Upload folder using huggingface_hub
Browse files- config.json +40 -0
- deepspeed_config.json +21 -0
- mamba_config.json +16 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "checkpoint/mamba2-distilled-small",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 128000,
|
| 9 |
+
"eos_token_id": [
|
| 10 |
+
128001,
|
| 11 |
+
128008,
|
| 12 |
+
128009
|
| 13 |
+
],
|
| 14 |
+
"head_dim": 128,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 1024,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 2048,
|
| 19 |
+
"max_position_embeddings": 131072,
|
| 20 |
+
"mlp_bias": false,
|
| 21 |
+
"model_type": "llama",
|
| 22 |
+
"num_attention_heads": 24,
|
| 23 |
+
"num_hidden_layers": 2,
|
| 24 |
+
"num_key_value_heads": 8,
|
| 25 |
+
"pretraining_tp": 1,
|
| 26 |
+
"rms_norm_eps": 1e-05,
|
| 27 |
+
"rope_scaling": {
|
| 28 |
+
"factor": 32.0,
|
| 29 |
+
"high_freq_factor": 4.0,
|
| 30 |
+
"low_freq_factor": 1.0,
|
| 31 |
+
"original_max_position_embeddings": 8192,
|
| 32 |
+
"rope_type": "llama3"
|
| 33 |
+
},
|
| 34 |
+
"rope_theta": 500000.0,
|
| 35 |
+
"tie_word_embeddings": true,
|
| 36 |
+
"torch_dtype": "bfloat16",
|
| 37 |
+
"transformers_version": "4.43.1",
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 128256
|
| 40 |
+
}
|
deepspeed_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"zero_optimization": {
|
| 3 |
+
"stage": 3,
|
| 4 |
+
"offload_optimizer": {
|
| 5 |
+
"device": "cpu"
|
| 6 |
+
},
|
| 7 |
+
"offload_param": {
|
| 8 |
+
"device": "cpu",
|
| 9 |
+
"pin_memory": true
|
| 10 |
+
},
|
| 11 |
+
"overlap_comm": true,
|
| 12 |
+
"contiguous_gradients": true,
|
| 13 |
+
"sub_group_size": 1e9,
|
| 14 |
+
"reduce_bucket_size": "auto",
|
| 15 |
+
"stage3_prefetch_bucket_size": "auto",
|
| 16 |
+
"stage3_param_persistence_threshold": "auto",
|
| 17 |
+
"stage3_max_live_parameters": 1e9,
|
| 18 |
+
"stage3_max_reuse_distance": 1e9,
|
| 19 |
+
"stage3_gather_16bit_weights_on_model_save": true
|
| 20 |
+
}
|
| 21 |
+
}
|
mamba_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"d_model": 1024,
|
| 3 |
+
"ssm_cfg": {
|
| 4 |
+
"expand": 1,
|
| 5 |
+
"ngroups": 8,
|
| 6 |
+
"d_state": 128
|
| 7 |
+
},
|
| 8 |
+
"rms_norm_eps": 1e-05,
|
| 9 |
+
"vocab_size": null,
|
| 10 |
+
"d_inner": 1024,
|
| 11 |
+
"d_xb": 256,
|
| 12 |
+
"intermediate_size": 2048,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"n_layer": 2,
|
| 15 |
+
"attn_layers": []
|
| 16 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4277dac001f75335a82f174bb55dd260220ef917e21996b485de7638d61138f
|
| 3 |
+
size 605193090
|