EleutherAI/SmolLM2-1.7B-magpie-ultra-v0.1-attribution
Browse files- README.md +2 -2
- config.json +1 -1
- generation_config.json +1 -1
- model.safetensors +1 -1
- tokenizer_config.json +1 -1
- training_args.bin +2 -2
README.md
CHANGED
@@ -27,7 +27,7 @@ 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/eleutherai/huggingface/runs/
|
31 |
|
32 |
|
33 |
This model was trained with SFT.
|
@@ -35,7 +35,7 @@ This model was trained with SFT.
|
|
35 |
### Framework versions
|
36 |
|
37 |
- TRL: 0.18.1
|
38 |
-
- Transformers: 4.
|
39 |
- Pytorch: 2.5.1
|
40 |
- Datasets: 3.6.0
|
41 |
- Tokenizers: 0.21.1
|
|
|
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/eleutherai/huggingface/runs/2e1kywoy)
|
31 |
|
32 |
|
33 |
This model was trained with SFT.
|
|
|
35 |
### Framework versions
|
36 |
|
37 |
- TRL: 0.18.1
|
38 |
+
- Transformers: 4.52.4
|
39 |
- Pytorch: 2.5.1
|
40 |
- Datasets: 3.6.0
|
41 |
- Tokenizers: 0.21.1
|
config.json
CHANGED
@@ -24,7 +24,7 @@
|
|
24 |
"rope_theta": 130000,
|
25 |
"tie_word_embeddings": true,
|
26 |
"torch_dtype": "bfloat16",
|
27 |
-
"transformers_version": "4.
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 49152
|
30 |
}
|
|
|
24 |
"rope_theta": 130000,
|
25 |
"tie_word_embeddings": true,
|
26 |
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.52.4",
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 49152
|
30 |
}
|
generation_config.json
CHANGED
@@ -3,5 +3,5 @@
|
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
"pad_token_id": 2,
|
6 |
-
"transformers_version": "4.
|
7 |
}
|
|
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
"pad_token_id": 2,
|
6 |
+
"transformers_version": "4.52.4"
|
7 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3422777952
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc3265f1eccc7f0a63088133dde35097dc97defc4153c5515541f94198a5254d
|
3 |
size 3422777952
|
tokenizer_config.json
CHANGED
@@ -143,10 +143,10 @@
|
|
143 |
"<|im_end|>"
|
144 |
],
|
145 |
"bos_token": "<|im_start|>",
|
146 |
-
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
147 |
"clean_up_tokenization_spaces": false,
|
148 |
"eos_token": "<|im_end|>",
|
149 |
"extra_special_tokens": {},
|
|
|
150 |
"model_max_length": 8192,
|
151 |
"pad_token": "<|im_end|>",
|
152 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
143 |
"<|im_end|>"
|
144 |
],
|
145 |
"bos_token": "<|im_start|>",
|
|
|
146 |
"clean_up_tokenization_spaces": false,
|
147 |
"eos_token": "<|im_end|>",
|
148 |
"extra_special_tokens": {},
|
149 |
+
"max_length": 8192,
|
150 |
"model_max_length": 8192,
|
151 |
"pad_token": "<|im_end|>",
|
152 |
"tokenizer_class": "GPT2Tokenizer",
|
training_args.bin
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:bc7ca4fc7c17fe67dad7f930c033aab41d667039fb6b330646c2f2d703a964a8
|
3 |
+
size 5624
|