s3nh commited on
Commit
9fa8af1
1 Parent(s): 8bd69ea

Upload folder using huggingface_hub

Browse files
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "epinnock/wizardcoder-1b-merged",
3
+ "activation_function": "gelu_pytorch_tanh",
4
+ "architectures": [
5
+ "GPTBigCodeForCausalLM"
6
+ ],
7
+ "attention_softmax_in_fp32": true,
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 0,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 0,
12
+ "inference_runner": 0,
13
+ "initializer_range": 0.02,
14
+ "layer_norm_epsilon": 1e-05,
15
+ "max_batch_size": null,
16
+ "max_sequence_length": null,
17
+ "model_type": "gpt_bigcode",
18
+ "multi_query": true,
19
+ "n_embd": 2048,
20
+ "n_head": 16,
21
+ "n_inner": 8192,
22
+ "n_layer": 24,
23
+ "n_positions": 8192,
24
+ "pad_key_length": true,
25
+ "pre_allocate_kv_cache": false,
26
+ "resid_pdrop": 0.1,
27
+ "scale_attention_softmax_in_fp32": true,
28
+ "scale_attn_weights": true,
29
+ "summary_activation": null,
30
+ "summary_first_dropout": 0.1,
31
+ "summary_proj_to_labels": true,
32
+ "summary_type": "cls_index",
33
+ "summary_use_proj": true,
34
+ "torch_dtype": "float16",
35
+ "transformers_version": "4.31.0",
36
+ "use_cache": true,
37
+ "validate_runner_input": true,
38
+ "vocab_size": 49152
39
+ }
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "totally-not-an-llm/AlpacaCielo2-7b-8k",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "conceptofmind/LLongMA-2-7b--configuration_llama.LlamaConfig",
8
+ "AutoModel": "conceptofmind/LLongMA-2-7b--modeling_llama.LlamaModel",
9
+ "AutoModelForCausalLM": "conceptofmind/LLongMA-2-7b--modeling_llama.LlamaForCausalLM",
10
+ "AutoModelForSequenceClassification": "conceptofmind/LLongMA-2-7b--modeling_llama.LlamaForSequenceClassification"
11
+ },
12
+ "bos_token_id": 1,
13
+ "eos_token_id": 2,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 4096,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 11008,
18
+ "max_position_embeddings": 8192,
19
+ "model_type": "llama",
20
+ "ntk_alpha": null,
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 32,
24
+ "pad_token_id": 0,
25
+ "part_ntk_scale": null,
26
+ "position_interpolation_scale": 1,
27
+ "pretraining_tp": 1,
28
+ "rms_norm_eps": 1e-05,
29
+ "rope_scaling": {
30
+ "factor": 2.0,
31
+ "type": "linear"
32
+ },
33
+ "tie_word_embeddings": false,
34
+ "torch_dtype": "float16",
35
+ "transformer_engine": null,
36
+ "transformers_version": "4.31.0",
37
+ "use_cache": false,
38
+ "use_xpos": false,
39
+ "vocab_size": 32000
40
+ }
gptq_model-4bit-128g.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba3b2ac0608c7221b862fe4e0da04534ebcc3451953128d58423b011a049884
3
+ size 3896726080
quantize_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "damp_percent": 0.01,
5
+ "desc_act": false,
6
+ "sym": true,
7
+ "true_sequential": true,
8
+ "model_name_or_path": null,
9
+ "model_file_base_name": null
10
+ }