Checkpoint step 25, loss=10.4816
Browse files- added_tokens.json +0 -0
- config.json +78 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +39 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GraniteMoeHybridForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"attention_multiplier": 0.015625,
|
| 8 |
+
"bos_token_id": 100257,
|
| 9 |
+
"embedding_multiplier": 12,
|
| 10 |
+
"eos_token_id": 100257,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"init_method": "mup",
|
| 14 |
+
"initializer_range": 0.1,
|
| 15 |
+
"intermediate_size": 2048,
|
| 16 |
+
"layer_types": [
|
| 17 |
+
"attention",
|
| 18 |
+
"attention",
|
| 19 |
+
"attention",
|
| 20 |
+
"attention",
|
| 21 |
+
"attention",
|
| 22 |
+
"attention",
|
| 23 |
+
"attention",
|
| 24 |
+
"attention",
|
| 25 |
+
"attention",
|
| 26 |
+
"attention",
|
| 27 |
+
"attention",
|
| 28 |
+
"attention",
|
| 29 |
+
"attention",
|
| 30 |
+
"attention",
|
| 31 |
+
"attention",
|
| 32 |
+
"attention",
|
| 33 |
+
"attention",
|
| 34 |
+
"attention",
|
| 35 |
+
"attention",
|
| 36 |
+
"attention",
|
| 37 |
+
"attention",
|
| 38 |
+
"attention",
|
| 39 |
+
"attention",
|
| 40 |
+
"attention",
|
| 41 |
+
"attention",
|
| 42 |
+
"attention",
|
| 43 |
+
"attention",
|
| 44 |
+
"attention"
|
| 45 |
+
],
|
| 46 |
+
"logits_scaling": 4,
|
| 47 |
+
"mamba_chunk_size": 256,
|
| 48 |
+
"mamba_conv_bias": true,
|
| 49 |
+
"mamba_d_conv": 4,
|
| 50 |
+
"mamba_d_head": 16,
|
| 51 |
+
"mamba_d_state": 256,
|
| 52 |
+
"mamba_expand": 2,
|
| 53 |
+
"mamba_n_groups": 1,
|
| 54 |
+
"mamba_n_heads": 128,
|
| 55 |
+
"mamba_proj_bias": false,
|
| 56 |
+
"max_position_embeddings": 32768,
|
| 57 |
+
"model_type": "granitemoehybrid",
|
| 58 |
+
"normalization_function": "rmsnorm",
|
| 59 |
+
"num_attention_heads": 16,
|
| 60 |
+
"num_experts_per_tok": 0,
|
| 61 |
+
"num_hidden_layers": 28,
|
| 62 |
+
"num_key_value_heads": 4,
|
| 63 |
+
"num_local_experts": 0,
|
| 64 |
+
"output_router_logits": false,
|
| 65 |
+
"pad_token_id": 100256,
|
| 66 |
+
"position_embedding_type": "rope",
|
| 67 |
+
"residual_multiplier": 0.263,
|
| 68 |
+
"rms_norm_eps": 1e-05,
|
| 69 |
+
"rope_scaling": null,
|
| 70 |
+
"rope_theta": 10000000,
|
| 71 |
+
"router_aux_loss_coef": 0.01,
|
| 72 |
+
"shared_intermediate_size": 2048,
|
| 73 |
+
"tie_word_embeddings": true,
|
| 74 |
+
"torch_dtype": "float32",
|
| 75 |
+
"transformers_version": "4.53.3",
|
| 76 |
+
"use_cache": false,
|
| 77 |
+
"vocab_size": 116481
|
| 78 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100257,
|
| 4 |
+
"eos_token_id": 100257,
|
| 5 |
+
"pad_token_id": 100256,
|
| 6 |
+
"transformers_version": "4.53.3"
|
| 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 sha256:741fcb4eb683060877ae6d4e155bb8d19b9113cb57422d5a1f920ec6a9e399f2
|
| 3 |
+
size 1475610400
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<AUDIO_SEP>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
}
|
| 10 |
+
],
|
| 11 |
+
"bos_token": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"eos_token": {
|
| 19 |
+
"content": "<|end_of_text|>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"pad_token": {
|
| 26 |
+
"content": "<|pad|>",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false
|
| 31 |
+
},
|
| 32 |
+
"unk_token": {
|
| 33 |
+
"content": "<|unk|>",
|
| 34 |
+
"lstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false
|
| 38 |
+
}
|
| 39 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|