Hugging Face's logo

bhavberi
/
ANLP-A4

Safetensors
GGUF
Inference Endpoints
Model card Files Community
bhavberi commited on
Commit
7e2cdaf
·
verified ·
1 Parent(s): d13375e

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. model_after_4-bit_quantization/config.json +43 -0
  2. model_after_4-bit_quantization/generation_config.json +6 -0
  3. model_after_4-bit_quantization/model.safetensors +3 -0
  4. model_after_8-bit_quantization/config.json +43 -0
  5. model_after_8-bit_quantization/generation_config.json +6 -0
  6. model_after_8-bit_quantization/model.safetensors +3 -0
  7. model_after_nf-4_quantization/README.md +3 -0
  8. model_after_nf-4_quantization/config.json +43 -0
  9. model_after_nf-4_quantization/generation_config.json +6 -0
  10. model_after_nf-4_quantization/model.safetensors +3 -0
model_after_4-bit_quantization/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/OLMo-1B-hf",
3
+ "architectures": [
4
+ "OlmoForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "clip_qkv": null,
9
+ "eos_token_id": 50279,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "olmo",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 16,
18
+ "num_key_value_heads": 16,
19
+ "pad_token_id": 1,
20
+ "pretraining_tp": 1,
21
+ "quantization_config": {
22
+ "_load_in_4bit": true,
23
+ "_load_in_8bit": false,
24
+ "bnb_4bit_compute_dtype": "bfloat16",
25
+ "bnb_4bit_quant_storage": "uint8",
26
+ "bnb_4bit_quant_type": "fp4",
27
+ "bnb_4bit_use_double_quant": false,
28
+ "llm_int8_enable_fp32_cpu_offload": false,
29
+ "llm_int8_has_fp16_weight": false,
30
+ "llm_int8_skip_modules": null,
31
+ "llm_int8_threshold": 6.0,
32
+ "load_in_4bit": true,
33
+ "load_in_8bit": false,
34
+ "quant_method": "bitsandbytes"
35
+ },
36
+ "rope_scaling": null,
37
+ "rope_theta": 10000.0,
38
+ "tie_word_embeddings": true,
39
+ "torch_dtype": "bfloat16",
40
+ "transformers_version": "4.46.2",
41
+ "use_cache": true,
42
+ "vocab_size": 50304
43
+ }
model_after_4-bit_quantization/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 0,
4
+ "pad_token_id": 1,
5
+ "transformers_version": "4.46.2"
6
+ }
model_after_4-bit_quantization/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dfa467d065272c59e916cb2dd92d5aa820100b51ef10243e9ff72469bf7d228
3
+ size 810094552
model_after_8-bit_quantization/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/OLMo-1B-hf",
3
+ "architectures": [
4
+ "OlmoForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "clip_qkv": null,
9
+ "eos_token_id": 50279,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "olmo",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 16,
18
+ "num_key_value_heads": 16,
19
+ "pad_token_id": 1,
20
+ "pretraining_tp": 1,
21
+ "quantization_config": {
22
+ "_load_in_4bit": false,
23
+ "_load_in_8bit": true,
24
+ "bnb_4bit_compute_dtype": "float32",
25
+ "bnb_4bit_quant_storage": "uint8",
26
+ "bnb_4bit_quant_type": "fp4",
27
+ "bnb_4bit_use_double_quant": false,
28
+ "llm_int8_enable_fp32_cpu_offload": false,
29
+ "llm_int8_has_fp16_weight": false,
30
+ "llm_int8_skip_modules": null,
31
+ "llm_int8_threshold": 6.0,
32
+ "load_in_4bit": false,
33
+ "load_in_8bit": true,
34
+ "quant_method": "bitsandbytes"
35
+ },
36
+ "rope_scaling": null,
37
+ "rope_theta": 10000.0,
38
+ "tie_word_embeddings": true,
39
+ "torch_dtype": "bfloat16",
40
+ "transformers_version": "4.46.2",
41
+ "use_cache": true,
42
+ "vocab_size": 50304
43
+ }
model_after_8-bit_quantization/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 0,
4
+ "pad_token_id": 1,
5
+ "transformers_version": "4.46.2"
6
+ }
model_after_8-bit_quantization/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21b3f9594b3f4a9c7985c7121be05eb963cb05bbacfdaf56cb568ac8f6f8ffd5
3
+ size 1281527448
model_after_nf-4_quantization/README.md ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ ---
2
+ license: mit
3
+ ---
model_after_nf-4_quantization/config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/OLMo-1B-hf",
3
+ "architectures": [
4
+ "OlmoForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "clip_qkv": null,
9
+ "eos_token_id": 50279,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "olmo",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 16,
18
+ "num_key_value_heads": 16,
19
+ "pad_token_id": 1,
20
+ "pretraining_tp": 1,
21
+ "quantization_config": {
22
+ "_load_in_4bit": true,
23
+ "_load_in_8bit": false,
24
+ "bnb_4bit_compute_dtype": "bfloat16",
25
+ "bnb_4bit_quant_storage": "uint8",
26
+ "bnb_4bit_quant_type": "nf4",
27
+ "bnb_4bit_use_double_quant": false,
28
+ "llm_int8_enable_fp32_cpu_offload": false,
29
+ "llm_int8_has_fp16_weight": false,
30
+ "llm_int8_skip_modules": null,
31
+ "llm_int8_threshold": 6.0,
32
+ "load_in_4bit": true,
33
+ "load_in_8bit": false,
34
+ "quant_method": "bitsandbytes"
35
+ },
36
+ "rope_scaling": null,
37
+ "rope_theta": 10000.0,
38
+ "tie_word_embeddings": true,
39
+ "torch_dtype": "bfloat16",
40
+ "transformers_version": "4.46.2",
41
+ "use_cache": true,
42
+ "vocab_size": 50304
43
+ }
model_after_nf-4_quantization/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 0,
4
+ "pad_token_id": 1,
5
+ "transformers_version": "4.46.2"
6
+ }
model_after_nf-4_quantization/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d3132002cd21ed338a8ed3f4ced7c6345e497794b4813183640e3f0c900d918
3
+ size 810094552