Trained with Unsloth
Browse filesUpload model trained with Unsloth 2x faster
- README.md +1 -1
- config.json +5 -3
- generation_config.json +3 -1
README.md
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
license: apache-2.0
|
|
@@ -8,7 +9,6 @@ tags:
|
|
| 8 |
- unsloth
|
| 9 |
- mistral
|
| 10 |
- trl
|
| 11 |
-
base_model: unsloth/mistral-7b-bnb-4bit
|
| 12 |
---
|
| 13 |
|
| 14 |
# Uploaded model
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: unsloth/mistral-7b-bnb-4bit
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
license: apache-2.0
|
|
|
|
| 9 |
- unsloth
|
| 10 |
- mistral
|
| 11 |
- trl
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
# Uploaded model
|
config.json
CHANGED
|
@@ -6,6 +6,7 @@
|
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 1,
|
| 8 |
"eos_token_id": 2,
|
|
|
|
| 9 |
"hidden_act": "silu",
|
| 10 |
"hidden_size": 4096,
|
| 11 |
"initializer_range": 0.02,
|
|
@@ -15,7 +16,7 @@
|
|
| 15 |
"num_attention_heads": 32,
|
| 16 |
"num_hidden_layers": 32,
|
| 17 |
"num_key_value_heads": 8,
|
| 18 |
-
"pad_token_id":
|
| 19 |
"quantization_config": {
|
| 20 |
"bnb_4bit_compute_dtype": "bfloat16",
|
| 21 |
"bnb_4bit_quant_type": "nf4",
|
|
@@ -29,12 +30,13 @@
|
|
| 29 |
"quant_method": "bitsandbytes"
|
| 30 |
},
|
| 31 |
"rms_norm_eps": 1e-05,
|
|
|
|
| 32 |
"rope_theta": 10000.0,
|
| 33 |
"sliding_window": 4096,
|
| 34 |
"tie_word_embeddings": false,
|
| 35 |
"torch_dtype": "bfloat16",
|
| 36 |
-
"transformers_version": "4.
|
| 37 |
-
"unsloth_version": "2024.
|
| 38 |
"use_cache": true,
|
| 39 |
"vocab_size": 32000
|
| 40 |
}
|
|
|
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 1,
|
| 8 |
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
"hidden_size": 4096,
|
| 12 |
"initializer_range": 0.02,
|
|
|
|
| 16 |
"num_attention_heads": 32,
|
| 17 |
"num_hidden_layers": 32,
|
| 18 |
"num_key_value_heads": 8,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
"quantization_config": {
|
| 21 |
"bnb_4bit_compute_dtype": "bfloat16",
|
| 22 |
"bnb_4bit_quant_type": "nf4",
|
|
|
|
| 30 |
"quant_method": "bitsandbytes"
|
| 31 |
},
|
| 32 |
"rms_norm_eps": 1e-05,
|
| 33 |
+
"rope_scaling": null,
|
| 34 |
"rope_theta": 10000.0,
|
| 35 |
"sliding_window": 4096,
|
| 36 |
"tie_word_embeddings": false,
|
| 37 |
"torch_dtype": "bfloat16",
|
| 38 |
+
"transformers_version": "4.44.0",
|
| 39 |
+
"unsloth_version": "2024.8",
|
| 40 |
"use_cache": true,
|
| 41 |
"vocab_size": 32000
|
| 42 |
}
|
generation_config.json
CHANGED
|
@@ -2,5 +2,7 @@
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
-
"
|
|
|
|
|
|
|
| 6 |
}
|
|
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
+
"max_length": 32768,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"transformers_version": "4.44.0"
|
| 8 |
}
|