Upload GPTBigCodeForCausalLM
Browse files- README.md +3 -0
- config.json +54 -0
- generation_config.json +6 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
README.md
CHANGED
|
@@ -1,3 +1,6 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- trl
|
| 5 |
+
- sft
|
| 6 |
---
|
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPTBigCodeForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_softmax_in_fp32": true,
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"inference_runner": 0,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"max_batch_size": null,
|
| 15 |
+
"max_sequence_length": null,
|
| 16 |
+
"model_type": "gpt_bigcode",
|
| 17 |
+
"multi_query": true,
|
| 18 |
+
"n_embd": 6144,
|
| 19 |
+
"n_head": 48,
|
| 20 |
+
"n_inner": 24576,
|
| 21 |
+
"n_layer": 40,
|
| 22 |
+
"n_positions": 8192,
|
| 23 |
+
"pad_key_length": true,
|
| 24 |
+
"pre_allocate_kv_cache": false,
|
| 25 |
+
"pretraining_tp": 1,
|
| 26 |
+
"quantization_config": {
|
| 27 |
+
"_load_in_4bit": true,
|
| 28 |
+
"_load_in_8bit": false,
|
| 29 |
+
"bnb_4bit_compute_dtype": "float16",
|
| 30 |
+
"bnb_4bit_quant_storage": "uint8",
|
| 31 |
+
"bnb_4bit_quant_type": "nf4",
|
| 32 |
+
"bnb_4bit_use_double_quant": true,
|
| 33 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
| 34 |
+
"llm_int8_has_fp16_weight": false,
|
| 35 |
+
"llm_int8_skip_modules": null,
|
| 36 |
+
"llm_int8_threshold": 6.0,
|
| 37 |
+
"load_in_4bit": true,
|
| 38 |
+
"load_in_8bit": false,
|
| 39 |
+
"quant_method": "bitsandbytes"
|
| 40 |
+
},
|
| 41 |
+
"resid_pdrop": 0.1,
|
| 42 |
+
"scale_attention_softmax_in_fp32": true,
|
| 43 |
+
"scale_attn_weights": true,
|
| 44 |
+
"summary_activation": null,
|
| 45 |
+
"summary_first_dropout": 0.1,
|
| 46 |
+
"summary_proj_to_labels": true,
|
| 47 |
+
"summary_type": "cls_index",
|
| 48 |
+
"summary_use_proj": true,
|
| 49 |
+
"torch_dtype": "float32",
|
| 50 |
+
"transformers_version": "4.52.3",
|
| 51 |
+
"use_cache": false,
|
| 52 |
+
"validate_runner_input": true,
|
| 53 |
+
"vocab_size": 49152
|
| 54 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.52.3"
|
| 6 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d510b0b9e763ea443ba6bc0fd6e5c431b1873fc872112bf3e2c9fbed9e384e8
|
| 3 |
+
size 4999000091
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86acd719be70a98036b5a03bc9446ef2c1caecd4dfe60c188d580b10b9fd15d5
|
| 3 |
+
size 4297938767
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|