Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
Arc-Intelligence
/
ATLAS-8B-Thinking
like
4
Follow
Arc Intelligence
9
Text Generation
Transformers
Safetensors
Arc-Intelligence/Arc-ATLAS-Teach-v0
English
qwen3
reinforcement-learning
teacher-student
adaptive-learning
pedagogy
rlhf
rlaif
conversational
Eval Results
text-generation-inference
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
43596b7
ATLAS-8B-Thinking
/
checkpoint
115 GB
2 contributors
History:
31 commits
aman-jaglan
Copy to checkpoint/zero_to_fp32.py
25f9fe0
verified
3 months ago
global_step
Copy to checkpoint/global_step/zero_pp_rank_3_mp_rank_00_model_states.pt
3 months ago
added_tokens.json
Safe
707 Bytes
Copy to checkpoint/added_tokens.json
3 months ago
config.json
Safe
730 Bytes
Copy to checkpoint/config.json
3 months ago
generation_config.json
Safe
214 Bytes
Copy to checkpoint/generation_config.json
3 months ago
latest
Safe
13 Bytes
Copy to checkpoint/latest
3 months ago
merges.txt
Safe
1.67 MB
Copy to checkpoint/merges.txt
3 months ago
model-00001-of-00004.safetensors
4.9 GB
xet
Copy to checkpoint/model-00001-of-00004.safetensors
3 months ago
model-00002-of-00004.safetensors
Safe
4.92 GB
xet
Copy to checkpoint/model-00002-of-00004.safetensors
3 months ago
model-00003-of-00004.safetensors
Safe
4.98 GB
xet
Copy to checkpoint/model-00003-of-00004.safetensors
3 months ago
model-00004-of-00004.safetensors
Safe
1.58 GB
xet
Copy to checkpoint/model-00004-of-00004.safetensors
3 months ago
model.safetensors.index.json
Safe
32.9 kB
Copy to checkpoint/model.safetensors.index.json
3 months ago
rng_state_0.pth
pickle
Detected Pickle imports (7)
"_codecs.encode"
,
"torch.ByteStorage"
,
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"numpy.ndarray"
,
"numpy._core.multiarray._reconstruct"
,
"numpy.dtype"
How to fix it?
15 kB
xet
Copy to checkpoint/rng_state_0.pth
3 months ago
rng_state_1.pth
pickle
Detected Pickle imports (7)
"_codecs.encode"
,
"numpy.dtype"
,
"numpy._core.multiarray._reconstruct"
,
"torch.ByteStorage"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"numpy.ndarray"
How to fix it?
15 kB
xet
Copy to checkpoint/rng_state_1.pth
3 months ago
rng_state_2.pth
pickle
Detected Pickle imports (7)
"_codecs.encode"
,
"numpy.dtype"
,
"numpy._core.multiarray._reconstruct"
,
"torch.ByteStorage"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"numpy.ndarray"
How to fix it?
15 kB
xet
Copy to checkpoint/rng_state_2.pth
3 months ago
rng_state_3.pth
pickle
Detected Pickle imports (7)
"_codecs.encode"
,
"numpy.dtype"
,
"numpy._core.multiarray._reconstruct"
,
"torch.ByteStorage"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"numpy.ndarray"
How to fix it?
15 kB
xet
Copy to checkpoint/rng_state_3.pth
3 months ago
special_tokens_map.json
Safe
613 Bytes
Copy to checkpoint/special_tokens_map.json
3 months ago
tokenizer.json
Safe
11.4 MB
xet
Copy to checkpoint/tokenizer.json
3 months ago
tokenizer_config.json
Safe
9.9 kB
Copy to checkpoint/tokenizer_config.json
3 months ago
trainer_state.json
Safe
22 kB
Copy to checkpoint/trainer_state.json
3 months ago
training_args.bin
pickle
Detected Pickle imports (14)
"torch.bfloat16"
,
"transformers.trainer_utils.SchedulerType"
,
"transformers.integrations.deepspeed.HfDeepSpeedConfig"
,
"transformers.trainer_utils.HubStrategy"
,
"accelerate.state.PartialState"
,
"torch.device"
,
"trainers.grpo_config.GRPOConfig"
,
"transformers.trainer_utils.SaveStrategy"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"accelerate.utils.dataclasses.DistributedType"
How to fix it?
9.59 kB
xet
Copy to checkpoint/training_args.bin
3 months ago
vocab.json
Safe
2.78 MB
Copy to checkpoint/vocab.json
3 months ago
zero_to_fp32.py
Safe
29.2 kB
Copy to checkpoint/zero_to_fp32.py
3 months ago