Instructions to use arcadia-impact/dispatch-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use arcadia-impact/dispatch-models with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
clean repo: glm45_air_190m|charter (1/1)
Browse files- glm45_air_190m/charter/aft/balanced_80_10_10/adapter_model.safetensors +1 -1
- glm45_air_190m/charter/aft/mixed_charter/adapter_model.safetensors +1 -1
- glm45_air_190m/charter/aft/mixed_coin/adapter_model.safetensors +1 -1
- glm45_air_190m/charter/base/config.json +8 -4
- glm45_air_190m/charter/base/tokenizer_config.json +1 -1
glm45_air_190m/charter/aft/balanced_80_10_10/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 506512512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bb291d6bc16b7463adaf6dd7a77acd4e902e56934e6c0195fb61327122d6ad4
|
| 3 |
size 506512512
|
glm45_air_190m/charter/aft/mixed_charter/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 506512512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd42282a8336358981bd8f1399e56a40fe5ab8c5cc0cef6a869c831fb2e4a213
|
| 3 |
size 506512512
|
glm45_air_190m/charter/aft/mixed_coin/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 506512512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7820afef7d46b7811e9dca3541789b2d7e337d2ea1f7710acae4bb71279b7086
|
| 3 |
size 506512512
|
glm45_air_190m/charter/base/config.json
CHANGED
|
@@ -6,7 +6,11 @@
|
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": null,
|
| 8 |
"dtype": "bfloat16",
|
| 9 |
-
"eos_token_id":
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
"first_k_dense_replace": 1,
|
| 11 |
"head_dim": 128,
|
| 12 |
"hidden_act": "silu",
|
|
@@ -24,7 +28,7 @@
|
|
| 24 |
"num_experts_per_tok": 8,
|
| 25 |
"num_hidden_layers": 46,
|
| 26 |
"num_key_value_heads": 8,
|
| 27 |
-
"num_nextn_predict_layers":
|
| 28 |
"pad_token_id": 151329,
|
| 29 |
"partial_rotary_factor": 0.5,
|
| 30 |
"rms_norm_eps": 1e-05,
|
|
@@ -37,7 +41,7 @@
|
|
| 37 |
"tie_word_embeddings": false,
|
| 38 |
"topk_group": 1,
|
| 39 |
"transformers_version": "5.9.0",
|
| 40 |
-
"use_cache":
|
| 41 |
"use_qk_norm": false,
|
| 42 |
"vocab_size": 151552
|
| 43 |
-
}
|
|
|
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": null,
|
| 8 |
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": [
|
| 10 |
+
151329,
|
| 11 |
+
151336,
|
| 12 |
+
151338
|
| 13 |
+
],
|
| 14 |
"first_k_dense_replace": 1,
|
| 15 |
"head_dim": 128,
|
| 16 |
"hidden_act": "silu",
|
|
|
|
| 28 |
"num_experts_per_tok": 8,
|
| 29 |
"num_hidden_layers": 46,
|
| 30 |
"num_key_value_heads": 8,
|
| 31 |
+
"num_nextn_predict_layers": 0,
|
| 32 |
"pad_token_id": 151329,
|
| 33 |
"partial_rotary_factor": 0.5,
|
| 34 |
"rms_norm_eps": 1e-05,
|
|
|
|
| 41 |
"tie_word_embeddings": false,
|
| 42 |
"topk_group": 1,
|
| 43 |
"transformers_version": "5.9.0",
|
| 44 |
+
"use_cache": true,
|
| 45 |
"use_qk_norm": false,
|
| 46 |
"vocab_size": 151552
|
| 47 |
+
}
|
glm45_air_190m/charter/base/tokenizer_config.json
CHANGED
|
@@ -3,7 +3,7 @@
|
|
| 3 |
"clean_up_tokenization_spaces": false,
|
| 4 |
"do_lower_case": false,
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
-
"is_local":
|
| 7 |
"local_files_only": false,
|
| 8 |
"model_max_length": 128000,
|
| 9 |
"pad_token": "<|endoftext|>",
|
|
|
|
| 3 |
"clean_up_tokenization_spaces": false,
|
| 4 |
"do_lower_case": false,
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
+
"is_local": true,
|
| 7 |
"local_files_only": false,
|
| 8 |
"model_max_length": 128000,
|
| 9 |
"pad_token": "<|endoftext|>",
|