Not working for me.

#5
by ZeroWw - opened
prompt="""
Tell me the difference between thinking in humans and in LLMs.
"""
m=f'{model_name}.{q_type}.gguf'
!./build/bin/llama-cli -no-cnv --ignore-eos -c 4096 -m /content/$m -t $(nproc) -ngl 999 -p "User: Hi\nBot:Hi\nUser: {prompt}\nBot:"

output:

load_backend: loaded RPC backend from /content/build/bin/libggml-rpc.so
load_backend: loaded CPU backend from /content/build/bin/libggml-cpu-haswell.so
build: 5662 (fb85a288) with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
main: llama backend init
main: load the model and apply lora adapter, if any
llama_model_loader: loaded meta data with 35 key-value pairs and 339 tensors from /content/OpenThinker3-7B.q8_0.gguf (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = qwen2
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = OpenThinker3 7B
llama_model_loader: - kv   3:                           general.basename str              = OpenThinker3
llama_model_loader: - kv   4:                         general.size_label str              = 7B
llama_model_loader: - kv   5:                            general.license str              = apache-2.0
llama_model_loader: - kv   6:                   general.base_model.count u32              = 1
llama_model_loader: - kv   7:                  general.base_model.0.name str              = Qwen2.5 7B Instruct
llama_model_loader: - kv   8:          general.base_model.0.organization str              = Qwen
llama_model_loader: - kv   9:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen2.5-7...
llama_model_loader: - kv  10:                      general.dataset.count u32              = 1
llama_model_loader: - kv  11:                     general.dataset.0.name str              = OpenThoughts3 1.2M
llama_model_loader: - kv  12:             general.dataset.0.organization str              = Open Thoughts
llama_model_loader: - kv  13:                 general.dataset.0.repo_url str              = https://huggingface.co/open-thoughts/...
llama_model_loader: - kv  14:                               general.tags arr[str,4]       = ["llama-factory", "full", "generated_...
llama_model_loader: - kv  15:                          qwen2.block_count u32              = 28
llama_model_loader: - kv  16:                       qwen2.context_length u32              = 32768
llama_model_loader: - kv  17:                     qwen2.embedding_length u32              = 3584
llama_model_loader: - kv  18:                  qwen2.feed_forward_length u32              = 18944
llama_model_loader: - kv  19:                 qwen2.attention.head_count u32              = 28
llama_model_loader: - kv  20:              qwen2.attention.head_count_kv u32              = 4
llama_model_loader: - kv  21:                       qwen2.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  22:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  28:                tokenizer.ggml.eos_token_id u32              = 151643
llama_model_loader: - kv  29:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  30:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  31:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  32:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  33:               general.quantization_version u32              = 2
llama_model_loader: - kv  34:                          general.file_type u32              = 7
llama_model_loader: - type  f32:  141 tensors
llama_model_loader: - type  f16:    2 tensors
llama_model_loader: - type q8_0:  196 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q8_0
print_info: file size   = 8.49 GiB (9.57 BPW) 
load: special tokens cache size = 22
load: token to piece cache size = 0.9310 MB
print_info: arch             = qwen2
print_info: vocab_only       = 0
print_info: n_ctx_train      = 32768
print_info: n_embd           = 3584
print_info: n_layer          = 28
print_info: n_head           = 28
print_info: n_head_kv        = 4
print_info: n_rot            = 128
print_info: n_swa            = 0
print_info: is_swa_any       = 0
print_info: n_embd_head_k    = 128
print_info: n_embd_head_v    = 128
print_info: n_gqa            = 7
print_info: n_embd_k_gqa     = 512
print_info: n_embd_v_gqa     = 512
print_info: f_norm_eps       = 0.0e+00
print_info: f_norm_rms_eps   = 1.0e-06
print_info: f_clamp_kqv      = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale    = 0.0e+00
print_info: f_attn_scale     = 0.0e+00
print_info: n_ff             = 18944
print_info: n_expert         = 0
print_info: n_expert_used    = 0
print_info: causal attn      = 1
print_info: pooling type     = -1
print_info: rope type        = 2
print_info: rope scaling     = linear
print_info: freq_base_train  = 1000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn  = 32768
print_info: rope_finetuned   = unknown
print_info: ssm_d_conv       = 0
print_info: ssm_d_inner      = 0
print_info: ssm_d_state      = 0
print_info: ssm_dt_rank      = 0
print_info: ssm_dt_b_c_rms   = 0
print_info: model type       = 7B
print_info: model params     = 7.62 B
print_info: general.name     = OpenThinker3 7B
print_info: vocab type       = BPE
print_info: n_vocab          = 152064
print_info: n_merges         = 151387
print_info: BOS token        = 151643 '<|endoftext|>'
print_info: EOS token        = 151643 '<|endoftext|>'
print_info: EOT token        = 151645 '<|im_end|>'
print_info: PAD token        = 151643 '<|endoftext|>'
print_info: LF token         = 198 'Ċ'
print_info: FIM PRE token    = 151659 '<|fim_prefix|>'
print_info: FIM SUF token    = 151661 '<|fim_suffix|>'
print_info: FIM MID token    = 151660 '<|fim_middle|>'
print_info: FIM PAD token    = 151662 '<|fim_pad|>'
print_info: FIM REP token    = 151663 '<|repo_name|>'
print_info: FIM SEP token    = 151664 '<|file_sep|>'
print_info: EOG token        = 151643 '<|endoftext|>'
print_info: EOG token        = 151645 '<|im_end|>'
print_info: EOG token        = 151662 '<|fim_pad|>'
print_info: EOG token        = 151663 '<|repo_name|>'
print_info: EOG token        = 151664 '<|file_sep|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 28 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 29/29 layers to GPU
load_tensors:   CPU_Mapped model buffer size =  8692.21 MiB
...............................................................................
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 4096
llama_context: n_ctx_per_seq = 4096
llama_context: n_batch       = 2048
llama_context: n_ubatch      = 512
llama_context: causal_attn   = 1
llama_context: flash_attn    = 0
llama_context: freq_base     = 1000000.0
llama_context: freq_scale    = 1
llama_context: n_ctx_per_seq (4096) < n_ctx_train (32768) -- the full capacity of the model will not be utilized
llama_context:        CPU  output buffer size =     0.58 MiB
llama_kv_cache_unified:        CPU KV buffer size =   224.00 MiB
llama_kv_cache_unified: size =  224.00 MiB (  4096 cells,  28 layers,  1 seqs), K (f16):  112.00 MiB, V (f16):  112.00 MiB
llama_context:        CPU compute buffer size =   304.00 MiB
llama_context: graph nodes  = 1098
llama_context: graph splits = 1
common_init_from_params: added <|endoftext|> logit bias = -inf
common_init_from_params: added <|im_end|> logit bias = -inf
common_init_from_params: added <|fim_pad|> logit bias = -inf
common_init_from_params: added <|repo_name|> logit bias = -inf
common_init_from_params: added <|file_sep|> logit bias = -inf
common_init_from_params: setting dry_penalty_last_n to ctx_size = 4096
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
main: llama threadpool init, n_threads = 2

system_info: n_threads = 2 (n_threads_batch = 2) / 2 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | BMI2 = 1 | LLAMAFILE = 1 | OPENMP = 1 | REPACK = 1 | 

sampler seed: 484452917
sampler params: 
    repeat_last_n = 64, repeat_penalty = 1.000, frequency_penalty = 0.000, presence_penalty = 0.000
    dry_multiplier = 0.000, dry_base = 1.750, dry_allowed_length = 2, dry_penalty_last_n = 4096
    top_k = 40, top_p = 0.950, min_p = 0.050, xtc_probability = 0.000, xtc_threshold = 0.100, typical_p = 1.000, top_n_sigma = -1.000, temp = 0.800
    mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
sampler chain: logits -> logit-bias -> penalties -> dry -> top-n-sigma -> top-k -> typical -> top-p -> min-p -> xtc -> temp-ext -> dist 
generate: n_ctx = 4096, n_batch = 2048, n_predict = -1, n_keep = 0

User: Hi
Bot:Hi
User: 
Tell me the difference between thinking in humans and in LLMs.

Bot:Hi
Bot:Hi
Bot:Hi
Bot:Hi
Bot:Hi
Bot:Hi
Bot:Hi
Bot:Hi
Bot:Hi
Bot:
llama_perf_sampler_print:    sampling time =       7.82 ms /    63 runs   (    0.12 ms per token,  8057.30 tokens per second)
llama_perf_context_print:        load time =   38022.97 ms
llama_perf_context_print: prompt eval time =    5862.03 ms /    27 tokens (  217.11 ms per token,     4.61 tokens per second)
llama_perf_context_print:        eval time =   16124.32 ms /    35 runs   (  460.69 ms per token,     2.17 tokens per second)
llama_perf_context_print:       total time =   22301.56 ms /    62 tokens
Interrupted by user

In theory it works for me, but i get endless thinking..but never ends. ( rational thinking.. but endless )

Open Thoughts org

Hi, I think you're missing the chat template? That should make it better :)

Sign up or log in to comment