Training in progress, step 5000
Browse files- config.json +38 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Apr21_19-44-48_luigi-inspiron135330/events.out.tfevents.1745235892.luigi-inspiron135330.713012.0 +3 -0
- runs/Apr21_19-50-19_luigi-inspiron135330/events.out.tfevents.1745236222.luigi-inspiron135330.717860.0 +3 -0
- runs/Apr21_19-52-25_luigi-inspiron135330/events.out.tfevents.1745236347.luigi-inspiron135330.719206.0 +3 -0
- runs/Apr21_20-02-42_luigi-inspiron135330/events.out.tfevents.1745236963.luigi-inspiron135330.725683.0 +3 -0
- runs/Apr21_20-05-03_luigi-inspiron135330/events.out.tfevents.1745237104.luigi-inspiron135330.727325.0 +3 -0
- runs/Apr21_20-05-47_luigi-inspiron135330/events.out.tfevents.1745237148.luigi-inspiron135330.727919.0 +3 -0
- runs/Apr21_20-06-58_luigi-inspiron135330/events.out.tfevents.1745237219.luigi-inspiron135330.728827.0 +3 -0
- runs/Apr21_20-11-54_luigi-inspiron135330/events.out.tfevents.1745237515.luigi-inspiron135330.731733.0 +3 -0
- runs/Apr21_20-19-42_luigi-inspiron135330/events.out.tfevents.1745237983.luigi-inspiron135330.736871.0 +3 -0
- runs/Apr21_20-23-09_luigi-inspiron135330/events.out.tfevents.1745238190.luigi-inspiron135330.742677.0 +3 -0
- runs/Apr21_20-35-29_luigi-inspiron135330/events.out.tfevents.1745238930.luigi-inspiron135330.7446.0 +3 -0
- runs/Apr21_20-36-20_luigi-inspiron135330/events.out.tfevents.1745238981.luigi-inspiron135330.8505.0 +3 -0
- runs/Apr21_20-37-30_luigi-inspiron135330/events.out.tfevents.1745239051.luigi-inspiron135330.9787.0 +3 -0
- runs/Apr21_20-38-46_luigi-inspiron135330/events.out.tfevents.1745239127.luigi-inspiron135330.11522.0 +3 -0
- runs/Apr21_20-40-05_luigi-inspiron135330/events.out.tfevents.1745239206.luigi-inspiron135330.12585.0 +3 -0
- runs/Apr21_20-41-12_luigi-inspiron135330/events.out.tfevents.1745239273.luigi-inspiron135330.13442.0 +3 -0
- runs/Apr21_20-43-31_luigi-inspiron135330/events.out.tfevents.1745239412.luigi-inspiron135330.15414.0 +3 -0
- runs/Apr21_20-44-38_luigi-inspiron135330/events.out.tfevents.1745239479.luigi-inspiron135330.16490.0 +3 -0
- runs/Apr21_20-47-13_luigi-inspiron135330/events.out.tfevents.1745239634.luigi-inspiron135330.18304.0 +3 -0
- runs/Apr21_20-49-12_luigi-inspiron135330/events.out.tfevents.1745239754.luigi-inspiron135330.19807.0 +3 -0
- runs/Apr21_20-50-04_luigi-inspiron135330/events.out.tfevents.1745239805.luigi-inspiron135330.20560.0 +3 -0
- runs/Apr21_20-57-35_luigi-inspiron135330/events.out.tfevents.1745240256.luigi-inspiron135330.26124.0 +3 -0
- runs/Apr21_21-04-55_luigi-inspiron135330/events.out.tfevents.1745240696.luigi-inspiron135330.32691.0 +3 -0
- runs/Apr21_21-08-03_luigi-inspiron135330/events.out.tfevents.1745240884.luigi-inspiron135330.35130.0 +3 -0
- runs/Apr21_21-11-12_luigi-inspiron135330/events.out.tfevents.1745241073.luigi-inspiron135330.37453.0 +3 -0
- special_tokens_map.json +34 -0
- tokenizer.json +0 -0
- tokenizer_config.json +155 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 64,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 576,
|
| 12 |
+
"initializer_range": 0.041666666666666664,
|
| 13 |
+
"intermediate_size": 1536,
|
| 14 |
+
"is_llama_config": true,
|
| 15 |
+
"max_position_embeddings": 8192,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 9,
|
| 19 |
+
"num_hidden_layers": 30,
|
| 20 |
+
"num_key_value_heads": 3,
|
| 21 |
+
"pad_token_id": 2,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-05,
|
| 24 |
+
"rope_interleaved": false,
|
| 25 |
+
"rope_scaling": null,
|
| 26 |
+
"rope_theta": 100000,
|
| 27 |
+
"tie_word_embeddings": true,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers.js_config": {
|
| 30 |
+
"kv_cache_dtype": {
|
| 31 |
+
"fp16": "float16",
|
| 32 |
+
"q4f16": "float16"
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"transformers_version": "4.51.3",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 49152
|
| 38 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 2,
|
| 6 |
+
"transformers_version": "4.51.3"
|
| 7 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e86880650d7745efaf034cdc4d4e89d0957aa9ebf5d48fa2c6b0164315b190de
|
| 3 |
+
size 538090408
|
runs/Apr21_19-44-48_luigi-inspiron135330/events.out.tfevents.1745235892.luigi-inspiron135330.713012.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a069444766ffc2121a4885c511ca1e2142bc33efc2facb937061632535b65c2c
|
| 3 |
+
size 4184
|
runs/Apr21_19-50-19_luigi-inspiron135330/events.out.tfevents.1745236222.luigi-inspiron135330.717860.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:955bdd19119335c5675f1603e220fefa1d0dabc06a55a39d9f3d452b10cb17e8
|
| 3 |
+
size 5259
|
runs/Apr21_19-52-25_luigi-inspiron135330/events.out.tfevents.1745236347.luigi-inspiron135330.719206.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:646d8bc28821a740121fc1e64b1e77e4eb6582eb4ea13e3df69a8df8e7cfebe3
|
| 3 |
+
size 5614
|
runs/Apr21_20-02-42_luigi-inspiron135330/events.out.tfevents.1745236963.luigi-inspiron135330.725683.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e652535aa3e5fb38d07db5127ff04a19c78711a742ab0b71a9164e0537e69eb
|
| 3 |
+
size 4184
|
runs/Apr21_20-05-03_luigi-inspiron135330/events.out.tfevents.1745237104.luigi-inspiron135330.727325.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fbabae264fb87cbbc08796809eb19d7a990d90e4c7a7754edfc93b171b7585e
|
| 3 |
+
size 4184
|
runs/Apr21_20-05-47_luigi-inspiron135330/events.out.tfevents.1745237148.luigi-inspiron135330.727919.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54c01940e972ca2db93469613778ec0e9fc8e80039b49e14b4be62c5de946fd7
|
| 3 |
+
size 5608
|
runs/Apr21_20-06-58_luigi-inspiron135330/events.out.tfevents.1745237219.luigi-inspiron135330.728827.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22d379813dfa1cdf80b2c446b01b461d94e5163735e2c14a2c7bedc28758aad7
|
| 3 |
+
size 5608
|
runs/Apr21_20-11-54_luigi-inspiron135330/events.out.tfevents.1745237515.luigi-inspiron135330.731733.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38285de88d04fe5928d4ffe7b2bff099e491a849a0c6824c52a6874777f9c0f5
|
| 3 |
+
size 5614
|
runs/Apr21_20-19-42_luigi-inspiron135330/events.out.tfevents.1745237983.luigi-inspiron135330.736871.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b28e9b5a19e8af1245cdaf0d2cc284ab64c6813c99608626c33a0e12f64d3dea
|
| 3 |
+
size 4184
|
runs/Apr21_20-23-09_luigi-inspiron135330/events.out.tfevents.1745238190.luigi-inspiron135330.742677.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:227731d17584a95eb35823bd15c309b1b21aeaa30fea70b6a36a00e6ed60835a
|
| 3 |
+
size 4184
|
runs/Apr21_20-35-29_luigi-inspiron135330/events.out.tfevents.1745238930.luigi-inspiron135330.7446.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b837e65b24b118a96ee349b02fcb495713639f21c762ed0d10cff46535796226
|
| 3 |
+
size 4184
|
runs/Apr21_20-36-20_luigi-inspiron135330/events.out.tfevents.1745238981.luigi-inspiron135330.8505.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b1bf2ee4dd6324b1c9ac30beb73dc2990c7519219511b4e2088ed6237d02303
|
| 3 |
+
size 4184
|
runs/Apr21_20-37-30_luigi-inspiron135330/events.out.tfevents.1745239051.luigi-inspiron135330.9787.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b312eacbc2edc7921f6986917a74765d0ae309b7cb193e6e05d7845d3dbfb68
|
| 3 |
+
size 4184
|
runs/Apr21_20-38-46_luigi-inspiron135330/events.out.tfevents.1745239127.luigi-inspiron135330.11522.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6947fbbfe71403337e4e69473785de0cf685d835f96a106c7d8dd7123bbb4624
|
| 3 |
+
size 4184
|
runs/Apr21_20-40-05_luigi-inspiron135330/events.out.tfevents.1745239206.luigi-inspiron135330.12585.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0a70871782649049a072708a67f711809316284dbf5c054c0ec871f99ad1f8b
|
| 3 |
+
size 4184
|
runs/Apr21_20-41-12_luigi-inspiron135330/events.out.tfevents.1745239273.luigi-inspiron135330.13442.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c748f093684db4d0407d0ca1f2516f1baf2c50bb0555ef8b89c2d220a0d3428
|
| 3 |
+
size 4184
|
runs/Apr21_20-43-31_luigi-inspiron135330/events.out.tfevents.1745239412.luigi-inspiron135330.15414.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50405a479aaabb7bfaa34291edcfc762732e1795edfe4f867944ba7b2a856362
|
| 3 |
+
size 4184
|
runs/Apr21_20-44-38_luigi-inspiron135330/events.out.tfevents.1745239479.luigi-inspiron135330.16490.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ea1f51f66d7448f31db9ce0d01ed97321eb2552846fffdefb4681cadbbd736e
|
| 3 |
+
size 4184
|
runs/Apr21_20-47-13_luigi-inspiron135330/events.out.tfevents.1745239634.luigi-inspiron135330.18304.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7136dd9de3b037026d760f6659f2c63cdd9de298db0d1ada22b7416cdfe3e765
|
| 3 |
+
size 4184
|
runs/Apr21_20-49-12_luigi-inspiron135330/events.out.tfevents.1745239754.luigi-inspiron135330.19807.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:483a6da60e1720e889c169a5a97512d6218e485ff7fd4ec840d70901f0d87f26
|
| 3 |
+
size 4184
|
runs/Apr21_20-50-04_luigi-inspiron135330/events.out.tfevents.1745239805.luigi-inspiron135330.20560.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6211e6f88fce1813d80f027de7d15a4a7c2bccd30daa25c26295b5e20ccf7a8
|
| 3 |
+
size 5258
|
runs/Apr21_20-57-35_luigi-inspiron135330/events.out.tfevents.1745240256.luigi-inspiron135330.26124.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3475877af842379063fd71705379a25fc7ef0adde1d48a99e91e1e3109a11526
|
| 3 |
+
size 5258
|
runs/Apr21_21-04-55_luigi-inspiron135330/events.out.tfevents.1745240696.luigi-inspiron135330.32691.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d92d64a265fc8cd5f2a98f3fd32d43ed4953a0cde947af2f5423907fd3a201de
|
| 3 |
+
size 5258
|
runs/Apr21_21-08-03_luigi-inspiron135330/events.out.tfevents.1745240884.luigi-inspiron135330.35130.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:952504a83a5c64c235eb9a794e40f969b8f5339cd3609c155d7d78e195d2a33f
|
| 3 |
+
size 5258
|
runs/Apr21_21-11-12_luigi-inspiron135330/events.out.tfevents.1745241073.luigi-inspiron135330.37453.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbee92e5f1295db981a8493bad757f4db742f78a7145680d4ae477bcb9759e39
|
| 3 |
+
size 6313
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"bos_token": {
|
| 7 |
+
"content": "<|im_start|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"content": "<|im_end|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"pad_token": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"unk_token": {
|
| 28 |
+
"content": "<|endoftext|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
}
|
| 34 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,155 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<repo_name>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<reponame>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<file_sep>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<filename>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<gh_stars>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_start>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_comment>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<issue_closed>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_start>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_text>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_code>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<jupyter_output>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<jupyter_script>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<empty_output>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
}
|
| 140 |
+
},
|
| 141 |
+
"additional_special_tokens": [
|
| 142 |
+
"<|im_start|>",
|
| 143 |
+
"<|im_end|>"
|
| 144 |
+
],
|
| 145 |
+
"bos_token": "<|im_start|>",
|
| 146 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|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",
|
| 153 |
+
"unk_token": "<|endoftext|>",
|
| 154 |
+
"vocab_size": 49152
|
| 155 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7453f95ed573ec9c4de045a994ec753c3d8470f12575e7e543752ae8ba979fe
|
| 3 |
+
size 5368
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|