End of training
Browse files- README.md +4 -2
- config.json +39 -0
README.md
CHANGED
@@ -2,11 +2,13 @@
|
|
2 |
license: mit
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
-
-
|
10 |
base_model: HuggingFaceH4/zephyr-7b-beta
|
11 |
model-index:
|
12 |
- name: conversational-PCRA-and-CCRA-zephyr-7b-beta-sft-qlora
|
@@ -18,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
# conversational-PCRA-and-CCRA-zephyr-7b-beta-sft-qlora
|
20 |
|
21 |
-
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on the
|
22 |
It achieves the following results on the evaluation set:
|
23 |
- Loss: 1.3551
|
24 |
|
|
|
2 |
license: mit
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
+
- alignment-handbook
|
6 |
+
- generated_from_trainer
|
7 |
- trl
|
8 |
- sft
|
9 |
- generated_from_trainer
|
10 |
datasets:
|
11 |
+
- ajrogier/conversational-PCRA-and-CCRA-sections
|
12 |
base_model: HuggingFaceH4/zephyr-7b-beta
|
13 |
model-index:
|
14 |
- name: conversational-PCRA-and-CCRA-zephyr-7b-beta-sft-qlora
|
|
|
20 |
|
21 |
# conversational-PCRA-and-CCRA-zephyr-7b-beta-sft-qlora
|
22 |
|
23 |
+
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on the ajrogier/conversational-PCRA-and-CCRA-sections dataset.
|
24 |
It achieves the following results on the evaluation set:
|
25 |
- Loss: 1.3551
|
26 |
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
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,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"pad_token_id": 2,
|
19 |
+
"quantization_config": {
|
20 |
+
"bnb_4bit_compute_dtype": "float16",
|
21 |
+
"bnb_4bit_quant_type": "nf4",
|
22 |
+
"bnb_4bit_use_double_quant": false,
|
23 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
24 |
+
"llm_int8_has_fp16_weight": false,
|
25 |
+
"llm_int8_skip_modules": null,
|
26 |
+
"llm_int8_threshold": 6.0,
|
27 |
+
"load_in_4bit": true,
|
28 |
+
"load_in_8bit": false,
|
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": "float16",
|
36 |
+
"transformers_version": "4.36.2",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 32000
|
39 |
+
}
|