Hugging Face's logo

unsloth
/
r1-1776-distill-llama-70b-GGUF

Text Generation
Transformers
GGUF
English
llama
deepseek
deepseek_v3
unsloth
Inference Endpoints
conversational
Model card Files Community
danielhanchen commited on
Commit
de533d8
·
verified ·
1 Parent(s): 3daed66

Add files using upload-large-folder tool

Browse files
Files changed (12) hide show
  1. .gitattributes +10 -0
  2. BF16/r1-1776-distill-llama-70b.BF16-00001-of-00003.gguf +3 -0
  3. BF16/r1-1776-distill-llama-70b.BF16-00002-of-00003.gguf +3 -0
  4. BF16/r1-1776-distill-llama-70b.BF16-00003-of-00003.gguf +3 -0
  5. Q8_0/r1-1776-distill-llama-70b.Q8_0-00001-of-00002.gguf +3 -0
  6. Q8_0/r1-1776-distill-llama-70b.Q8_0-00002-of-00002.gguf +3 -0
  7. config.json +38 -0
  8. r1-1776-distill-llama-70b-Q2_K.gguf +3 -0
  9. r1-1776-distill-llama-70b-Q2_K_L.gguf +3 -0
  10. r1-1776-distill-llama-70b-Q3_K_M.gguf +3 -0
  11. r1-1776-distill-llama-70b-Q4_K_M.gguf +3 -0
  12. r1-1776-distill-llama-70b-Q5_K_M.gguf +3 -0
.gitattributes CHANGED
@@ -33,3 +33,13 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ r1-1776-distill-llama-70b-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
37
+ r1-1776-distill-llama-70b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
38
+ r1-1776-distill-llama-70b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
39
+ r1-1776-distill-llama-70b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
40
+ r1-1776-distill-llama-70b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
41
+ BF16/r1-1776-distill-llama-70b.BF16-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
42
+ BF16/r1-1776-distill-llama-70b.BF16-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
43
+ BF16/r1-1776-distill-llama-70b.BF16-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Q8_0/r1-1776-distill-llama-70b.Q8_0-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Q8_0/r1-1776-distill-llama-70b.Q8_0-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
BF16/r1-1776-distill-llama-70b.BF16-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b576a2d534afcdfb5809d3b2bf0cd5ee6adeb0c085d677ff0a32123ae8f712e0
3
+ size 49875751520
BF16/r1-1776-distill-llama-70b.BF16-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d07731ea1dfd11729c5b51d807bf2fd1571b14dd41ee7f6b376034549fa1e48b
3
+ size 49779916256
BF16/r1-1776-distill-llama-70b.BF16-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7c2eb8c514a14fe6ae80e22747702d1af7c6f117bec226b9a00fddaa763722c
3
+ size 41462247744
Q8_0/r1-1776-distill-llama-70b.Q8_0-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d34f94b5c827d5939081f49bc14b078b736476fca04208cf3239e35cf57da67
3
+ size 49809934368
Q8_0/r1-1776-distill-llama-70b.Q8_0-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d8f7a8508d8b4cbc2b136f2d443d049fb308ea716fd7287135d56a6ebcbd7c9
3
+ size 25165117664
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "perplexity-ai/r1-1776-distill-llama-70b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 8192,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 28672,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 64,
19
+ "num_hidden_layers": 80,
20
+ "num_key_value_heads": 8,
21
+ "pad_token_id": 128004,
22
+ "pretraining_tp": 1,
23
+ "rms_norm_eps": 1e-05,
24
+ "rope_scaling": {
25
+ "factor": 8.0,
26
+ "high_freq_factor": 4.0,
27
+ "low_freq_factor": 1.0,
28
+ "original_max_position_embeddings": 8192,
29
+ "rope_type": "llama3"
30
+ },
31
+ "rope_theta": 500000.0,
32
+ "tie_word_embeddings": false,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.50.0.dev0",
35
+ "unsloth_fixed": true,
36
+ "use_cache": true,
37
+ "vocab_size": 128256
38
+ }
r1-1776-distill-llama-70b-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13028e900b0b850b75477daf6a0e34728f24f70396ca72adccf2d467f295e992
3
+ size 26375110720
r1-1776-distill-llama-70b-Q2_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85fcd71de26a1457ba86568381ba9686ca3532f9b58672ce5c96f0298ef505c0
3
+ size 26621362240
r1-1776-distill-llama-70b-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e55705829059ccac96163cd456c324b9227b312850c82d12762c9331709d4a58
3
+ size 42520395840
r1-1776-distill-llama-70b-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e55705829059ccac96163cd456c324b9227b312850c82d12762c9331709d4a58
3
+ size 42520395840
r1-1776-distill-llama-70b-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e55705829059ccac96163cd456c324b9227b312850c82d12762c9331709d4a58
3
+ size 42520395840