
3 |
size 167832240
|
chat_template.jinja
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>
|
2 |
+
|
3 |
+
'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>
|
4 |
+
|
5 |
+
' }}
|
runs/Jun23_19-24-34_9d64d03a1a51/events.out.tfevents.1750706706.9d64d03a1a51.2883.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ccbf062fc10a52c0fb273d59084cc32c3d489cacb30e1cf1145e4294de15ba1
|
3 |
+
size 30742
|
tokenizer_config.json
CHANGED
@@ -2050,7 +2050,6 @@
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
-
"chat_template": "{% 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 %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
"eos_token": "<|eot_id|>",
|
2056 |
"extra_special_tokens": {},
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
|
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
"eos_token": "<|eot_id|>",
|
2055 |
"extra_special_tokens": {},
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:408cde1a98115358f3d90ea98262cfa7e7dc5ee2b91236d7b980314b777f0176
|
3 |
size 5752
|