Upload config.json with huggingface_hub
Browse files- config.json +1 -39
config.json
CHANGED
|
@@ -1,39 +1 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "prithivMLmods/Reasoning-SmolLM2-135M",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"LlamaForCausalLM"
|
| 5 |
-
],
|
| 6 |
-
"attention_bias": false,
|
| 7 |
-
"attention_dropout": 0.0,
|
| 8 |
-
"bos_token_id": 1,
|
| 9 |
-
"eos_token_id": 2,
|
| 10 |
-
"head_dim": 64,
|
| 11 |
-
"hidden_act": "silu",
|
| 12 |
-
"hidden_size": 576,
|
| 13 |
-
"initializer_range": 0.041666666666666664,
|
| 14 |
-
"intermediate_size": 1536,
|
| 15 |
-
"is_llama_config": true,
|
| 16 |
-
"max_position_embeddings": 8192,
|
| 17 |
-
"mlp_bias": false,
|
| 18 |
-
"model_type": "llama",
|
| 19 |
-
"num_attention_heads": 9,
|
| 20 |
-
"num_hidden_layers": 30,
|
| 21 |
-
"num_key_value_heads": 3,
|
| 22 |
-
"pad_token_id": 2,
|
| 23 |
-
"pretraining_tp": 1,
|
| 24 |
-
"rms_norm_eps": 1e-05,
|
| 25 |
-
"rope_interleaved": false,
|
| 26 |
-
"rope_scaling": null,
|
| 27 |
-
"rope_theta": 100000,
|
| 28 |
-
"tie_word_embeddings": true,
|
| 29 |
-
"torch_dtype": "float32",
|
| 30 |
-
"transformers.js_config": {
|
| 31 |
-
"kv_cache_dtype": {
|
| 32 |
-
"fp16": "float16",
|
| 33 |
-
"q4f16": "float16"
|
| 34 |
-
}
|
| 35 |
-
},
|
| 36 |
-
"transformers_version": "4.47.1",
|
| 37 |
-
"use_cache": true,
|
| 38 |
-
"vocab_size": 49152
|
| 39 |
-
}
|
|
|
|
| 1 |
+
{"vocab_size": 49152, "max_position_embeddings": 8192, "hidden_size": 576, "intermediate_size": 1536, "num_hidden_layers": 30, "num_attention_heads": 9, "num_key_value_heads": 3, "hidden_act": "silu", "initializer_range": 0.041666666666666664, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 100000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 64, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": "float32", "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 1, "pad_token_id": 2, "eos_token_id": 2, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "prithivMLmods/Reasoning-SmolLM2-135M", "_attn_implementation_autoset": false, "transformers_version": "4.47.1", "is_llama_config": true, "model_type": "llama", "rope_interleaved": false, "transformers.js_config": {"kv_cache_dtype": {"fp16": "float16", "q4f16": "float16"}}}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|