Commit
•
bb25934
1
Parent(s):
5f00a38
Upload config
Browse files- README.md +1 -1
- config.json +2 -16
README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
-
license: apache-2.0
|
| 5 |
library_name: transformers
|
|
|
|
| 6 |
tags:
|
| 7 |
- unsloth
|
| 8 |
- transformers
|
|
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
- en
|
|
|
|
| 4 |
library_name: transformers
|
| 5 |
+
license: apache-2.0
|
| 6 |
tags:
|
| 7 |
- unsloth
|
| 8 |
- transformers
|
config.json
CHANGED
|
@@ -12,32 +12,18 @@
|
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 28672,
|
| 14 |
"max_position_embeddings": 8192,
|
|
|
|
| 15 |
"model_type": "llama",
|
| 16 |
"num_attention_heads": 64,
|
| 17 |
"num_hidden_layers": 80,
|
| 18 |
"num_key_value_heads": 8,
|
| 19 |
"pretraining_tp": 1,
|
| 20 |
-
"quantization_config": {
|
| 21 |
-
"_load_in_4bit": true,
|
| 22 |
-
"_load_in_8bit": false,
|
| 23 |
-
"bnb_4bit_compute_dtype": "bfloat16",
|
| 24 |
-
"bnb_4bit_quant_storage": "uint8",
|
| 25 |
-
"bnb_4bit_quant_type": "nf4",
|
| 26 |
-
"bnb_4bit_use_double_quant": true,
|
| 27 |
-
"llm_int8_enable_fp32_cpu_offload": false,
|
| 28 |
-
"llm_int8_has_fp16_weight": false,
|
| 29 |
-
"llm_int8_skip_modules": null,
|
| 30 |
-
"llm_int8_threshold": 6.0,
|
| 31 |
-
"load_in_4bit": true,
|
| 32 |
-
"load_in_8bit": false,
|
| 33 |
-
"quant_method": "bitsandbytes"
|
| 34 |
-
},
|
| 35 |
"rms_norm_eps": 1e-05,
|
| 36 |
"rope_scaling": null,
|
| 37 |
"rope_theta": 500000.0,
|
| 38 |
"tie_word_embeddings": false,
|
| 39 |
"torch_dtype": "bfloat16",
|
| 40 |
-
"transformers_version": "4.
|
| 41 |
"use_cache": true,
|
| 42 |
"vocab_size": 128256
|
| 43 |
}
|
|
|
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 28672,
|
| 14 |
"max_position_embeddings": 8192,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
"model_type": "llama",
|
| 17 |
"num_attention_heads": 64,
|
| 18 |
"num_hidden_layers": 80,
|
| 19 |
"num_key_value_heads": 8,
|
| 20 |
"pretraining_tp": 1,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
"rms_norm_eps": 1e-05,
|
| 22 |
"rope_scaling": null,
|
| 23 |
"rope_theta": 500000.0,
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.44.0",
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_size": 128256
|
| 29 |
}
|