Hugging Face's logo

deepcogito
/
cogito-671b-v2.1

Text Generation
Transformers
Safetensors
deepseek_v3
conversational
custom_code
text-generation-inference
Model card Files
xet
Community
1
drishanarora commited on
Commit
36240f9
·
verified ·
1 Parent(s): 6754120

Add files using upload-large-folder tool

Browse files
Files changed (50) hide show
  1. README.md +5 -0
  2. chat_template.jinja +107 -0
  3. config.json +65 -0
  4. model-00001-of-00270.safetensors +3 -0
  5. model-00003-of-00270.safetensors +3 -0
  6. model-00005-of-00270.safetensors +3 -0
  7. model-00011-of-00270.safetensors +3 -0
  8. model-00012-of-00270.safetensors +3 -0
  9. model-00015-of-00270.safetensors +3 -0
  10. model-00017-of-00270.safetensors +3 -0
  11. model-00020-of-00270.safetensors +3 -0
  12. model-00021-of-00270.safetensors +3 -0
  13. model-00024-of-00270.safetensors +3 -0
  14. model-00025-of-00270.safetensors +3 -0
  15. model-00026-of-00270.safetensors +3 -0
  16. model-00032-of-00270.safetensors +3 -0
  17. model-00033-of-00270.safetensors +3 -0
  18. model-00047-of-00270.safetensors +3 -0
  19. model-00051-of-00270.safetensors +3 -0
  20. model-00056-of-00270.safetensors +3 -0
  21. model-00058-of-00270.safetensors +3 -0
  22. model-00064-of-00270.safetensors +3 -0
  23. model-00066-of-00270.safetensors +3 -0
  24. model-00071-of-00270.safetensors +3 -0
  25. model-00074-of-00270.safetensors +3 -0
  26. model-00075-of-00270.safetensors +3 -0
  27. model-00076-of-00270.safetensors +3 -0
  28. model-00091-of-00270.safetensors +3 -0
  29. model-00107-of-00270.safetensors +3 -0
  30. model-00112-of-00270.safetensors +3 -0
  31. model-00118-of-00270.safetensors +3 -0
  32. model-00119-of-00270.safetensors +3 -0
  33. model-00125-of-00270.safetensors +3 -0
  34. model-00132-of-00270.safetensors +3 -0
  35. model-00135-of-00270.safetensors +3 -0
  36. model-00146-of-00270.safetensors +3 -0
  37. model-00153-of-00270.safetensors +3 -0
  38. model-00164-of-00270.safetensors +3 -0
  39. model-00187-of-00270.safetensors +3 -0
  40. model-00192-of-00270.safetensors +3 -0
  41. model-00212-of-00270.safetensors +3 -0
  42. model-00218-of-00270.safetensors +3 -0
  43. model-00219-of-00270.safetensors +3 -0
  44. model-00222-of-00270.safetensors +3 -0
  45. model-00238-of-00270.safetensors +3 -0
  46. model-00259-of-00270.safetensors +3 -0
  47. model.safetensors.index.json +0 -0
  48. special_tokens_map.json +23 -0
  49. tokenizer.json +0 -0
  50. tokenizer_config.json +0 -0
README.md ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ ---
4
+ # cogito-671b-v2.1-m4
5
+ This is experimental checkpoint 4 for Cogito v2.1. More details in the experiment doc.
chat_template.jinja ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {# ==================================================================== #}
2
+ {# Deepseek v3 template with enable_thinking and tools support #}
3
+ {# ==================================================================== #}
4
+ {%- if not enable_thinking is defined %}{% set enable_thinking = false %}{% endif -%}
5
+ {%- if not tools is defined %}{% set tools = none %}{% endif -%}
6
+ {%- if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif -%}
7
+
8
+ {# --------------------------- Collect system prompt -------------------- #}
9
+ {%- set ns = namespace(system_prompt='', is_last_user=false, outputs_open=false, first_output=true) -%}
10
+
11
+ {%- if messages and messages[0].role == 'system' -%}
12
+ {%- set raw = messages[0].content -%}
13
+ {%- set ns.system_prompt = raw if raw is string else raw[0].text -%}
14
+ {%- set messages = messages[1:] -%}
15
+ {%- endif -%}
16
+
17
+ {# --------------------------- Inject deep thinking --------------------- #}
18
+ {%- if enable_thinking -%}
19
+ {%- set ns.system_prompt = ns.system_prompt and 'Enable deep thinking subroutine.
20
+
21
+ ' ~ ns.system_prompt or 'Enable deep thinking subroutine.' -%}
22
+ {%- endif -%}
23
+
24
+ {# --------------------------- Append tools block ----------------------- #}
25
+ {%- if tools is not none -%}
26
+ {%- if ns.system_prompt -%}
27
+ {%- set ns.system_prompt = ns.system_prompt ~ '
28
+
29
+ You have the following functions available:
30
+
31
+ ' -%}
32
+ {%- else -%}
33
+ {%- set ns.system_prompt = 'You have the following functions available:
34
+
35
+ ' -%}
36
+ {%- endif -%}
37
+ {%- for t in tools -%}
38
+ {%- set ns.system_prompt = ns.system_prompt ~ "```json
39
+ " ~ (t | tojson(indent=4)) ~ "
40
+ ```
41
+
42
+ " -%}
43
+ {%- endfor -%}
44
+ {%- endif -%}
45
+
46
+ {{- bos_token -}}{{- ns.system_prompt -}}
47
+
48
+ {# --------------------------- Iterate conversation --------------------- #}
49
+ {%- for m in messages -%}
50
+ {# --------------------------- USER ---------------------------------- #}
51
+ {%- if m.role == 'user' -%}
52
+ {%- set ns.is_last_user = true -%}
53
+ {%- set txt = m.content if m.content is string else m.content | selectattr('type','equalto','text') | map(attribute='text') | join('') -%}
54
+ {{- "<｜User｜>" -}}{{- txt -}}{{- "<｜Assistant｜>" -}}
55
+ {%- endif -%}
56
+
57
+ {# --------------------------- ASSISTANT with TOOL CALLS -------------- #}
58
+ {%- if m.role == 'assistant' and m.tool_calls is defined and m.tool_calls -%}
59
+ {%- set ns.is_last_user = false -%}
60
+ {%- set lead = m.content is string and m.content|trim or (m.content and m.content | selectattr('type','equalto','text') | map(attribute='text') | join('')) or '' -%}
61
+ {{- lead -}}{{- "<｜tool▁calls▁begin｜>" -}}
62
+ {%- for call in m.tool_calls -%}
63
+ {{- "<｜tool▁call▁begin｜>" -}}{{- call.type -}}{{- "<｜tool▁sep｜>" -}}{{- call.function.name -}}
64
+ {{- "
65
+ ```json
66
+ " -}}{{- call.function.arguments -}}{{- "
67
+ ```" -}}{{- "<｜tool▁call▁end｜>" -}}
68
+ {%- if not loop.last -%}{{- "
69
+ " -}}{%- endif -%}
70
+ {%- endfor -%}
71
+ {{- "<｜tool▁calls▁end｜>" -}}{{- "<｜end▁of▁sentence｜>" -}}
72
+ {%- endif -%}
73
+
74
+ {# --------------------------- ASSISTANT plain ------------------------ #}
75
+ {%- if m.role == 'assistant' and (m.tool_calls is not defined or not m.tool_calls) -%}
76
+ {%- set ns.is_last_user = false -%}
77
+ {%- set txt = m.content if m.content is string else m.content | selectattr('type','equalto','text') | map(attribute='text') | join('') -%}
78
+ {{- txt -}}{{- "<｜end▁of▁sentence｜>" -}}
79
+ {%- endif -%}
80
+
81
+ {# --------------------------- TOOL output ---------------------------- #}
82
+ {%- if m.role == 'tool' -%}
83
+ {%- set ns.is_last_user = false -%}
84
+ {%- set out_txt = m.content if m.content is string else m.content | selectattr('type','equalto','text') | map(attribute='text') | join('') -%}
85
+ {%- if not ns.outputs_open -%}
86
+ {{- "<｜tool▁outputs▁begin｜>" -}}
87
+ {%- set ns.outputs_open = true -%}
88
+ {%- endif -%}
89
+ {{- "<｜tool▁output▁begin｜>" -}}{{- out_txt -}}{{- "<｜tool▁output▁end｜>" -}}
90
+ {%- if loop.nextitem is defined and loop.nextitem.role == 'tool' -%}
91
+ {{- "
92
+ " -}}
93
+ {%- endif -%}
94
+ {%- if loop.nextitem is undefined or loop.nextitem.role != 'tool' -%}
95
+ {{- "<｜tool▁outputs▁end｜>" -}}
96
+ {%- set ns.outputs_open = false -%}
97
+ {%- endif -%}
98
+ {%- endif -%}
99
+ {%- endfor -%}
100
+
101
+ {%- if ns.outputs_open -%}
102
+ {{- "<｜tool▁outputs▁end｜>" -}}
103
+ {%- endif -%}
104
+
105
+ {%- if add_generation_prompt and not ns.is_last_user -%}
106
+ {{- "<｜Assistant｜>" -}}
107
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DeepseekV3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_deepseek.DeepseekV3Config",
9
+ "AutoModel": "modeling_deepseek.DeepseekV3Model",
10
+ "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
11
+ },
12
+ "aux_loss_alpha": 0.001,
13
+ "bos_token_id": 0,
14
+ "dtype": "bfloat16",
15
+ "eos_token_id": 1,
16
+ "ep_size": 1,
17
+ "first_k_dense_replace": 3,
18
+ "head_dim": 64,
19
+ "hidden_act": "silu",
20
+ "hidden_size": 7168,
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 18432,
23
+ "kv_lora_rank": 512,
24
+ "max_position_embeddings": 163840,
25
+ "model_type": "deepseek_v3",
26
+ "moe_intermediate_size": 2048,
27
+ "moe_layer_freq": 1,
28
+ "n_group": 8,
29
+ "n_routed_experts": 256,
30
+ "n_shared_experts": 1,
31
+ "norm_topk_prob": true,
32
+ "num_attention_heads": 128,
33
+ "num_experts_per_tok": 8,
34
+ "num_hidden_layers": 61,
35
+ "num_key_value_heads": 128,
36
+ "num_nextn_predict_layers": 1,
37
+ "pretraining_tp": 1,
38
+ "q_lora_rank": 1536,
39
+ "qk_head_dim": 192,
40
+ "qk_nope_head_dim": 128,
41
+ "qk_rope_head_dim": 64,
42
+ "rms_norm_eps": 1e-06,
43
+ "rope_interleave": true,
44
+ "rope_scaling": {
45
+ "beta_fast": 32.0,
46
+ "beta_slow": 1.0,
47
+ "factor": 40.0,
48
+ "mscale": 1.0,
49
+ "mscale_all_dim": 1.0,
50
+ "original_max_position_embeddings": 4096,
51
+ "rope_type": "yarn",
52
+ "type": "yarn"
53
+ },
54
+ "rope_theta": 10000,
55
+ "routed_scaling_factor": 2.5,
56
+ "scoring_func": "sigmoid",
57
+ "seq_aux": true,
58
+ "tie_word_embeddings": false,
59
+ "topk_group": 4,
60
+ "topk_method": "noaux_tc",
61
+ "transformers_version": "4.57.1",
62
+ "use_cache": true,
63
+ "v_head_dim": 128,
64
+ "vocab_size": 128815
65
+ }
model-00001-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e2719d99bbc184bab59e92ea91402bb666dd5439dd6ba1c0bbee92a5fb01ff4
3
+ size 4860366560
model-00003-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e1dcf7defff399e9c4a4bbd11b07b7ceab1cc62362895b3bc6c4c87a4c800c8
3
+ size 4991243184
model-00005-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:848ec3c1493da0b8ac24fc28b395fead0975b34260aeb2ff786a43ecedeb0790
3
+ size 4991243064
model-00011-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13992fc00bf159df9d3e1eedd280e56a3825075995e50b030a329b74be51cf10
3
+ size 4987474984
model-00012-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d19d5f9be7186b3f0c5416761a44734c61d404f8ba2fabd56dcc1d9ec0264de2
3
+ size 4991243184
model-00015-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5fea0585c15eddae14a7d86a43fc96a3c5ffce254e1d867b64a27a81a748a01
3
+ size 4973826792
model-00017-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:096364cbd6d4810e2317b017f76cccd4f51e83d73aea7ff8f312fd175ce266a7
3
+ size 4991243184
model-00020-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09bc6c862b64e4bdeb8a686f5b8d647d1137b097441186003901283c4403bc02
3
+ size 4987474944
model-00021-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:766803556ca2709f1dab226cfba899f66818d82c4fb72cb2915dd02adbeac552
3
+ size 4991243184
model-00024-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc913d9bd9b0b113d4de0e17b70bb034b87066f820a60c8fb3f0da210eabc93b
3
+ size 4991243008
model-00025-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f42ef8df73d318f009d5eb1046893778216b7241e246d988ab4ddb63c5e8bc8
3
+ size 4987475008
model-00026-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d770b65673a2ff6e55125dbf7da2fd3b2587d5f33be6a822bfe62e7e185af11
3
+ size 4991243184
model-00032-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e5571de9e62fdbca1b92dd2df33e46b9683879be16f203fa3f43761538c3172
3
+ size 4991243184
model-00033-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e2a6bdd16b41877ef7f90f9ef1a5ca694c7a056e23ff50927e1210a61575987
3
+ size 4991243016
model-00047-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b4c45851d310ba9eb91c2e576a765db6e8ae01ae9fc6b5fff850faead660952
3
+ size 4991243008
model-00051-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a7790dc76cd89c1d9d44414c68985ed36f2a47d0bb53ae88318be4ecd35c9da
3
+ size 4991243128
model-00056-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cea67ab8d0f1f1467090d330a701986e5674a34210afd365828463e7844c772f
3
+ size 4991243064
model-00058-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6d619723be99bb403c1a7cfe924941ce0741838fb15d825ceeeeedfc14e476a
3
+ size 4991243184
model-00064-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45e65cb2cdfe92680a1b06755290ce791fd3c6a3588fbb26fc24d0e879653242
3
+ size 4991243176
model-00066-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec584e015ac4843a22a6fef8ee27ab157c9040c32434e51fcbe0a79df06b84a6
3
+ size 4860580080
model-00071-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae1cb2794069bea70e747cb4c62a0682d6717ffeac4e516a0d3ce3ac0e2663c0
3
+ size 4987474944
model-00074-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02dcd33343c377203889b11b9bc9c6587ae10739173d876f5b4e9ace5f274213
3
+ size 4991243144
model-00075-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54978398fbd2ce267ec70de739b2e1b945cd30ac34bdd74a596f206a690ce9d0
3
+ size 4991243016
model-00076-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4374cfeaa1a98a457bb8b69fc6e16f2e3966e9a58f0a8bf768d46785d08ffab1
3
+ size 4987475008
model-00091-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2ba121db7aaf08468311e854668a6c7025aad46649c42ee659684dd780dc868
3
+ size 4991243184
model-00107-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:425336f78d3dd4f2ccba7ba3c907e3c9d9ecdc01bc6a89d21e51b3727a8620a9
3
+ size 4991243024
model-00112-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eaa5ccc7f3f89de180a5ff63b8dd34ae6b2727597df8b98da10836ba745a8f7
3
+ size 4991243016
model-00118-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:450a05ff1f4f65b696643048d0c4c4dca11d0ead29fcbe35bbb4262e8ec15c8b
3
+ size 4991243184
model-00119-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:069dd0d4450fcb95a676212e577f3837189cfacccb68ab50ee2e0b58942f7a97
3
+ size 4991243176
model-00125-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1db4f822e3c129ba02b0b6ee247ec721fa40c64011c9aaa278ad06f08ccba3c3
3
+ size 4991243096
model-00132-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0781aa4c926e1db1ca91cfe80de3c9728098c3f676b5e0f3a793233a0682a46a
3
+ size 4991243184
model-00135-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0c7d1b739b663fd3c80e29fe92d787e93962d577584f2e64195c74559adb97b
3
+ size 4991243016
model-00146-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:203de5a2ede6955f2a62089d50ce2744c4bc342aa2db9b96917a3e76cb1061a9
3
+ size 4991243008
model-00153-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52f21aa604742c835d62cc815b5c220a54b9c2b360b94c1cd2de4cc8d81521aa
3
+ size 4991243048
model-00164-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:257be94a7784d73f4a2418ea2675d9e59f50693e08916aa6955149376e1258cb
3
+ size 4991243184
model-00187-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e06932e7b028aa375ba3336745cbab0c1a6662ac1a63d2a73b96188f75d40af4
3
+ size 4971336728
model-00192-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3acb598a3c0811c3ae94e8073b1f9603d553aeb49a2b6a167b20d3f39d309b05
3
+ size 4991243184
model-00212-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efb001183a036fb5d36aa6c53063fe7e78750c12d1d7e0a4dd12534522a3f5a8
3
+ size 4991243176
model-00218-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f118f5c7787f9549df8f13dda7a973a1533d90e912d7521abd1c8af13c74e849
3
+ size 4991243008
model-00219-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdad03a6feaa6705f8ecf0f8c038230f6f86088fe0b6de1a017fdbf4f8b60257
3
+ size 4987475000
model-00222-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffb75e669c132cbd8e0d239915886ec537a725409cfaafe2d7618e19f03ccf06
3
+ size 4991243088
model-00238-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f57ce4935d1a18e535dfe8ec6ef8150b3e20249fe54c2b6fdef4f8cdb9c88c21
3
+ size 4991243184
model-00259-of-00270.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83fe152c9280e73e03f1d5ef3bed684cfe4699f024efd605917d4f37ec17ace2
3
+ size 4991242904
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<｜begin▁of▁sentence｜>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<｜end▁of▁sentence｜>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<｜▁pad▁｜>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff