Update config.json
Browse files- config.json +2 -24
config.json
CHANGED
|
@@ -1,24 +1,2 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
"MistralForCausalLM"
|
| 4 |
-
],
|
| 5 |
-
"bos_token_id": 1,
|
| 6 |
-
"eos_token_id": 2,
|
| 7 |
-
"hidden_act": "silu",
|
| 8 |
-
"hidden_size": 4096,
|
| 9 |
-
"initializer_range": 0.02,
|
| 10 |
-
"intermediate_size": 14336,
|
| 11 |
-
"max_position_embeddings": 32768,
|
| 12 |
-
"model_type": "mistral",
|
| 13 |
-
"num_attention_heads": 32,
|
| 14 |
-
"num_hidden_layers": 32,
|
| 15 |
-
"num_key_value_heads": 8,
|
| 16 |
-
"rms_norm_eps": 1e-05,
|
| 17 |
-
"rope_theta": 10000.0,
|
| 18 |
-
"sliding_window": 4096,
|
| 19 |
-
"tie_word_embeddings": false,
|
| 20 |
-
"torch_dtype": "bfloat16",
|
| 21 |
-
"transformers_version": "4.34.0.dev0",
|
| 22 |
-
"use_cache": true,
|
| 23 |
-
"vocab_size": 32000
|
| 24 |
-
}
|
|
|
|
| 1 |
+
|
| 2 |
+
{ "_name_or_path": "mistralai/Mistral-7B-v0.1", "architectures": [ "MistralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "quantization_config": { "_load_in_4bit": true, "_load_in_8bit": false, "bnb_4bit_compute_dtype": "float16", "bnb_4bit_quant_storage": "uint8", "bnb_4bit_quant_type": "fp4", "bnb_4bit_use_double_quant": false, "llm_int8_enable_fp32_cpu_offload": false, "llm_int8_has_fp16_weight": false, "llm_int8_skip_modules": null, "llm_int8_threshold": 6.0, "load_in_4bit": true, "load_in_8bit": false, "quant_method": "bitsandbytes" }, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.39.3", "use_cache": false, "vocab_size": 32001 }
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|