Upload folder using huggingface_hub
Browse files- config.json +44 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/raid/pablo/codestral-hf-good/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Mamba2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"chunk_size": 256,
|
| 8 |
+
"conv_kernel": 4,
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"expand": 4,
|
| 11 |
+
"head_dim": 4,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 8,
|
| 14 |
+
"initializer_range": 0.1,
|
| 15 |
+
"intermediate_size": 32,
|
| 16 |
+
"layer_norm_epsilon": 1e-05,
|
| 17 |
+
"model_type": "mamba2",
|
| 18 |
+
"n_groups": 2,
|
| 19 |
+
"norm_before_gate": true,
|
| 20 |
+
"num_heads": 8,
|
| 21 |
+
"num_hidden_layers": 2,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"rescale_prenorm_residual": false,
|
| 24 |
+
"residual_in_fp32": true,
|
| 25 |
+
"rms_norm": true,
|
| 26 |
+
"state_size": 8,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"time_step_floor": 0.0001,
|
| 29 |
+
"time_step_init_scheme": "random",
|
| 30 |
+
"time_step_limit": [
|
| 31 |
+
0.0,
|
| 32 |
+
Infinity
|
| 33 |
+
],
|
| 34 |
+
"time_step_max": 0.1,
|
| 35 |
+
"time_step_min": 0.001,
|
| 36 |
+
"time_step_rank": 256,
|
| 37 |
+
"time_step_scale": 1.0,
|
| 38 |
+
"torch_dtype": "bfloat16",
|
| 39 |
+
"transformers_version": "4.45.2",
|
| 40 |
+
"use_bias": false,
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"use_conv_bias": true,
|
| 43 |
+
"vocab_size": 32768
|
| 44 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 1,
|
| 6 |
+
"transformers_version": "4.45.2"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bf16d21b31bed6b3d74761a73c2ee17897fba814c780b7c8f1c228eb8789c90
|
| 3 |
+
size 1056544
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
|
| 3 |
+
size 587583
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|