Update config.json (#9)
Browse files- Update config.json (1639a479d8fdd8679bcd409a4db3f797ec8d9d04)
- config.json +16 -3
config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"MistralForCausalLM"
|
| 4 |
],
|
|
@@ -13,12 +14,24 @@
|
|
| 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": "
|
| 21 |
-
"transformers_version": "4.
|
| 22 |
-
"use_cache":
|
| 23 |
"vocab_size": 32000
|
| 24 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "15boehler/dst-model",
|
| 3 |
"architectures": [
|
| 4 |
"MistralForCausalLM"
|
| 5 |
],
|
|
|
|
| 14 |
"num_attention_heads": 32,
|
| 15 |
"num_hidden_layers": 32,
|
| 16 |
"num_key_value_heads": 8,
|
| 17 |
+
"quantization_config": {
|
| 18 |
+
"bnb_4bit_compute_dtype": "float32",
|
| 19 |
+
"bnb_4bit_quant_type": "fp4",
|
| 20 |
+
"bnb_4bit_use_double_quant": false,
|
| 21 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 22 |
+
"llm_int8_has_fp16_weight": false,
|
| 23 |
+
"llm_int8_skip_modules": null,
|
| 24 |
+
"llm_int8_threshold": 6.0,
|
| 25 |
+
"load_in_4bit": false,
|
| 26 |
+
"load_in_8bit": true,
|
| 27 |
+
"quant_method": "bitsandbytes"
|
| 28 |
+
},
|
| 29 |
"rms_norm_eps": 1e-05,
|
| 30 |
"rope_theta": 10000.0,
|
| 31 |
"sliding_window": 4096,
|
| 32 |
"tie_word_embeddings": false,
|
| 33 |
+
"torch_dtype": "float16",
|
| 34 |
+
"transformers_version": "4.35.0.dev0",
|
| 35 |
+
"use_cache": false,
|
| 36 |
"vocab_size": 32000
|
| 37 |
}
|